Search

In recent years, the research pertaining to speech recognition technology in the Kazakh language has gained significant importance. This is due to the increasing demand for natural language processing applications in the region where Kazakh is predominantly spoken. Thus, there exists an urgent requirement for precise and dependable speech recognition systems. The research study examines the application of sophisticated deep learning methodologies, such as Natural Language Processing (NLP) and Hidden Markov Model (HMM), in facilitating speech recognition for the Kazakh language. Additionally, the investigation delves into how various techniques, including data preprocessing, acoustic modeling, and language modeling, can aid in devising effective speech recognition systems. The article deliberates on the feasible uses of speech recognition technology in the geographic area where Kazakh language is spoken and outlines its future research prospects. The investigation underscores the significance of persistent inquiry in this realm to confront distinctive obstacles encountered in creating speech recognition systems for languages with restricted resources. [ABSTRACT FROM AUTHOR]

Voice isolation, a prominent research area in the field of speech processing, has garnered a great deal of attention due to its prospective implications in numerous domains. Deep neural networks (DNNs) have emerged as a potent instrument for addressing the challenges associated with vocal isolation. This paper presents a comprehensive study on the use of DNNs for voice isolation, focusing on speech recognition and speaker identification tasks. The proposed method uses frequency domain and time domain techniques to improve the separation of target utterances from background noise. The experimental results demonstrate the efficacy of the proposed method, revealing substantial improvements in voice isolation precision and robustness. This study's findings contribute to the increasing corpus of research on voice isolation techniques and provide valuable insights into the application of DNNs to improve speech processing tasks . [ABSTRACT FROM AUTHOR]

Automatic speech recognition (ASR) is one of the ways used to transform acoustic speech signals into text. Over the last few decades, an enormous amount of research work has been done in the research area of speech recognition (SR). However, most studies have focused on building ASR systems based on adult speech. The recognition of children's speech was neglected for some time, which means that the field of children's SR research is wide open. Children's SR is a challenging task due to the large variations in children's articulatory, acoustic, physical, and linguistic characteristics compared to adult speech. Thus, the field became a very attractive area of research and it is important to understand where the main center of attention is, and what are the most widely used methods for extracting acoustic features, various acoustic models, speech datasets, the SR toolkits used during the recognition process, and so on. ASR systems or interfaces are extensively used and integrated into various real-life applications, such as search engines, the healthcare industry, biometric analysis, car systems, the military, aids for people with disabilities, and mobile devices. A systematic literature review (SLR) is presented in this work by extracting the relevant information from 76 research papers published from 2009 to 2020 in the field of ASR for children. The objective of this review is to throw light on the trends of research in children's speech recognition and analyze the potential of trending techniques to recognize children's speech. [ABSTRACT FROM AUTHOR]

This study aims to address the deviation in downstream tasks caused by inaccurate recognition results when applying Automatic Speech Recognition (ASR) technology in the Air Traffic Control (ATC) field. This paper presents a novel cascaded model architecture, namely Conformer-CTC/Attention-T5 (CCAT), to build a highly accurate and robust ATC speech recognition model. To tackle the challenges posed by noise and fast speech rate in ATC, the Conformer model is employed to extract robust and discriminative speech representations from raw waveforms. On the decoding side, the Attention mechanism is integrated to facilitate precise alignment between input features and output characters. The Text-To-Text Transfer Transformer (T5) language model is also introduced to handle particular pronunciations and code-mixing issues, providing more accurate and concise textual output for downstream tasks. To enhance the model’s robustness, transfer learning and data augmentation techniques are utilized in the training strategy. The model’s performance is optimized by performing hyperparameter tunings, such as adjusting the number of attention heads, encoder layers, and the weights of the loss function. The experimental results demonstrate the significant contributions of data augmentation, hyperparameter tuning, and error correction models to the overall model performance. On the Our ATC Corpus dataset, the proposed model achieves a Character Error Rate (CER) of 3.44%, representing a 3.64% improvement compared to the baseline model. Moreover, the effectiveness of the proposed model is validated on two publicly available datasets. On the AISHELL-1 dataset, the CCAT model achieves a CER of 3.42%, showcasing a 1.23% improvement over the baseline model. Similarly, on the LibriSpeech dataset, the CCAT model achieves a Word Error Rate (WER) of 5.27%, demonstrating a performance improvement of 7.67% compared to the baseline model. Additionally, this paper proposes an evaluation criterion for assessing the robustness of ATC speech recognition systems. In robustness evaluation experiments based on this criterion, the proposed model demonstrates a performance improvement of 22% compared to the baseline model. [ABSTRACT FROM AUTHOR]

Traditional sentiment analysis focuses on text-level sentiment mining, transforming sentiment mining into classification or regression problems, resulting in a sentiment analysis low accuracy rate. Sentiment analysis refers to the use of natural language processing, text analysis, and computational linguistics to systematically identify, extract, quantify, and study sentimental states. Therefore, more scholars have begun to focus on speech recognition and facial expression recognition research, and extracting and analysing people's sentiment tendencies can improve sentiment recognition accuracy. Traditional single-modal sentiment analysis can no longer meet people's needs. Therefore, this paper proposes a multimodal sentiment analysis method based on the multimodal sentiment analysis method that can obtain more sentimental information sources and help people make better decisions. The experimental results in this paper show that the highest recognition rates of CNN-SVM, RNN-SVM, and CRNN-SVM were 76.8%, 71.2%, and 93.5%, respectively. It can be seen that CRNN-SVM has the highest sentiment tendency recognition rate in deep learning, so it is suitable to apply CRNN-SVM to sentiment tendency analysis system design in this paper. The average accuracy rate of the system designed in this paper was 91%, and the stability was also very strong, which shows that the system designed in this paper is meaningful. The main contribution of this paper is based on the limitations of single-mode emotion analysis. It proposes a multimode emotion analysis method and introduces a convolutional neural network to help people obtain more emotional information sources to meet their needs. [ABSTRACT FROM AUTHOR]

Due to its numerous practical applications, human emotion recognition from speech is now a challenging and demanding research subject for scientists. The Speech databases, speech features, and classifiers are the important factors for recognizing emotions from speech. The availability of suitable emotional speech databases is the first step for Speech Emotion Recognition (SER). This paper presents a comprehensive literature review of emotional speech databases. The availability of appropriate emotional speech databases in all emotions and languages are summarized. A total of 26 papers for the emotional speech database have been reviewed. It determines which speech databases are often used and also identifies popular speech databases and the languages in which the majority of the databases are available. [ABSTRACT FROM AUTHOR]

English speech incorporates numerous features associated with the speaker's emotions, offering valuable cues for emotion recognition. This paper begins by briefly outlining preprocessing approaches for English speech signals. Subsequently, the Mel-frequency cepstral coefficient (MFCC), energy, and short-time zero-crossing rate were chosen as features, and their statistical properties were computed. The resulting 250-dimensional feature fusion was employed as input. A novel approach that combined gated recurrent unit (GRU) and a convolutional neural network (CNN) was designed for emotion recognition. The bidirectional GRU (BiGRU) method was enhanced through jump-joining to create a CNN-Skip-BiGRU model as an emotion recognition method for English speech. Experimental evaluations were conducted using the IEMOCAP dataset. The findings indicated that the fusion features exhibited superior performance in emotion recognition, achieving an unweighted accuracy rate of 70.31% and a weighted accuracy rate of 70.88%. In contrast to models like CNN-long short-term memory (LSTM), the CNN-Skip-BiGRU model demonstrated enhanced discriminative capabilities for different emotions. Moreover, it stood favorably against several existing emotion recognition methods. These results underscore the efficacy of the improved method in English speech emotion identification, suggesting its potential practical applications. [ABSTRACT FROM AUTHOR]

Abstract: The field of automatic speech recognition (ASR) is discussed from the viewpoint of pattern recognition (PR). This tutorial examines the problem area, its methods, successes and failures, focusing on the nature of the speech signal and techniques to accomplish useful data reduction. Comparison is made with other areas of PR. Suggestions are given for areas of future progress. [Copyright &y& Elsevier]

Muslims aim to recite and memorize the Holy Quran correctly. However, traditional recitation verification approaches depend on humans who may not be available. On the other hand, Artificial Intelligence (AI) capabilities assist in developing intelligent recitation verification tools based on speech recognition techniques. This study aims to overview the current state of the intelligent Quran recitation recognition and verification solutions and highlight the related open issues. A systematic literature review was performed on the published paper since 2006 up to date to answer six research questions. The research questions covered the speech recognition techniques and methods used to develop Quran recitation recognition and verification models, the database and tools used, and the existing mobile application supporting real-time intelligent Quran recitation verification services. Based on the review results, a taxonomy of the Quran recitation recognition and verification techniques was generated, including traditional and end-to-end speech recognition methods. Moreover, the limitations of the existing AI-based Quran recitation verification applications were reported. Additionally, the available Quran audio datasets and tools capable of dealing with Quranic speech were identified. In conclusion, several open issues can be addressed in future research, e.g., considering AI-based approaches to ensure sequence recitation and recognize diacritics-based errors. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative technique for creating a cough detection system that relies on speech recognition algorithms. The strategy utilizes the Kaldi platform, which is open source and incorporates a hybrid system of Gaussian Mixture Model-based Hidden Markov Models (GMM-HMM) through a straightforward monophone training model. Additionally, the study examines the effectiveness of two different feature extraction approaches, Mel Frequency Cepstral Coefficient (MFCC) and Perceptual Linear Prediction (PLP). The proposed system can function as a collection tool for gathering natural and spontaneous cough data from conversations or continuous speech. The paper also compares the Kaldi and CMU Sphinx4 toolkits, concluding that Kaldi's use of GMM-HMM outperforms CMU Sphinx4. [ABSTRACT FROM AUTHOR]

Speech recognition systems have become a unique human-computer interaction (HCI) family. Speech is one of the most naturally developed human abilities; speech signal processing opens up a transparent and hand-free computation experience. This paper aims to present a retrospective yet modern approach to the world of speech recognition systems. The development journey of ASR (Automatic Speech Recognition) has seen quite a few milestones and breakthrough technologies that have been highlighted in this paper. A step-by-step rundown of the fundamental stages in developing speech recognition systems has been presented, along with a brief discussion of various modern-day developments and applications in this domain. This review paper aims to summarize and provide a beginning point for those starting in the vast field of speech signal processing. Since speech recognition has a vast potential in various industries like telecommunication, emotion recognition, healthcare, etc., this review would be helpful to researchers who aim at exploring more applications that society can quickly adopt in future years of evolution. [ABSTRACT FROM AUTHOR]

In an online class, students respond to queries initiated by the educator through voice, video, or chat. The educator receives these responses but cannot ascertain the emotion carried in these responses with confidence. This emotional limitation in online classes is a major drawback as emotions play a very important role in gauging student engagement and learning. This limitation in the detection of emotions or affective states in the responses of the student makes it difficult for the educator to decide if the student is on the right track or needs more help. On the other hand, if a negative affective state is detected, the educator could modify their teaching approach, speed, or content to the advantage of the student. This poses as an additional disadvantage to educators who suffer from any form of hearing impairment like late or acquired deafness, as they would have difficulty in hearing as well as gauging the emotion from student's feedback. Emotions being a key element in decision making and speech being one of the affective measurement channels, a useful solution would be to use an automatic speech emotion recognition system. In this paper, speech emotion recognition systems (SER) have been reviewed with the intention of identifying research gaps that need to be bridged before an effective SER application can be incorporated in any online education system for teaching. This would guarantee inclusivity as it would benefit all educators, especially the late deafened. This paper has been written with the intention of providing an in-depth understanding of SER components, spanning from emotional models to classifiers. The opportunities for possible improvements have also been touched upon. Special attention is given to deep learning approaches to understand their main contributions and challenges so far in this area. [ABSTRACT FROM AUTHOR]

Background: Cochlear implantation can be used when a patient's hearing cannot satisfactorily be improved after optimised hearing aid fitting. However, in patients with a cochlear nerve or brain disorder affecting hearing, the benefits of cochlear implants are not so straightforward. Methods: This paper describes a 58-year-old patient suffering from multiple sclerosis and profound sensorineural hearing loss, rehabilitated with a cochlear implant. Literature concerning cochlear implantation in demyelinating conditions was systematically reviewed using PubMed/Medline and Web of Science databases. Results: The patient's cochlear implantation was successful, with speech discrimination scores remaining above 90 per cent for eight years post-operatively. No previous cases of cochlear implantation with multiple sclerosis related hearing loss have been reported, despite the high incidence of hearing loss in multiple sclerosis patients. Conclusion: This paper demonstrates that multiple sclerosis lesions should not be an exclusion criterion in an otherwise suitable candidate for cochlear implantation. [ABSTRACT FROM AUTHOR]

This paper describes how automatic speech recognition (ASR) can be used to explore electronic patient records (EPR) in a sterile environment. As an information display, we used a system that was developed for the presentation of patient data and for supporting surgical hand disinfection. The speech recognition was performed using the Mozilla Web Speech API. A room microphone, a Jabra Box, and a directional microphone, a RØDE NT-USB Mini, were tested at various positions. Interactions with the EPR are triggered with a list of commands. The interaction was working as indented and test persons reported the system as intuitive. [ABSTRACT FROM AUTHOR]

Research on voice recognition for African languages is limited due to the scarcity of digital resources for training and adaptation, despite its broad usefulness. The Hausa language, spoken by almost fifty million inhabitants in West and Central Africa, is an example of a linguistic domain that has not been thoroughly studied. The Hausa language employs diacritics, which are symbols located above alphabetical characters to convey further information. By removing diacritics, the number of homographs increases, making it difficult to distinguish between similar words. This paper presents a study on speech recognition in the Hausa Language, specifically focusing on diacritized words. The study utilises the state-of-the-art wave2vec2.0 and Whisper deep learning architecture models, for transcribing audio signals into corresponding Hausa text. According to the results obtained in the study, the Whisper-large deep model emerged as the best, achieving a word error rate of 4.23% representing a considerable improvement of 43.9% when compared to the existing state-of-the-art model for Hausa language speech recognition. Additionally, the Whsiper-large model demonstrated a diacritic coverage of 92%, precision of 98.87%, with a diacritic error rate of 2.1%. [ABSTRACT FROM AUTHOR]

In this paper, a system for automatic detection and correction of mispronunciation of native Chinese learners of English by speech recognition technology is designed with the help of radiomagnetic pronunciation recording devices and computer-aided software. This paper extends the standard pronunciation dictionary by predicting the phoneme confusion rules in the language learner's pronunciation that may lead to mispronunciation and generates an extended pronunciation dictionary containing the standard pronunciation of each word and the possible mispronunciation variations, and automatic speech recognition uses the extended pronunciation dictionary to detect and diagnose the learner's mispronunciation of phonemes and provides real-time feedback. It is generated by systematic crosslinguistic phonological comparative analysis of the differences in phoneme pronunciation with each other, and a data-driven approach is used to do automatic phoneme recognition of learner speech and analyze the mapping relationship between the resulting mispronunciation and the corresponding standard pronunciation to automatically generate additional phoneme confusion rules. In this paper, we investigate various aspects of several issues related to the automatic correction of English pronunciation errors based on radiomagnetic pronunciation recording devices; design the general block diagram of the system, etc.; and discuss some key techniques and issues, including endpoint detection, feature extraction, and the system's study of pronunciation standard algorithms, analyzing their respective characteristics. Finally, we design and implement a model of an automatic English pronunciation error correction system based on a radiomagnetic pronunciation recording device. Based on the characteristics of English pronunciation, the correction algorithm implemented in this system uses the similarity and pronunciation duration ratings based on the log posterior probability, which combines the scores of both, and standardizes this system scoring through linear mapping. This system can achieve the purpose of automatic recognition of English mispronunciation correction and, at the same time, improve the user's spoken English pronunciation to a certain extent. [ABSTRACT FROM AUTHOR]

In recent years, the multidimensional visualization technology continues to accelerate, resulting in a huge amount of data, higher requirements for related technologies, and more opportunities. Under the background of big data technology application, multidimensional visualization methods can shine in different fields, such as applying them to linguistic research. Although the technology has a wide range of applications, it cannot effectively and intuitively display multidimensional voice feature data, which is difficult to fully meet the requirements of parameter visualization. In order to deeply study linguistic speech recognition and other issues, this paper introduces speech recognition technology to complete the creation and improvement of a multidimensional perspective analysis system for speech data and uses socket mechanism to complete the server construction, including voice recognition, data enhancement, model training and other modules. This system takes the target voice data collection as the calling end. Thus, based on socket connection, data interaction with the server can meet the task requirements of the multidimensional perspective analysis system and can achieve two-way data interaction. The simulation experiment results show that the system based on OpenSMILE toolbox can effectively obtain high-dimensional features, and its performance is excellent, which can meet most of the task requirements. It contains many kinds of acoustic feature data, which can solve the problem of over compression of the original signal, and mine the characteristics of voice waves to explain the relationship between frames. The system is higher than low-dimensional features in recognizing multiple speakers. This paper designs an effective simulation system by applying speech recognition technology to multidimensional linguistic data analysis in the context of big data. [ABSTRACT FROM AUTHOR]

The use of memristive neuromorphic circuit and system is a promising solution for next-generation Artificial Intelligence (AI) computing, as it offers possibilities that go beyond conventional GPU-based artificial neural network computing platforms. However, most of the existing memristive neuromorphic circuits and systems are designed for the specific networks, which is lack of universality and flexibility. Therefore, this paper proposes a universal memristive circuit and system framework for pure-attention-based transformer networks to implement multifunction applications on edge devices. Furthermore, the verification of image recognition and speech recognition was achieved by extending the size of the memristor crossbar array macros and reconfiguring the memristor weights without changing the memristive transformer circuit and framework. This paper not only provides a universal edge implementation framework for multifunction applications of the transformer, but also offers a low-power and promising solution for the application of pure-attention-based transformers on edge devices. [ABSTRACT FROM AUTHOR]

This paper starts from the basic principles of speech recognition, starting from acoustic models and features, and applies deep convolutional neural networks to speech recognition processing. It also introduces the overall process of speech recognition and mainstream algorithms to classify and summarize the speech recognition system. Due to the technological innovation of speech recognition and offline speech recognition systems, we found that traditional systems have low interactivity, poor flexibility, poor recognition command library, and other problems. We provide solutions for this paper according to the specific application environment. This paper introduces the design and implementation of an artificial intelligence teaching management system based on the Internet of Things (IoT) technology. Based on the design of the entire system, the system databases such as the video surveillance module, artificial intelligence security module, and remote control module are designed and realized the functions of these modules. Finally, RFID technology and database technology will be used to realize the informatization of training room personnel and equipment management, and the positioning and storage inspection of training room equipment. Secondly, from the perspective of environmental monitoring of the training room, temperature/ humidity sensors and optical sensors are used to complete the collection of real-time environmental data in the training room, thereby transmitting the data to the host system. It realizes the pairing through the Zigbee wireless communication module. Real-time monitoring of training room and management system. This paper introduces speech recognition and artificial intelligence into the management system of the training room so that the training can be better recorded and managed. [ABSTRACT FROM AUTHOR]

Natural language processing technologies have become more widely available in recent years, making them more useful in everyday situations. Machine learning systems that employ accessible datasets and corporate work to serve the whole spectrum of problems addressed in computational linguistics have lately yielded a number of promising breakthroughs. These methods were particularly advantageous for regional languages, as they were provided with cutting-edge language processing tools as soon as the requisite corporate information was generated. The bulk of modern people are unconcerned about the importance of reading. Reading aloud, on the other hand, is an effective technique for nourishing feelings as well as a necessary skill in the learning process. This paper proposed a novel approach for speech recognition based on neural networks. The attention mechanism is first utilized to determine the speech accuracy and fluency assessments, with the spectrum map as the feature extraction input. To increase phoneme identification accuracy, reading precision, for example, employs a new type of deep speech. It makes use of the exportchapter tool, which provides a corpus, as well as the TensorFlow framework in the experimental setting. The experimental findings reveal that the suggested model can more effectively assess spoken speech accuracy and reading fluency than the old model, and its evaluation model's score outcomes are more accurate. [ABSTRACT FROM AUTHOR]

Identifying the gender of a person and his age by way of speaking is considered a crucial task in computer vision. It is a very important and active research topic with many areas of application, such as identifying a person, trustworthiness, demographic analysis, safety and health knowledge, visual monitoring, and aging progress. Data matching is to identify the gender of the person and his age. Thus, the study touches on a review of many research papers from 2016 to 2022. At the heart of the topic, many systematic reviews of multimodal pedagogies in Age and Gender Estimation for Adaptive were undertaken. However, no current study of the theme concerns connected to multimodal pedagogies in Age and Gender Estimation for Adaptive Learning has been published. The multimodal pedagogies in four different databases within the keywords indicate the heart of the topic. A qualitative thematic analysis based on 48 articles found during the search revealed four common themes, such as multimodal engagement and speech with the Human-Robot Interaction life world. The study touches on the presentation of many major concepts, namely Age Estimation, Gender Estimation, Speaker Recognition, Speech recognition, Speaker Localization, and Speaker Gender Identification. According to specific criteria, they were presented to all studies. The essay compares these themes to the thematic findings of other review studies on the same topic such as multimodal age, gender estimation, and dataset used. The main objective of this paper is to provide a comprehensive analysis based on the surveyed region. The study provides a platform for professors, researchers, and students alike, and proposes directions for future research. [ABSTRACT FROM AUTHOR]

When a band is performing at a public occasion, certain sound effects are expected to be added to enliven the atmosphere. To achieve this effect, microphones and instruments are all connected to an audio mixer, then the expected audio output will be played through the speakers. However, sound engineers always spend plenty of time tuning the mixer until the satisfied results are obtained. This paper presents a smart digital mixer system that integrates touch control, speech control, and commonly used functions on an Android mobile platform to improve the mobility of audio mixer while tuning. The proposed system adopts a digital signal processor (DSP) as the core of the hardware architecture. The application provides a UI interface on an Android mobile phone in order to achieve the functions of speech recognition and touch control. The control commands will be transmitted to DSP via Bluetooth 5.0, self-defined Bluetooth packet format (SBPF), and data transfer controller (DTC). The main contribution of this work is to propose multiple functions of a mixer system with a convenient and interactive user interface. The experimental results show the average accuracy of all respondents reached 92.3%. Moreover, the proposed system has the advantage of having a low-cost hardware circuit design, and provides high flexibility of setting for the audio mixer system according to the user's preference. [ABSTRACT FROM AUTHOR]

This paper presents an in-depth study and analysis of adaptive proofreading of spoken English pronunciation in a wireless sensor network environment. This paper addresses the above problem by combining two common methods for controlling the transmission rate of sensing nodes maximizing network utility algorithm and congestion control mechanism. Firstly, the transmission rate of one-hop nodes at a distance from the aggregation node is dynamically adjusted by the increasing exploration algorithm under the premise of unknown link transmission capacity, while the transmission rate of one-hop nodes is proportionally allocated to multihop nodes in multihop nodes by the congestion control mechanism based on the average reception success rate of the link. A design framework for a speech recognition system with complementary offline recognition and online recognition based on the C/S model is proposed, and a speech recognition system in swarm intelligence awareness is implemented based on the Sphinx engine. The client side implements the speech recognition of decoder in the offline state, and the server side provides the functions of recognition consistency detection, model adjustment training, monitoring, and recommendation in the online state as well as the interface for external access. The scene adaptation module effectively improves the speech recognition system's speech recognition correct rate under different scenes, and the discourse topic recognition module verifies the recognition effectiveness of the speech recognition system under different discourse topics, which can meet the requirements of users' personalized speech input. [ABSTRACT FROM AUTHOR]

The user can utilise voice acknowledgement in making it more straightforward for individuals with inabilities to get to entryway frameworks and give better security to lives and properties. In this paper, the advancement of the technology is used for opening any locking system. We are implementing this type of module where it can be of low cost, and even physically disabled persons can open the door without any assistance. The Blynk app and a Wi-Fi module can access the system by giving the input and output as a voice recognition speech command. Hence, in this paper, any person can use google assistant from their smartphone to lock or unlock a secure system with just two controls, i.e., "Ok Google Lock Door one", "Ok Google Unlock Door one". This project works seamlessly for three locks in one system that can be operated separately using only one main microcontroller, i.e., Node-MCU ESP8266, and relays drivers so that our project can be quickly developed and deployed. The applications of this project are endless as technology constantly evolves. Suppose the user is connected to the internet and operated using Google Assistant. In that case, the lock is operated only from one account, making it secure and available to all who use smartphones and have a google account. Even for people who are blind, this can be an excellent way to lock and unlock their resources just with their voice. Anyone can utilise this project from their convenience, making it the easiest way for anyone to lock/unlock just by two words, i.e., "Ok, Google Lock Door." [ABSTRACT FROM AUTHOR]

Featured Application: Pepper, the social robot, includes various capabilities, and exploration of its features and functionalities can provide valuable insights into its strengths and limitations where it may require improvement. In this paper, five capabilities—mapping and navigation, speech, hearing, object detection, and face detection, are considered for investigation. All of them can be employed in various settings, such as schools, hospitals, and the service industry, to enhance the user experience. The application of social robots is increasing daily due to their various capabilities. In real settings, social robots have been successfully deployed in multiple domains, such as health, education, and the service industry. However, it is crucial to identify the strengths and limitations of a social robot before it can be employed in a real-life scenario. In this study, we explore and examine the capabilities of a humanoid robot, 'Pepper', which can be programmed to interact with humans. The present paper investigates five capabilities of Pepper: mapping and navigation, speech, hearing, object detection, and face detection. We attempt to study each of these capabilities in-depth with the help of experiments conducted in the laboratory. It has been identified that Pepper's sound and speech recognition capabilities yielded satisfactory results, even with various accents. On the other hand, Pepper's built-in SLAM navigation is unreliable, making it difficult to reach destinations accurately due to generated maps. Moreover, its object and face detection capabilities delivered inconsistent outcomes. This shows that Pepper has potential for improvement in its current capabilities. However, previous studies showed that with the integration of artificial intelligence techniques, a social robot's capabilities can be enhanced significantly. In the future, we will focus on such integration in the Pepper robot, and the present study's exploration will help to establish a baseline comprehension of the in-built artificial intelligence of Pepper. The findings of the present paper provide insights to researchers and practitioners planning to use the Pepper robot in their future work. [ABSTRACT FROM AUTHOR]

Speakers with dysarthria often struggle to accurately pronounce words and effectively communicate with others. Automatic speech recognition (ASR) is a powerful tool for extracting the content from speakers with dysarthria. However, the narrow concept of ASR typically only covers technologies that process acoustic modality signals. In this paper, we broaden the scope of this concept that the generalized concept of ASR for dysarthric speech. Our survey discussed the systems encompassed acoustic modality processing, articulatory movements processing and audio-visual modality fusion processing in the application of recognizing dysarthric speech. Contrary to previous surveys on dysarthric speech recognition, we have conducted a systematic review of the advancements in this field. In particular, we introduced state-of-the-art technologies to supplement the survey of recent research during the era of multi-modality fusion in dysarthric speech recognition. Our survey found that audio-visual fusion technologies perform better than traditional ASR technologies in the task of dysarthric speech recognition. However, training audio-visual fusion models requires more computing resources, and the available data corpus for dysarthric speech is limited. Despite these challenges, state-of-the-art technologies show promising potential for further improving the accuracy of dysarthric speech recognition in the future. [ABSTRACT FROM AUTHOR]

This paper constructs a SDN network traffic prediction model based on speech recognition and applies it to the educational information optimization platform. By analyzing the influencing factors of SDN network equipment, communication links, and network traffic, this paper constructs the initial index set of SDN network traffic situation. In the data plane of SDN, the queue management algorithm is used to control the flow. On this basis, an IRS mechanism is proposed based on the advantages of SDN centralized control and the difference of transmission performance requirements between large and small streams. For the transmission of large traffic, IRS adopts greedy routing and multipath routing based on the remaining bandwidth to make the traffic evenly distributed in the network, and IRS adds the scheduling strategy based on IP addressing to avoid packet disorder. Simulation results show that the effectiveness of this algorithm can reach 95.67% at the highest, and the MSE convergence is 0.0021 at the lowest. At the same time, this method completes the quantitative evaluation of SDN network traffic situation, effectively solves the problem that SDN traffic situation labels cannot be determined, and opens a new vision of global state observation for SDN network management. This research can provide some technical support for the educational information optimization platform. [ABSTRACT FROM AUTHOR]

In order to solve the problem of lack of multimodal emotional database, a computer speech recognition technology and graphic form design research were proposed. Using the hidden Markov model (HMM) to recognize speech emotion is mainly to provide emotion type for the subsequent expression fusion. When the emotion category in the speech is obtained, the facial animation parameter (FAP) corresponding to the speech emotion can be combined with the lip movement FAP based on the Moving Pictures Experts Group (MPEG-4) face animation standard to obtain a comprehensive FAP. The results show that the recognition effect of speech emotion recognition in the method used in this paper is relatively better than that obtained by other literature methods, and the average recognition rate reaches 70.24%, which is higher than the other three methods. It is verified that this method can present a better recognition effect. [ABSTRACT FROM AUTHOR]

INTRODUCTION: In the online English learning platform, noise interference makes people unable to hear the content of English teaching clearly, which leads to a great reduction in the efficiency of English learning. In order to improve the voice quality of online English learning platform, the speech enhancement method of the online English learning platform based on deep neural network is studied. OBJECTIVES: This paper proposes a deep neural network-based speech enhancement method for online English learning platform in order to obtain more desirable results in the application of speech quality optimization. METHODS: The optimized VMD (Variable Modal Decomposition) algorithm is combined with the Moth-flame optimization algorithm to find the optimal solution to obtain the optimal value of the decomposition mode number and the penalty factor of the variational modal decomposition algorithm, and then the optimized variational modal decomposition algorithm is used to filter the noise information in the speech signal; Through the network speech enhancement method based on deep neural network learning, the denoised speech signal is taken as the enhancement target to achieve speech enhancement. RESULTS: The research results show that the method not only has significant denoising ability for speech signal, but also after this method is used, PESQ value of speech quality perception evaluation of speech signal is greater than 4.0dB, the spectral features are prominent, and the speech quality is improved. CONCLUSION: Through experiments from three perspectives: speech signal denoising, speech quality enhancement and speech spectrum information, the usability of the method in this paper is confirmed. [ABSTRACT FROM AUTHOR]

Recently, the machine learning research trend expands to the system performance optimization field, where it has still been proposed by researchers based on their intuitions and heuristics. Compared to conventional major machine learning research areas such as image or speech recognition, machine learning-based system performance optimization fields are at the beginning stage. However, recent papers show that this approach is promising and has significant potential. This paper reviews 11 machine learning-based system performance optimization approaches from nine recent papers based on well-known machine learning models such as perceptron, LSTM, and RNN. This survey provides a detailed design and summarizes model, input, output, and prediction method of each approach. This paper covers various system performance areas from the data structure to essential system components of a computer system such as index structure, branch predictor, sort, and cache management. The result shows that machine learning-based system performance optimization has an important potential for future research. We expect that this paper shows a wide range of applicability of machine learning technology and provides a new perspective for system performance optimization. [ABSTRACT FROM AUTHOR]

Flexible and wearable sensors are now becoming the favorite of the new information age for their great prospects, especially in human health monitoring, and which are mainly aimed at improving the comprehensive sensing performance. However, the equilibrium between sensitivity and response time of the sensor has not been well balanced. Herein, a simple and low‐cost strategy to fabricate flexible pressure sensors based on thermoplastic polyurethane (TPU) substrate with unique surface stochastic morphology replicated from the abrasive paper, which is inspired by skin epidermis, is presented. The integrated TPU flexible pressure sensor exhibits a high sensitivity of −2.24 kPa−1 in a linear pressure regime of 0–200 Pa, and the effective working range of this sensor is close to 2 kPa, ultrafast response time and relaxation time of 10 ms, low detection limits of 0.72 Pa, and excellent cycling stability over 3000 cycles. The fabricated sensors demonstrate outstanding sensing capabilities in monitoring human physiological signals, such as subtle pulse, wrist movement, and speech recognition, making promising potential in practical human health monitoring applications. [ABSTRACT FROM AUTHOR]

With the economic globalization continuous growth of China's socioeconomic level tends to be internationalized, China's attention to English has been significantly improved. However, the domestic English teaching level is limited, so it is impossible to correct students' English pronunciation and make a reasonable evaluation at all times so that oral training has certain disadvantages. However, the computer-aided language learning system at home and abroad focuses on the practice of words and grammar, and the evaluation indicators are less and not comprehensive. In view of the complexity of English pronunciation changes, traditional speech recognition is difficult to recognize speech speed and improve its accuracy. Furthermore, to strengthen the English pronunciation of domestic students, a nonlinear network structure is studied in depth to simulate the human brain to analyze a model of speech recognition is established Mel frequency cepstrum characteristic parameters of human ear model and deep belief network. In this paper, the traditional computer pronunciation evaluation method is improved in an all-round way, and a set of high-quality speech recognition system of speech recognition method is constructed. Aiming at the above problems, it takes the students as the research, which proves that the method adopted in this paper can give the learners accurate pronunciation quality analysis report and guidance and correct their intonation and improve the learning effect, and the experimental data verify that the improved speech recognition system model recognition ability is higher than the traditional model. [ABSTRACT FROM AUTHOR]

Background: Despite the rapid expansion of electronic health records, the use of computer mouse and keyboard, challenges the data entry into these systems. Speech recognition software is one of the substitutes for the mouse and keyboard. The objective of this study was to evaluate the use of online and offline speech recognition software on spelling errors in nursing reports and to compare them with errors in handwritten reports.Methods: For this study, online and offline speech recognition software were selected and customized based on unrecognized terms by these softwares. Two groups of 35 nurses provided the admission notes of hospitalized patients upon their arrival using three data entry methods (using the handwritten method or two types of speech recognition software). After at least a month, they created the same reports using the other methods. The number of spelling errors in each method was determined. These errors were compared between the paper method and the two electronic methods before and after the correction of errors.Results: The lowest accuracy was related to online software with 96.4% and accuracy. On the average per report, the online method 6.76, and the offline method 4.56 generated more errors than the paper method. After correcting the errors by the participants, the number of errors in the online reports decreased by 94.75% and the number of errors in the offline reports decreased by 97.20%. The highest number of reports with errors was related to reports created by online software.Conclusion: Although two software had relatively high accuracy, they created more errors than the paper method that can be lowered by optimizing and upgrading these softwares. The results showed that error correction by users significantly reduced the documentation errors caused by the software. [ABSTRACT FROM AUTHOR]

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module, which can be developed independently, is explicitly used at the front-end of the target audio applications. In this paper, we present an end-to-end learning solution to jointly optimise the models for audio enhancement (AE) and the subsequent applications. To guide the optimisation of the AE module towards a target application, and especially to overcome difficult samples, we make use of the sample-wise performance measure as an indication of sample importance. In experiments, we consider four representative applications to evaluate our training paradigm, i.e., ASR, speech command recognition (SCR), speech emotion recognition (SER), and ASC. These applications are associated with speech and nonspeech tasks concerning semantic and non-semantic features, transient and global information, and the experimental results indicate that our proposed approach can considerably boost the noise robustness of the models, especially at low signal-to-noise ratios, for a wide range of computer audition tasks in everyday-life noisy environments. [ABSTRACT FROM AUTHOR]

Approaches to automatic speech recognition have transited from Hidden Markov Model (HMM)-based ASR to deep neural networks. The advantages of deep neural network approaches are that they can be developed quickly and perform better given large language resources. Nevertheless, dialect speech recognition is still challenging due to the limited resources. Transfer learning approaches have been proposed to improve speech recognition for low resources. In the first approach, the model is pre-trained on a large and diverse labeled dataset to learn the acoustic and language patterns from the speech signal. Then, the model parameters are updated with a new dataset, and the pre-trained model is fine-tuned on a low-resource language dataset. The fine-tuning process is usually completed by freezing the pre-trained layers and training the remaining layers of the model on the low-resource language corpus. Another approach is to use a pre-trained model to capture the compact and meaningful features as input to the encoder. Pre-training in this approach usually involves using unsupervised learning methods to train models on a corpus of large amounts of unmarked data. It enables the model to learn the general patterns and relationships between the input speech signals. This paper proposes a training recipe using transfer learning and Standard Malay models to improve automatic speech recognition for Kelantan and Sarawak Malay dialects. [ABSTRACT FROM AUTHOR]

Most of the adversarial attacks against speech recognition systems focus on specific adversarial perturbations, which are generated by adversaries for each normal example to achieve the attack. Universal adversarial perturbations (UAPs), which are independent of the examples, have recently received wide attention for their enhanced real-time applicability and expanded threat range. However, most of the UAP research concentrates on the image domain, and less on speech. In this paper, we propose a staged perturbation generation method that constructs CommanderUAP, which achieves a high success rate of universal adversarial attack against speech recognition models. Moreover, we apply some methods from model training to improve the generalization in attack and we control the imperceptibility of the perturbation in both time and frequency domains. In specific scenarios, CommanderUAP can also transfer attack some commercial speech recognition APIs. [ABSTRACT FROM AUTHOR]

Speech is produced by a nonlinear, dynamical Vocal Tract (VT) system, and is transmitted through multiple (air, bone and skin conduction) modes, as captured by the air, bone and throat microphones respectively. Speaker specific characteristics that capture this nonlinearity are rarely used as stand-alone features for speaker modeling, and at best have been used in tandem with well known linear spectral features to produce tangible results. This paper proposes Recurrent Plot (RP) embeddings as stand-alone, non-linear speaker-discriminating features. Two datasets, the continuous multimodal TIMIT speech corpus and the consonant-vowel unimodal syllable dataset, are used in this study for conducting closed-set speaker identification experiments. Experiments with unimodal speaker recognition systems show that RP embeddings capture the nonlinear dynamics of the VT system which are unique to every speaker, in all the modes of speech. The Air (A), Bone (B) and Throat (T) microphone systems, trained purely on RP embeddings perform with an accuracy of 95.81%, 98.18% and 99.74%, respectively. Experiments using the joint feature space of combined RP embeddings for bimodal (A–T, A–B, B–T) and trimodal (A–B–T) systems show that the best trimodal system (99.84% accuracy) performs on par with trimodal systems using spectrogram (99.45%) and MFCC (99.98%). The 98.84% performance of the B–T bimodal system shows the efficacy of a speaker recognition system based entirely on alternate (bone and throat) speech, in the absence of the standard (air) speech. The results underscore the significance of the RP embedding, as a nonlinear feature representation of the dynamical VT system that can act independently for speaker recognition. It is envisaged that speech recognition too will benefit from this nonlinear feature. [ABSTRACT FROM AUTHOR]

This document is an editorial titled "Physiological signal processing for wellness" published in the journal Frontiers in Signal Processing. The editorial discusses the field of physiological signal processing and its potential to transform the way we approach wellness. By analyzing signals like heart rate, brain activity, and skin temperature, researchers can gain insights into our internal state and develop personalized wellbeing solutions. The editorial also acknowledges the challenges of data privacy, algorithm accuracy, and generalizability across diverse populations. The document includes summaries of three research papers on topics related to physiological signal processing, including predicting mental states using heart rate variability, using AI cough analysis for early detection of COVID-19, and decoding silent thoughts through imagined speech recognition. Each paper highlights the potential of advanced signal processing techniques for improving mental state assessment, COVID-19 detection, and communication technology. Another paper explores the use of deep learning for more accurate and automated ECG analysis, addressing challenges in signal transformation and fine-tuning pre-trained models. The document concludes by emphasizing the importance of collaboration and responsible development of this technology to ensure equitable access to personalized wellbeing solutions. [Extracted from the article]

Intelligent music teaching is the direction of subsequent reforms in music teaching methods. In order to improve the intelligence of music teaching, this paper conducts research on speech recognition technology. The speech conversion system based on Multiscale Star GAN extracts different levels of multiscale features of the global features of music utterance through the multiscale structure, which enhances the details of the converted speech and uses residual connections to alleviate the problem of gradient disappearance and enable the network to spread more deeply. In addition, after improving the speech recognition algorithm, this paper combines the needs of music teaching to construct a music teaching system based on speech recognition and artificial intelligence and designs system functional modules. Finally, this paper evaluates the performance of the system constructed in this paper by means of teaching experiments. From the experimental analysis, it can be seen that the system constructed in this paper has a good teaching effect. [ABSTRACT FROM AUTHOR]

An introduction to the journal is presented in which the editor discusses various topics within the issue, including machine learning algorithms, neural networks, and transformers in recurrent neural networks (RNN).

In this paper, we use machine learning algorithms to conduct in-depth research and analysis on the construction of human-computer interaction systems and propose a simple and effective method for extracting salient features based on contextual information. The method can retain the dynamic and static information of gestures intact, which results in a richer and more robust feature representation. Secondly, this paper proposes a dynamic planning algorithm based on feature matching, which uses the consistency and accuracy of feature matching to measure the similarity of two frames and then uses a dynamic planning algorithm to find the optimal matching distance between two gesture sequences. The algorithm ensures the continuity and accuracy of the gesture description and makes full use of the spatiotemporal location information of the features. The features and limitations of common motion target detection methods in motion gesture detection and common machine learning tracking methods in gesture tracking are first analyzed, and then, the kernel correlation filter method is improved by designing a confidence model and introducing a scale filter, and finally, comparison experiments are conducted on a self-built gesture dataset to verify the effectiveness of the improved method. During the training and validation of the model by the corpus, the complementary feature extraction methods are ablated and learned, and the corresponding results obtained are compared with the three baseline methods. But due to this feature, GMMs are not suitable when users want to model the time structure. It has been widely used in classification tasks. By using the kernel function, the support vector machine can transform the original input set into a high-dimensional feature space. After experiments, the speech emotion recognition method proposed in this paper outperforms the baseline methods, proving the effectiveness of complementary feature extraction and the superiority of the deep learning model. The speech is used as the input of the system, and the emotion recognition is performed on the input speech, and the corresponding emotion obtained is successfully applied to the human-computer dialogue system in combination with the online speech recognition method, which proves that the speech emotion recognition applied to the human-computer dialogue system has application research value. [ABSTRACT FROM AUTHOR]

The characteristics of acoustic emission signals generated in the process of rock deformation and fission contain rich information on internal rock damage. The use of acoustic emissions monitoring technology can analyze and identify the precursor information of rock failure. At present, in the field of acoustic emissions monitoring and the early warning of rock fracture disasters, there is no real-time identification method for a disaster precursor characteristic signal. It is easy to lose information by analyzing the characteristic parameters of traditional acoustic emissions to find signals that serve as precursors to disasters, and analysis has mostly been based on post-analysis, which leads to poor real-time recognition of disaster precursor characteristics and low application levels in the engineering field. Based on this, this paper regards the acoustic emissions signal of rock fracture as a kind of speech signal generated by rock fracture uses this idea of speech recognition for reference alongside spectral analysis (STFT) and Mel frequency analysis to realize the feature extraction of acoustic emissions from rock fracture. In deep learning, based on the VGG16 convolutional neural network and AlexNet convolutional neural network, six intelligent real-time recognition models of rock fracture and key acoustic emission signals were constructed, and the network structure and loss function of traditional VGG16 were optimized. The experimental results show that these six deep-learning models can achieve the real-time intelligent recognition of key signals, and Mel, combined with the improved VGG16, achieved the best performance with 87.68% accuracy and 81.05% recall. Then, by comparing multiple groups of signal recognition models, Mel+VGG-FL proposed in this paper was verified as having a high recognition accuracy and certain recognition efficiency, performing the intelligent real-time recognition of key acoustic emission signals in the process of rock fracture more accurately, which can provide new ideas and methods for related research and the real-time intelligent recognition of rock fracture precursor characteristics. [ABSTRACT FROM AUTHOR]

Dysarthric speech has several pathological characteristics, such as discontinuous pronunciation, uncontrolled volume, slow speech, explosive pronunciation, improper pauses, excessive nasal sounds, and air-flow noise during pronunciation, which differ from healthy speech. Automatic speech recognition (ASR) can be very helpful for speakers with dysarthria. Our research aims to provide a scoping review of ASR for dysarthric speech, covering papers in this field from 1990 to 2022. Our survey found that the development of research studies about the acoustic features and acoustic models of dysarthric speech is nearly synchronous. During the 2010s, deep learning technologies were widely applied to improve the performance of ASR systems. In the era of deep learning, many advanced methods (such as convolutional neural networks, deep neural networks, and recurrent neural networks) are being applied to design acoustic models and lexical and language models for dysarthric-speech-recognition tasks. Deep learning methods are also used to extract acoustic features from dysarthric speech. Additionally, this scoping review found that speaker-dependent problems seriously limit the generalization applicability of the acoustic model. The scarce available speech data cannot satisfy the amount required to train models using big data. [ABSTRACT FROM AUTHOR]

Education is a fundamental right that enriches everyone's life. However, physically challenged people often debar from the general and advanced education system. Audio-Visual Automatic Speech Recognition (AV-ASR) based system is useful to improve the education of physically challenged people by providing hands-free computing. They can communicate to the learning system through AV-ASR. However, it is challenging to trace the lip correctly for visual modality. Thus, this paper addresses the appearance-based visual feature along with the co-occurrence statistical measure for visual speech recognition. Local Binary Pattern-Three Orthogonal Planes (LBP-TOP) and Grey-Level Co-occurrence Matrix (GLCM) is proposed for visual speech information. The experimental results show that the proposed system achieves 76.60 % accuracy for visual speech and 96.00 % accuracy for audio speech recognition. [ABSTRACT FROM AUTHOR]

Speech recognition is one of the most convenient forms of human beings engaging in the exchanging of information. In this research, we want to make robots understand human language and communicate with each other through the human language, and to realize man–machine interactive and humanoid– robot interactive. Therefore, this research mainly studies NAO robots’ speech recognition and humanoid communication between double-humanoid robots. This paper introduces the future direction and application prospect of speech recognition as well as its basic method and knowledge of speech recognition fields. This research also proposes the application of the most advanced method—establishment of the Hidden Markov Model (HMM) for the continuous word recognition in the speech recognition of NAO robots. In addition, this paper focuses on the establishment of a modelling algorithm and the extraction method of speech characteristics and the existing problems. Meanwhile, this research demonstrates the experiments of the NAO robot structured function and the voice interactive of double-humanoid robots. Through the use of an NAO-robot-controlled platform, Choregraphe software, and combined calling of Baidu speech recognition, the communication between double-humanoid robots has been achieved. Besides, a series of programming designs have realized the interactive functions such as NAO robots’ daily dialogue and communication, arithmetic function (addition, subtraction, multiplication, and division), singing, making movement, and rhetorical-pattern dialogues. Finally, it shows the significance and contribution of research of interaction between doublehumanoid robots. [ABSTRACT FROM AUTHOR]

The signal corresponding to English speech contains a lot of redundant information and environmental interference information, which will produce a lot of distortion in the process of English speech translation signal recognition. Based on this, a large number of studies focus on encoding and processing English speech, so as to achieve high-precision speech recognition. The traditional wavelet denoising algorithm plays an obvious role in the recognition of English speech translation signals, which mainly depends on the excellent local time-frequency domain characteristics of the wavelet signal algorithm, but the traditional wavelet signal algorithm is still difficult to select the recognition threshold, and the recognition accuracy is easy to be affected. Based on this, this paper will improve the traditional wavelet denoising algorithm, abandon the single-threshold judgment of the original traditional algorithm, innovatively adopt the combination of soft threshold and hard threshold, further solve the distortion problem of the denoising algorithm in the process of English speech translation signal recognition, improve the signal-to-noise ratio of English speech recognition, and further reduce the root mean square error of the signal. Good noise reduction effect is realized, and the accuracy of speech recognition is improved. In the experiment, the algorithm is compared with the traditional algorithm based on MATLAB simulation software. The simulation results are consistent with the actual theoretical results. At the same time, the algorithm proposed in this paper has obvious advantages in the recognition accuracy of English speech translation signals, which reflects the superiority and practical value of the algorithm. [ABSTRACT FROM AUTHOR]

In multi-lingual, multi-speaker environments (e.g., international conference scenarios), speech, language, and background sounds can overlap. In real-world scenarios, source separation techniques are needed to separate target sounds. Downstream tasks, such as ASR, speaker recognition, speech recognition, VAD, etc., can be combined with speech separation tasks to gain a better understanding. Since most of the evaluation methods for monophonic separation are either single or subjective, this paper used the downstream recognition task as an overall evaluation criterion. Thus, the performance could be directly evaluated by the metrics of the downstream task. In this paper, we investigated a two-stage training scheme that combined speech separation and language identification tasks. To analyze and optimize the separation performance of single-channel overlapping speech, the separated speech was fed to a language identification engine to evaluate its accuracy. The speech separation model was a single-channel speech separation network trained with WSJ0-2mix. For the language identification system, we used an Oriental Language Dataset and a dataset synthesized by directly mixing different proportions of speech groups. The combined effect of these two models was evaluated for various overlapping speech scenarios. When the language identification network model was based on single-person single-speech frequency spectrum features, Chinese, Japanese, Korean, Indonesian, and Vietnamese had significantly improved recognition results over the mixed audio spectrum. [ABSTRACT FROM AUTHOR]

As one of Chinese minority languages, Tibetan speech recognition technology was not researched upon as extensively as Chinese and English were until recently. This, along with the relatively small Tibetan corpus, has resulted in an unsatisfying performance of Tibetan speech recognition based on an end-to-end model. This paper aims to achieve an accurate Tibetan speech recognition using a small amount of Tibetan training data. We demonstrate effective methods of Tibetan end-to-end speech recognition via cross-language transfer learning from three aspects: modeling unit selection, transfer learning method, and source language selection. Experimental results show that the Chinese-Tibetan multi-language learning method using multilanguage character set as the modeling unit yields the best performance on Tibetan Character Error Rate (CER) at 27.3%, which is reduced by 26.1% compared to the language-specific model. And our method also achieves the 2.2% higher accuracy using less amount of data compared with the method using Tibetan multi-dialect transfer learning under the same model structure and data set. [ABSTRACT FROM AUTHOR]

The embedded English speech teaching recognition system is a technology that writes the English speech recognition device control program into the chip and embeds the chip into the device, so that the human-like chip controls the English speech device to complete the speech recognition operation. Applying the embedded technology to the English speech recognition system can improve the recognition accuracy of the system to a higher level in terms of recognizing the English speech of a specific person. The purpose of this paper is to research and design an automatic error detection method for embedded English speech teaching recognition system in the context of artificial intelligence. This paper first gives a general introduction to the overview of artificial intelligence, then analyzes the speech recognition algorithm, uses MatLab software to obtain the correct number of recognition system words and the correct rate, and then implements the embedded English teaching recognition system in different environments. The experimental results of comparison through multiple test analysis show that in a quiet environment, the error rate of the embedded English speech teaching recognition system is very low, and the correct recognition rate can reach more than 90%. In a noisy environment affected by various noises, the correct recognition rate of the embedded English speech teaching recognition system is basically above 60%. [ABSTRACT FROM AUTHOR]