Search

The inability to communicate verbally is widely acknowledged as a significant disability. The primary objective of this research is to create a practical system aimed at individuals with hearing impairments, particularly those who depend on sign language as their primary means of communication. This system aims to enable deaf individuals to express themselves, communicate effectively and facilitate understanding of their language which would otherwise be challenging since most people are unfamiliar with sign language. By employing human gesture interpretation and motion capture, this technology can facilitate the translation of sign language into spoken language and vice versa. Despite the existence of various methods to convert sign language into voice, none of them currently provide an entirely intuitive user interface. Our objective is to create a system that not only translates sign language but also integrates a natural user interface, thus enhancing accessibility for individuals who are blind or have visual impairments. This system will achieve this by recognizing facial expressions and effectively conveying emotions behind words assisting visually impaired individuals in expressing themselves more effectively. Hence, in this project, we tentatively aim to build a system that can ease the lives of blind, deaf and dumb people to some extent. Normal communication like normal people do might never be possible for differently abled people but through our project, we try to provide them with a tool that can help them experience normalcy while communicating with normal people. [ABSTRACT FROM AUTHOR]

Accessibility in online platforms is a critical concern in our increasingly digital world, where information and services are predominantly accessed through the Internet. The purpose of this systematic review is to provide a comprehensive overview of the current state of the art in online accessibility technologies, and it is focused on key tools such as sign language recognition, speech-to-text, text-to-speech, and voice recognition. Despite advancements in digital inclusivity, numerous technical limitations persist, which limit the accessibility of online content for individuals with disabilities. Our findings indicate that while speech and voice technologies have achieved good accuracies and low word error rates, further research is needed to improve the accuracy and usability of sign language recognition systems, especially for continuous sign language recognition, as they have low accuracy. In this review, we analyzed research articles and publications from well-known databases, including Google Scholar, Elsevier, IEEE Xplore, and Springer. In order to ensure a high standard of quality, we applied the PRISMA 2020 and PEDro methodologies to quantitatively and qualitatively filter the thousands of articles provided by these databases, and we selected only studies that were related to our study. Key areas of investigation included the performance and accuracy of sign language interfaces, speech-to-text, text-to-speech, and speech recognition applications and the compatibility of these technologies with different platforms and devices. This review also explores the role of emerging technologies such as artificial intelligence (AI) and machine learning (ML) in enhancing accessibility and personalizing user experiences. Through a critical analysis of current solutions and a discussion of existing gaps, this paper offers insights into potential improvements and future directions for creating more accessible online environments. The findings might be valuable to researchers and developers dedicated to promoting digital inclusivity and equality. [ABSTRACT FROM AUTHOR]

Simple Summary: Wood-boring pests pose a significant threat to the health of trees in forest and urban ecosystems. Their larvae live deep within the xylem of tree trunks, where visible signs of their activity on the trunk surface are minimal. Traditional monitoring methods are time-consuming and labor-intensive, making it difficult to detect infestations early, thereby complicating pest control efforts. Taking the emerald ash borer (EAB), Agrilus planipennis Fairmaire, 1888 (Coleoptera: Buprestidae), and the small carpenter moth (SCM), Streltzoviella insularis Staudinger, 1892 (Lepidoptera: Cossidae), commonly found on ash trees (Fraxinus chinensis Roxb) in northern China, as examples, acoustic sensors can be used to collect the feeding vibration signals of their larvae, providing a new approach to pest identification. This paper proposes a deep learning recognition model, BorerNet, which uses these boring vibration signals as input and incorporates an attention mechanism. Experimental results show that this model achieves high recognition accuracy. The method can provide technical support for the identification and control of wood-boring pests. Wood-boring pests are difficult to monitor due to their concealed lifestyle. To effectively control these wood-boring pests, it is first necessary to efficiently and accurately detect their presence and identify their species, which requires addressing the limitations of traditional monitoring methods. This paper proposes a deep learning-based model called BorerNet, which incorporates an attention mechanism to accurately identify wood-boring pests using the limited vibration signals generated by feeding larvae. Acoustic sensors can be used to collect boring vibration signals from the larvae of the emerald ash borer (EAB), Agrilus planipennis Fairmaire, 1888 (Coleoptera: Buprestidae), and the small carpenter moth (SCM), Streltzoviella insularis Staudinger, 1892 (Lepidoptera: Cossidae). After preprocessing steps such as clipping and segmentation, Mel-frequency cepstral coefficients (MFCCs) are extracted as inputs for the BorerNet model, with noisy signals from real environments used as the test set. BorerNet learns from the input features and outputs identification results. The research findings demonstrate that BorerNet achieves an identification accuracy of 96.67% and exhibits strong robustness and generalization capabilities. Compared to traditional methods, this approach offers significant advantages in terms of automation, recognition efficiency, and cost-effectiveness. It enables the early detection and treatment of pest infestations and allows for the development of targeted control strategies for different pests. This introduces innovative technology into the field of tree health monitoring, enhancing the ability to detect wood-boring pests early and making a substantial contribution to forestry-related research and practical applications. [ABSTRACT FROM AUTHOR]

Copyright of Revista Foco (Interdisciplinary Studies Journal) is the property of Revista Foco and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To avoid interference from unexpected background noises and obtain high fidelity voice signal, acoustic sensors with high sensitivity, flat frequency response, and high signal-to-noise ratio (SNR) are urgently needed for voice recognition. Graphene-oxide (GO) has received extensive attention due to its advantages of controllable thickness and high fracture strength. However, low mechanical sensitivity (SM) introduced by undesirable initial stress limits the performance of GO material in the field of voice recognition. To alleviate the aforementioned issue, GO diaphragm with annular corrugations is proposed. By means of the reusable copper mold machined by picosecond laser, the fabrication and transfer of corrugated GO diaphragm are realized, thus achieving a Fabry–Perot (F–P) acoustic sensor. Benefitting from the structural advantage of the corrugated GO diaphragm, our F–P acoustic sensor exhibits high SM (43.70 nm/Pa@17 kHz), flat frequency response (−3.2 to 3.7 dB within 300–3500 Hz), and high SNR (76.66 dB@1 kHz). In addition, further acoustic measurements also demonstrate other merits, including an excellent frequency detection resolution (0.01 Hz) and high time stability (output relative variation less than 6.7% for 90 min). Given the merits presented before, the fabricated F–P acoustic sensor with corrugated GO diaphragm can serve as a high-fidelity platform for acoustic detection and voice recognition. In conjunction with the deep residual learning framework, high recognition accuracy of 98.4% is achieved by training and testing the data recorded by the fabricated F–P acoustic sensor. [ABSTRACT FROM AUTHOR]

In hopes of resolving the issue of poor quality of information input for teaching spoken English online, the study creates an English teaching assistance model based on a recognition algorithm named dynamic time warping (DTW) and relies on automated voice recognition technology. In hopes of improving the algorithm's efficiency, the study modifies the speech signal's time-domain properties during the pre-processing stage and enhances the algorithm's performance in terms of computational effort and storage space. Finally, a simulation experiment is employed to evaluate the model application's efficacy. The study's revised DTW model, which achieves recognition rates of above 95% for all phonetic symbols and tops the list for cloudy consonant recognition with rates of 98.5%, 98.8%, and 98.7% throughout the three tests, respectively, is demonstrated by the study's findings. The enhanced model for DTW voice recognition also presents higher efficiency and requires less time for training and testing. The DTW model's KS value, which is the highest among the models analyzed in the KS value analysis, is 0.63. Among the comparative models, the model also presents the lowest curve position for both test functions. This shows that the upgraded DTW model features superior voice recognition capabilities, which could significantly improve online English education and lead to better teaching outcomes. [ABSTRACT FROM AUTHOR]

This is the second in a series of studies assessing the usability and reliability of a novel voice-based delivery system of mental health screening assessments. The previous study demonstrated the reliability and patient preference of a voice-based format of the Patient Health Questionnaire 9 (PHQ 9) for measuring major depression compared to a traditional paper format. Through this study, we further examined the Amazon Alexa tool in the administration of the General Anxiety Disorder 7 (GAD 7). With a replicated methodology to the first study, 40 newly administered patients completed the GAD 7 in one format at their first session and the alternate format at their follow up. Results from the new in clinic population replicated the findings observed in the first PHQ 9 study: GAD 7 assessment scores for the Alexa and paper version showed a high degree of reliability (α = 0.77), patients showed higher overall positive attitudes for the voice-based GAD 7 format, and subscales for attractiveness, stimulation, and novelty were significantly higher for the voiced-based format. Results also demonstrated 42 (84%) of the 50 patients who completed the voice-based format responded as being willing to use the device from home. With new recommendations of universal screening of anxiety disorders for patients below the age of 65 and rapid changes in virtual mental healthcare, convenient screenings are more important than ever. We believe this novel clinical assessment tool has the potential to improve patient behavioral healthcare while mitigating the workload of healthcare professionals. [ABSTRACT FROM AUTHOR]

Many social animals can recognize other individuals by their vocalizations. This requires a memory system capable of mapping incoming acoustic signals to one of many known individuals. Using the zebra finch, a social songbird that uses songs and distance calls to communicate individual identity (Elie and Theunissen, 2018), we tested the role of two cortical-like brain regions in a vocal recognition task. We found that the rostral region of the Cadomedial Nidopallium (NCM), a secondary auditory region of the avian pallium, was necessary for maintaining auditory memories for conspecific vocalizations in both male and female birds, whereas HVC (used as a proper name), a premotor areas that gates auditory input into the vocal motor and song learning pathways in male birds (Roberts and Mooney, 2013), was not. Both NCM and HVC have previously been implicated for processing the tutor song in the context of song learning (Sakata and Yazaki-Sugiyama, 2020). Our results suggest that NCM might not only store songs as templates for future vocal imitation but also songs and calls for perceptual discrimination of vocalizers in both male and female birds. NCM could therefore operate as a site for auditory memories for vocalizations used in various facets of communication. We also observed that new auditory memories could be acquired without intact HVC or NCM but that for these new memories NCM lesions caused deficits in either memory capacity or auditory discrimination. These results suggest that the high-capacity memory functions of the avian pallial auditory system depend on NCM.SIGNIFICANCE STATEMENT Many aspects of vocal communication require the formation of auditory memories. Voice recognition, for example, requires a memory for vocalizers to identify acoustical features. In both birds and primates, the locus and neural correlates of these high-level memories remain poorly described. Previous work suggests that this memory formation is mediated by high-level sensory areas, not traditional memory areas such as the hippocampus. Using lesion experiments, we show that one secondary auditory brain region in songbirds that had previously been implicated in storing song memories for vocal imitation is also implicated in storing vocal memories for individual recognition. The role of the neural circuits in this region in interpreting the meaning of communication calls should be investigated in the future.

Automatic Speech Recognition (ASR) technology has gained significant importance in modern communication systems, enabling the conversion of spoken language into written text. This research paper presents an in-depth analysis of voice recognition in the context of the Gujarati language, a tonal and multilingual language with unique phonetic characteristics. The study focuses on a meticulously curated Gujarati speech corpus, comprising diverse speakers of various ages, genders, and regional backgrounds. The corpus is subjected to detailed acoustic analysis, exploring prosodic features and tonal variations inherent in the language. Through the development and evaluation of ASR models, this research investigates the challenges and opportunities posed by the Gujarati language's phonemic complexity and tonal nuances. The findings shed light on the impact of corpus characteristics, including speaker diversity and phonemic inventory, on ASR model performance. As the field of voice recognition continues to advance, this research contributes valuable insights into effective ASR model design and training strategies for tonal languages, specifically focusing on the linguistic and acoustic peculiarities of Gujarati. The outcomes of this study offer directions for further advancements in ASR technology and corpus analysis, addressing the challenges of accurately capturing the intricate linguistic features of tonal languages for robust voice recognition systems. [ABSTRACT FROM AUTHOR]

Emotional stimuli and events are better and more easily remembered than neutral ones. However, this advantage appears to come at a cost, namely a decreased accuracy for peripheral, emotion-irrelevant details. There is some evidence, particularly in the visual modality, that this trade-off also applies to emotional expressions, leading to a difficulty in identifying an unfamiliar individual's identity when presented with an expression different from the one encountered at encoding. On the other hand, past research also suggests that identity recognition memory benefits from exposure to different encoding exemplars, although whether this is also the case for emotional expressions, particularly voices, remains unknown. Here, we directly addressed these questions by conducting a series of voice and face identity memory online studies, using a within-subject old/new recognition test in separate unimodal modules. In the Main Study, half of the identities were encoded with four presentations of one single expression (angry, fearful, happy, or sad; Uni condition) and the other half with one presentation of each emotion (Multi condition); all identities, intermixed with an equal number of new ones, were presented with a neutral expression in a subsequent recognition test. Participants (N = 547, 481 female) were randomly assigned to one of four groups in which a different Uni single emotion was used. Results, using linear mixed models on response choice and drift-diffusion-model parameters, revealed that high-arousal expressions interfered with emotion-independent identity recognition accuracy, but that such deficit could be compensated by presenting the same individual with various expressions (i.e., high exemplar variability). These findings were confirmed by a significant correlation between memory performance and stimulus arousal, across modalities and emotions, and by two follow-up studies (Study 1: N = 172, 150 female; Study 2: N = 174, 154 female), which extended the original observations and ruled out some potential confounding effects. Taken together, the findings reported here expand and refine our current knowledge of the influence of emotion on memory, and highlight the importance of, and interaction between, exemplar variability and emotional arousal in identity recognition memory. [ABSTRACT FROM AUTHOR]

Transcribing interviews is one of the most time-consuming and alienating tasks in qualitative research. Some have tried to bypass the problem by hiring external transcribers, which however can be very expensive. Whether due to the time and energy or the financial investment that transcribing requires, researchers therefore often self-impose a limit on the number of interviews that they conduct or even refuse to conduct interviews altogether. To prevent this and help reduce transcription fatigue, some scholars have developed the so-called "listen and repeat" technique. This involves speaking into a microphone what one hears through their headset while a voice recognition software transcribes word by word what it hears. However, this technique has many limitations and still requires a considerable amount of time and effort to be put by the researcher. This article introduces an alternative transcription technique which helps overcome these problems thanks to recent advancements of Artificial Intelligence in the field of voice recognition. Although the drawbacks and unintended consequences of Artificial Intelligence are often highlighted, this article explores its use for interview transcription showing that it can improve drastically the work and life of qualitative researchers. More specifically, this article introduces a transcription technique which allows to generate transcripts fully offline (avoiding in so doing the security concerns that the rising number of cloud-based transcription platforms often raise), rapidly and at little to no cost which one only needs to revise whilst listening to interview recordings, which is why I call this the "listen and revise" technique. [ABSTRACT FROM AUTHOR]

In Japan, the excessive length of time required for nursing records has become a social problem. A shift to concise "bulleted" records is needed to apply speech recognition and to work with foreign caregivers. Therefore, using 96,000 descriptively described anonymized nursing records, we identified typical situations for each information source and attempted to convert them to "bulleted" records using ChatGPT-3.5(For return from the operating room, Status on return, Temperature control, Blood drainage, Stoma care, Monitoring, Respiration and Oxygen, Sensation and pain, etc.). The results showed that ChatGPT-3.5 has some usable functionality as a tool for extracting keywords in "bulleted" records. Furthermore, through the process of converting to a "bulleted" record, it became clear that the transition to a standardized nursing record utilizing the "Standard Terminology for Nursing Observation and Action (STerNOA)" would be facilitated. [ABSTRACT FROM AUTHOR]

Individual speech impairment damages a specific region of the brain, which is the main cause of aphasia. The goal is to develop a method, namely Jaya Gazelle algorithm-conv-transformer transducer + deep residual network (JGA_CTT+DRN), for speech intelligibility with aphasia. The input voice signal is first exposed to signal preprocessing using a Gaussian filter. The preprocessed output is given to the feature extraction phase, where specific features like the zero-crossing rate, spectral roll-off, spectral centroid, MFCC-Mel-frequency cepstral coefficients, probability of voicing, linear prediction cepstral coefficients (LPCC), chromogram, empirical mode decomposition (EMD), and statistical features, namely energy and entropy, are extracted. Nonlinear spectral subtraction is then applied for voice enhancement. Following that, voice recognition is performed using a CTT, and the training process proceeds using Jaya Gazelle optimization (JGO), which is created by fusing the Jaya algorithm and the Gazelle optimization algorithm (GOA). Finally, speech is transformed into text when the language and pronunciation model have been developed. Moreover, developed JGA_CTT+DRN is evaluated for its performance by three metrics like positive predictive value (PPV), recognition accuracy and negative predictive value (NPV), with higher values of 92%, 93% and 91.9%. [ABSTRACT FROM AUTHOR]

Voice notes, spoken messages recorded and sent via smartphones, have become a widespread means of communication. A likely consequence of this situation is that voice note users become more frequently exposed to recordings of their own voices (self-voices). This correlational study examined if frequent exposure to recordings of the self-voice via voice note replay was associated with improved self-voice recognition (accuracy and response latency) and self-voice liking. Participants (N = 128), regular voice note users, reported voice note replay frequency. They also reported self-voice satisfaction/liking. Finally, participants completed a novel self-voice recognition task, where, across 20 trials, they identified whether a recording was them (self-voice) or not (non-self-voice). The tendency to frequently replay voice notes was positively correlated with self-voice liking and recognition accuracy. These findings may have implications for the treatment of social anxiety disorder and auditory verbal hallucinations.

Abstract Violent crime cases which include, robbery, rape, and homicide are terribly on the rise, and the role of security in combating this menace cannot be overemphasized. This research presents a security device that aims at fighting violent crimes using voice recognition technology. The work also tends to solve the issue of network downtime when the user is out of reach for help in time of attack. In this work, a voice processing unit which comprises the condenser microphone, an amplifier, a shift register, and a timer was designed. The processing unit circuit was incorporated into microcontrollers which create Human-Device interaction and the GSM communication unit which is made up of two GSM modules. The two microcontrollers used in the design are PIC18F4520 and PIC16F873A. The microcontrollers were programmed with C++ using the MPLAB IDE software and the circuit simulation was done using Proteus Design Suite version 8. The result shows that the appropriate authority receives SMS whenever the pre-recorded code is mentioned. The result also shows that during network downtime, the second GSM module sends an SMS to the appropriate authority. Evaluating the performance of this work, it was observed that the device works best in a calm area compared to a noisy area. This work is designed to work in domestic areas like homes, offices, malls, and mainly areas free from so much noise. Therefore, this work has successfully reduced the crime rate in emergencies.

Abstract Voice identification is being increasingly adopted in various domains, including security infrastructures, intelligent home systems, and personalised digital assistants. Notably, it harbours significant promise in transforming healthcare, especially in electronic health record detecting and speech impairment monitoring such as aphasia. Current strategies such as acoustic models based on deep learning, voice bio‐metrics, and spectrogram analysis, have been identified with several drawbacks including vulnerability to altered voices, susceptibility to ambient noise, and the necessity for significant computational power. In response to these issues, the authors introduce a ground‐breaking method of voice identification using Ultra‐Wideband (UWB) technology. This method capitalises on the micro‐Doppler shifts associated with movements of the laryngeal prominence. The distinctive nature of these bio‐metric traits related to speech production provides superior resistance against common pitfalls of voice identification. The proposed model leverages the high‐resolution characteristics of UWB to register tiny variations in laryngeal movements produced during speech, thus forming a distinct voice profile for each speaker. Through rigorous testing, the proposed system demonstrated significant progress in voice identification, achieving close to 90% accuracy in controlled experimental settings. This breakthrough indicates that UWB‐enabled voice identification could have a profound effect on medical applications, providing potential improvements in diagnosing, monitoring, possibly treating speech disorders, and thereby shaping a future of enhanced and secured healthcare services.

Industrial robots are indispensable in modern manufacturing across various sectors, including nuclear, chemical, and aerospace industries. They serve to replace humans in hazardous operations, ensuring worker safety, while also enhancing production efficiency and product quality, particularly in tasks such as welding and assembly. However, the maintenance and repair of these robots present significant challenges. When malfunctions occur, workers often face the daunting task of sifting through extensive industrial manuals to diagnose the root cause based on error codes, a process that is time-consuming and hampers productivity.To address this issue, this paper proposes an intelligent voice query method designed to facilitate access to industrial manual content. The goal is to empower workers to swiftly comprehend the causes of robot failures and retrieve corresponding solutions through interactive voice commands, thereby streamlining troubleshooting efforts. Leveraging voice recognition technology, workers can effortlessly issue queries without the need for manual search and interpretation. The effectiveness of this method was rigorously evaluated through experimental validation in real-world scenarios, demonstrating notable improvements in maintenance efficiency.

Speech recognition is a captivating process that revolutionizes human-computer interactions, allowing us to interact and control machines through spoken commands. The foundation of speech recognition lies in understanding a given language’s linguistic and textual characteristics. Although automatic speech recognition (ASR) systems flawlessly convert speech into text for various international languages, their implementation for Arabic remains inadequate. In this research, we diligently explore the current state of Arabic ASR systems and unveil the challenges encountered during their development. We categorize these challenges into two groups: those specific to the Arabic language and those more general. We propose strategies to overcome these obstacles and emphasize the need for ASR architectures tailored to the Arabic language’s unique grammatical and phonetic structure. In addition, we provide a comprehensive and explicit description of various feature extraction methods, language models, and acoustic models utilized in the Arabic ASR system.

It is not always possible to find enough data for deep learning studies. So, various data augmentation techniques have been developed and thus the success of deep learning models has increased. In this work, a comprehensive study has been conducted to evaluate the efficiency of different data augmentation techniques in terms of improving the voice classification models' performance. To this end, we proposed extracting MFCC features from the audio files, converting them into RGB images, and using CNN deep learning model for classifying the constructed RGB images into 12 classes. Moreover, Random search algorithm has been adopted for tuning the hyperparameters and selecting the best CNN model that can achieve this task with as high performance as possible. After that, some voice augmentation and image augmentation techniques have been used to increase the number of samples in the original dataset, and 17 different datasets have been constructed and used for training the proposed model. Particularly, 5 different voice augmentation techniques have been used for constructing 5 different datasets from the original dataset. When the proposed model has been trained using these voice augmentation-based datasets the validation accuracy and F1-score exceed 95%. Then, we suggested using image augmentation techniques for constructing another dataset from the original dataset. By training the model using this dataset we noted that the validation accuracy and F1-score of the proposed model dropped down to 81,92 and 81.67 respectively. Afterward, we suggested applying image augmentation techniques to the voice augmentation techniques-based datasets, and 5 different datasets have been constructed using this method. The results obtained by training the proposed model using these datasets showed that the classification accuracy and F1-score dropped down to 77.25 and 77.08 respectively. So, we concluded that the image augmentation techniques are not so suitable for voice recognition and classification tasks. To prof this hypothesis, we suggested merging the image augmentation-based dataset with voice augmentation-based datasets (i.e. the dataset gave the best results in this study), and 5 different datasets, each of which contains 18,000 samples, have been constructed using this method. When the proposed model has been trained using these datasets the classification accuracy and F1-score did not exceed 84.33% and 84.41% respectively in the best case. Furthermore, in order to prove the obtained results we suggested testing the proposed method using one more dataset from a different language namely the Turkish language dataset. The proposed approach gave more than 96% of classification accuracy when tested using this dataset i.e. Turkish dataset. The obtained results showed that it is preferred to apply voice augmentation techniques to the raw audio files instead of applying image augmentation techniques to the extracted feature matrixes in order to improve the performance of voice classification deep learning models. [ABSTRACT FROM AUTHOR]

The information content of the parameters of a spectral voice source model in an automatic voice identity recognition problem is studied. For the voice parameters, the identity recognition error was 20.8%; using these parameters together with the pitch period reduced the error to 13.8%. Lastly, the combined use of the spectral model parameters with the pitch period and mel-frequency cepstral coefficients provided the highest accuracy (the recognition error was 1.2%). [ABSTRACT FROM AUTHOR]

Voice identification is being increasingly adopted in various domains, including security infrastructures, intelligent home systems, and personalised digital assistants. Notably, it harbours significant promise in transforming healthcare, especially in electronic health record detecting and speech impairment monitoring such as aphasia. Current strategies such as acoustic models based on deep learning, voice bio‐metrics, and spectrogram analysis, have been identified with several drawbacks including vulnerability to altered voices, susceptibility to ambient noise, and the necessity for significant computational power. In response to these issues, the authors introduce a ground‐breaking method of voice identification using Ultra‐Wideband (UWB) technology. This method capitalises on the micro‐Doppler shifts associated with movements of the laryngeal prominence. The distinctive nature of these bio‐metric traits related to speech production provides superior resistance against common pitfalls of voice identification. The proposed model leverages the high‐resolution characteristics of UWB to register tiny variations in laryngeal movements produced during speech, thus forming a distinct voice profile for each speaker. Through rigorous testing, the proposed system demonstrated significant progress in voice identification, achieving close to 90% accuracy in controlled experimental settings. This breakthrough indicates that UWB‐enabled voice identification could have a profound effect on medical applications, providing potential improvements in diagnosing, monitoring, possibly treating speech disorders, and thereby shaping a future of enhanced and secured healthcare services. [ABSTRACT FROM AUTHOR]

This paper introduces three system architectures for speaker identification that aim to overcome the limitations of diarization and voice-based biometric systems. Diarization systems utilize unsupervised algorithms to segment audio data based on the time boundaries of utterances, but they do not distinguish individual speakers. On the other hand, voice-based biometric systems can only identify individuals in recordings with a single speaker. Identifying speakers in recordings of natural conversations can be challenging, especially when emotional shifts can alter voice characteristics, making gender identification difficult. To address this issue, the proposed architectures include techniques for gender, emotion, and diarization at either the segment or group level. The evaluation of these architectures utilized two speech databases, namely VoxCeleb and RAVDESS (Ryerson audio-visual database of emotional speech and song) datasets. The findings reveal that the proposed approach outperforms the strategy level in terms of recognition results, despite the real-time processing advantage of the latter. The challenge of identifying multiple speakers engaging in a conversation while considering emotional changes that impact speech is effectively addressed by the proposed architectures. The data indicates that the gender and emotion classification of diarization achieves an accuracy of over 98 percent. These results suggest that the proposed speech-based approach can achieve highly accurate speaker identification. [ABSTRACT FROM AUTHOR]

This research aims to develop a system capable of processing voice input to recognize Al-Quran reading by recitation of Tajwid, using wavelet signal extraction and classification of Tajwid rules using ANFIS. The process stages include data acquisition, audio data preprocessing, extraction using wavelet packets, division of training data and test data, and classification. The data obtained were 20 observations from 10 observations carried out in data pre-processing. The wavelet decomposition process produces six main features as ANFIS input variables and 64 rules. Then the data was separated into 17 observations for training data and three for testing data. The test results obtained from the training that had been carried out produced plots that were too fit; in this experiment, the WPANFIS classification model got 100% appropriate classification and SSE values that were the same as the training result, 0.00081225. [ABSTRACT FROM AUTHOR]

Multisensory context often facilitates perception and memory. In fact, encoding items within a multisensory context can improve memory even on strictly unisensory tests (i.e., when the multisensory context is absent). Prior studies that have consistently found these multisensory facilitation effects have largely employed multisensory contexts in which the stimuli were meaningfully related to the items targeting for remembering (e.g., pairing canonical sounds and images). Other studies have used unrelated stimuli as multisensory context. A third possible type of multisensory context is one that is environmentally related simply because the stimuli are often encountered together in the real world. We predicted that encountering such a multisensory context would also enhance memory through cross-modal associations, or representations relating to one's prior multisensory experience with that sort of stimuli in general. In two memory experiments, we used faces and voices of unfamiliar people as everyday stimuli individuals have substantial experience integrating the perceptual features of. We assigned participants to face- or voice-recognition groups and ensured that, during the study phase, half of the face or voice targets were encountered also with information in the other modality. Voices initially encoded along with faces were consistently remembered better, providing evidence that cross-modal associations could explain the observed multisensory facilitation. [ABSTRACT FROM AUTHOR]

Voice recognition systems have gained significant prevalence in our everyday lives, encompassing a wide range of applications, from virtual assistants on smartphones to voicecontrolled home automation systems. This research paper presents a comprehensive design and implementation of a voice recognition security system employing artificial neural networks. The system's training involved a dataset consisting of 900 audio samples collected from 10 distinct speakers, enabling the resulting model to accurately classify the speaker of a given audio sample. For the implementation of the voice recognition system, Python serves as the primary programming language. The system leverages the Keras library, which offers a high-level interface for constructing and training neural networks, with efficient computation facilitated by the TensorFlow back-end. Additionally, the Flask framework, a Python-based web framework, was utilized to create a user interface in the form of a web application for the voice recognition system. To effectively train the artificial neural network, the audio data undergoes preprocessing, involving the extraction of relevant features from the audio samples. Subsequently, during the preprocessing phase, the audio data is labelled, and the neural network is trained on this labelled dataset to learn the classification of different speakers. The trained model was rigorously tested on a set of previously unseen audio samples, yielding an impressive classification accuracy exceeding 96%. The finalized model will be integrated into the web application, enabling users to upload audio files and receive accurate predictions regarding the speaker's identity. This paper demonstrates the efficacy of artificial neural networks in the context of voice recognition systems, while also providing a practical framework for constructing such systems using readily available tools and libraries. [ABSTRACT FROM AUTHOR]

The increasing prevalence of digital interactions in our lives has raised concerns regarding social withdrawal, exemplified by the hikikomori phenomenon. To combat this issue, we introduce PointPal, an intelligent social platform aimed at bridging the gap between online engagement and real-world interactions, with a particular focus on addressing challenges associated with excessive internet use and hikikomori tendencies. PointPal provides a sophisticated digital environment where users can securely connect based on mutual interests, facilitating a seamless transition from virtual conversations to in-person meetings. Incorporating artificial intelligence voice recognition technology enhances accessibility and safety, while a personal safety button addresses concerns about meeting unfamiliar individuals online, promoting secure navigation of the digital landscape and encouraging more sustainable usage patterns. Through a comprehensive survey conducted among a diverse group in the UAE, including young adults, residents, tourists, and travellers, we identified key features deemed essential for facilitating offline meetups. The Interactive Map emerged as the top priority, followed by AI Chatbot Assistance, emphasizing the importance of user support, and User Meetup Reviews, highlighting the value of peer feedback. Conversely, Photo & Media Sharing was considered less vital. By integrating an Interactive Map and AI Chatbot Assistance, PointPal endeavours to revolutionize the social application industry, substantiating its potential value. Built on a microservices architecture, the system ensures modularity and scalability, comprising essential services such as User Management, Interest Management, Meeting Management, Chat, Moderation, and AI Chatbot microservices. The incorporation of AI sound recognition provides users with a natural and intuitive means of interaction, distinguishing PointPal by fostering meaningful connections and guaranteeing socially secure internet navigation, thereby surpassing existing applications.