Search

As an important piece of equipment in industrial production, the health of an air compressor directly impacts the success of production. Therefore, researching fault diagnosis methods for air compressors is of significant importance in improving the continuity, reliability, and safety of production. Traditional fault diagnosis methods, however, struggle to obtain accurate fault features. The measurement of feature distribution differences between various working conditions lacks sufficient domain adaptability, making it challenging to achieve high recognition accuracy. Additionally, the operation of air compressors generates background noise, which can introduce interference and impact the accuracy in fault detection. In order to overcome these limitations, a fault diagnosis method for air compressors based on feature fusion is proposed. Firstly, the Mel-frequency cepstral coefficients (MFCC) features and wavelet transform features of the air compressor are extracted separately. Then, late fusion is applied at the decision level to combine confidence scores and predicted bounding boxes. The best network model is determined based on evaluation metrics to complete the classification. Based on the experimental results analysis, the feature fusion method demonstrated superior recognition performance. [ABSTRACT FROM AUTHOR]

This paper describes a study on speaker recognition using the ECAPA-TDNN architecture, which stands for Extended Context-Aware Parallel Aggregations Time-Delay Neural Network. It utilizes X-vectors, a method for extracting speaker features by converting speech into fixed-length vectors, and introduces a squeeze-and-excitation block to model dependencies between channels. In order to better explore temporal relationships in the context of speaker recognition and improve the algorithm's generalization performance in complex acoustic scenarios, this study adds input gates and forget gates to the ECAPA-TDNN architecture, combining them with CIFG (Convolutional LSTM with Input and Forget Gates) modules. These are embedded into a residual structure of multi-layer aggregated features. A sub-center Arcface, an improved loss function based on Arcface, is used for selecting sub-centers for subclass discrimination, retaining advantageous sub-centers to enhance intra-class compactness and strengthen the robustness of the network. Experimental results demonstrate that the improved ECAPA-TDNN-CIFG in this study outperforms the baseline model, yielding more accurate and efficient recognition results. [ABSTRACT FROM AUTHOR]

Purpose – The safe operation of the metro power transformer directly relates to the safety and efficiency of the entire metro system. Through voiceprint technology, the sounds emitted by the transformer can be monitored in real-time, thereby achieving real-time monitoring of the transformer’s operational status. However, the environment surrounding power transformers is filled with various interfering sounds that intertwine with both the normal operational voiceprints and faulty voiceprints of the transformer, severely impacting the accuracy and reliability of voiceprint identification. Therefore, effective preprocessing steps are required to identify and separate the sound signals of transformer operation, which is a prerequisite for subsequent analysis. Design/methodology/approach – This paper proposes an Adaptive Threshold Repeating Pattern Extraction Technique (REPET) algorithm to separate and denoise the transformer operation sound signals. By analyzing the Short-Time Fourier Transform (STFT) amplitude spectrum, the algorithm identifies and utilizes the repeating periodic structures within the signal to automatically adjust the threshold, effectively distinguishing and extracting stable background signals from transient foreground events. The REPET algorithm first calculates the autocorrelation matrix of the signal to determine the repeating period, then constructs a repeating segment model. Through comparison with the amplitude spectrum of the original signal, repeating patterns are extracted and a soft time-frequency mask is generated. Findings – After adaptive thresholding processing, the target signal is separated. Experiments conducted on mixed sounds to separate background sounds from foreground sounds using this algorithm and comparing the results with those obtained using the FastICA algorithm demonstrate that the Adaptive Threshold REPET method achieves good separation effects. Originality/value – A REPET method with adaptive threshold is proposed, which adopts the dynamic threshold adjustment mechanism, adaptively calculates the threshold for blind source separation and improves the adaptability and robustness of the algorithm to the statistical characteristics of the signal. It also lays the foundation for transformer fault detection based on acoustic fingerprinting.

Abstract With the continuous development and application of online interactive activities and network transmission technology, online interactive behaviors such as online discussion meetings and online teaching have become indispensable in people’s studies and work. However, the effectiveness of working with online discussions and feedback from participants on their conference performance has been a major concern, and this is the issue examined in this post. Based on the above issues, this paper designs an online discussion activity-level evaluation system based on voiceprint recognition technology. The application system developed in this project is divided into two parts; the first part is to segment the online discussion audio into multiple independent audio segments by audio segmentation technology and train the voiceprint recognition model to predict the speaker’s identity in each separate audio component. In the second part, we propose a linear normalized online meeting activity-level calculation model based on the modified main indexes by traversing and counting each participant’s speaking frequency and total speaking time as the main indexes for activity-level evaluation. To make the evaluation results more objective, reasonable, and distinguishable, the activity score of each participant is calculated, and each participant’s activity-level in the discussion meeting is derived by combining the fuzzy membership function. To test the system’s performance, we designed an experiment with 25 participants in an online discussion meeting, with two assistants manually recording the discussion and a host moderating the meeting. The results of the experiment showed that the system’s evaluation results matched those recorded by the two assistants. The system can fulfill the task of distinguishing the level of activity of participants in online discussions.

Aiming at the problems of insufficient feature expression ability and weak generalization ability of the traditional Res2Net model in the field of voice print recognition, this paper proposes a feature extraction module known as the SE-DR-Res2Block, which combinedly uses dense connection and residual connection. The combination of low-semantic features with spatial information characteristics allows focusing more on detailed information and high-semantic information that concentrates on global information as well as abstract features. This can compensate for the loss of some detailed information caused by abstraction. First, the feature of each layer in the dense connection structure is derived from the feature output of all previous layers to realize feature reuse. Second, the structure and working principle of the ECAPA-TDNN network using traditional Res2Block is introduced. To achieve more efficient feature extraction, the dense connection is used to further realize full feature mining. Based on SE-block, a more efficient feature extraction module, SE-DR-Res2Net, is proposed by combining the residual join and dense links. As compared to the traditional SE-Block structures, the convolutional layers are used here instead of fully connected layers. Because they not only reduce the number of parameters needed for training but also allow weight sharing, thereby reducing overfitting. Therefore, effective extraction of feature information from different layers is essential for obtaining multiscale expression as well as maximizing the reuse of features. During the collection of more scale-specific feature information, a large number of dense structures can lead to a dramatic increase in parameters and computational complexity. By using partial residual structures instead of dense structures, we can effectively prevent the dramatic increase in parameter quantity while maintaining the performance to a certain extent. Finally, to verify the effectiveness of the module, SE-Res2block, Full-SE-Res2block, SE-DR-Res2block, and Full-SE-DR-Res2block are adopted based on the different network models. Voxceleb1 and SITW (speakers in the wild) datasets were used for Voxceleb1 and SITW, respectively. The performance comparison of Res2Net-50 models with different modules on the Voxceleb1 dataset shows that SE-DR-Res2Net-50 achieves the best equal error rate of 3.51%, which also validates the adaptability of this module on different networks. The usage of different modules on different networks, as well as experiments and analyses conducted on different datasets, were compared. The experimental results showed that the optimal equal error rates of the ECAPA-TDNN network model using SE-DR-Res2block had reached 2.24% and 3.65%, respectively. This verifies the feature expression ability of this module, and the corresponding results based on different test data sets also confirm its excellent generalization ability.

This paper explores the process of traditional voiceprint recognition, analyzes the traditional GMM recognition algorithm, and proposes a GE2E-based voiceprint recognition algorithm by combining it with the deep neural network. It firstly uses the Bi-GRU network to replace the LSTM network to prevent the lack of semantic information, then adds the SGD algorithm to optimize the speech features, and finally improves the stability and accuracy of recognition by the GE2E loss function. On this basis, a voiceprint recognition system based on GE2E is designed, and the overall performance of the system is tested. Additionally, a voiceprint recognition system is being explored for fault localization. The results show that the recognition accuracy of male voiceprints in the test is at [0.89,0.95], and the recognition accuracy of female voiceprints is at [0.88,0.96], and there is not much difference in the voiceprint recognition accuracy of the voiceprint recognition system for both male and female students, and the overall recognition accuracy is greater than 0.9. When applied in fault location, the error between the measured distance and the actual fault distance is within 0.1 meters, enabling fault location.

(1) Background: Voiceprint recognition technology uses individual vocal characteristics for identity authentication and faces many challenges in cross-scenario applications. The sound environment, device characteristics, and recording conditions in different scenarios cause changes in sound features, which, in turn, affect the accuracy of voiceprint recognition. (2) Methods: Based on the latest trends in deep learning, this paper uses the perceptual wavelet packet entropy (PWPE) method to extract the basic voiceprint features of the speaker before using the efficient channel attention (ECA) block and the Res2Net block to extract deep features. The PWPE block removes the effect of environmental noise on voiceprint features, so the perceptual wavelet packet entropy-guided ECA–Res2Net–Time-Delay-Neural-Network (PWPE-ECA-Res2Net-TDNN) model shows an excellent robustness. The ECA-Res2Net-TDNN block uses temporal statistical pooling with a multi-head attention mechanism to weight frame-level audio features, resulting in a weighted average of the final representation of the speech-level feature vectors. The sub-center ArcFace loss function is used to enhance intra-class compactness and inter-class differences, avoiding classification via output value alone like the softmax loss function. Based on the aforementioned elements, the PWPE-ECA-Res2Net-TDNN model for speaker recognition is designed to extract speaker feature embeddings more efficiently in cross-scenario applications. (3) Conclusions: The experimental results demonstrate that, compared to the ECAPA-TDNN model using MFCC features, the PWPE-based ECAPA-TDNN model performs better in terms of cross-scene recognition accuracy, exhibiting a stronger robustness and better noise resistance. Furthermore, the model maintains a relatively short recognition time even under the highest recognition rate conditions. Finally, a set of ablation experiments targeting each module of the proposed model is conducted. The results indicate that each module contributes to an improvement in the recognition performance. [ABSTRACT FROM AUTHOR]

High-voltage reactor is one of the critical equipment to ensure the safe and stable operation of power system. As the fault of high-voltage reactor is difficult to be identified accurately， a voiceprint recognition method based on LSTM （long short-term memory） neural network for high-voltage reactor faults is proposed. Firstly， the voiceprint signals generated during the operation of a high-voltage reactor are collected. Then the signals are divided into several segments， converted into a spectrogram， and the Mel time spectrum is used to reduce the dimensionality. Finally， the LSTM network is used to identify the high-voltage reactor faults in the spectrogram. The experimental results show that the proposed method can realize the intelligent diagnosis of high-voltage reactor faults， effectively improve the accuracy of fault identification， reduce the manpower required for fault detection， and improve the intelligent level of power grid safety monitoring.

Aiming at the difficulty of manual detection and high costs in the detection of wear defects in mine filling pipelines, a densely connected convolutional neural network model (SE＿DenseNet) integrated with SENet is proposed, which can realize remote and rapid identification of filling pipeline wear. The method firstly reconstructs the components with high correlation with the original signal through complete ensemble empirical mode decomposition (CEEMDAN). After that, the short-time Fourier transform is used to transform the acoustic signal recognition problem into an image recognition problem. And finally, the spectrogram is input into the DenseNet network model, and through feature reuse, the channel attention mechanism SENet is fused to enhance the feature information, and the accurate voiceprint recognition of the filling pipeline wear sound signal is realized. The results show that the accuracy of SE＿DenseNet recognition can reach 97.368%. Compared with the similar deep baseline network models ResNet101 and DenseNet121,the generalization ability and recognition accuracy of the network model have been improved, the number of model parameters has decreased, so the model can converge faster. The above advantages of SE＿DenseNet can be applied to similar non-destructive testing of solid-liquid two-phase flow pipelines. [ABSTRACT FROM AUTHOR]

Voiceprint recognition can extract voice features and identity the speaker through the voice information, which has great application prospects in personnel identity verification and voice dispatching in the electric industry. The traditional voiceprint recognition algorithms work well in a quiet environment. However, noise interference inevitably exists in the electric industry, degrading the accuracy of traditional voiceprint recognition algorithms. In this paper, we propose an enhanced deep residual shrinkage network (EDRSN)-based voiceprint recognition by combining the traditional voiceprint recognition algorithms with deep learning (DL) in the context of the noisy electric industry environment, where a dual-path convolution recurrent network (DPCRN) is employed to reduce the noise, and its structure is also improved based on the deep residual shrinkage network (DRSN). Moreover, we further use a convolutional block attention mechanism (CBAM) module and a hybrid dilated convolution (HDC) in the proposed EDRSN. Simulation results show that the proposed network can enhance the speaker's vocal features and further distinguish and eliminate the noise features, thus reducing the noise influence and achieving better recognition performance in a noisy electric environment. [ABSTRACT FROM AUTHOR]

In multi-speaker scenarios, speech processing tasks like speaker identification and speech recognition are susceptible to noise and overlapped voices. As the overlapped voices are a complicated mixture of signals, a target extraction method from this mixture is a good front-end solution for further processing like understanding and classifying. The quality of speech separation can be assessed by the noise ratio or subjective scoring and can also be assessed by accuracy of the downstream processing tasks like speaker identification. In order to make the separation model and speaker identification model more adapted to complex multi-speaker speech overlapping scenarios, this research investigates the speech separation model and incorporate with a voiceprint recognition task. This paper proposes a feature-scale single channel speech separation network connected to a back-end speaker verification network with MFCCT features, so the accuracy of speaker identification indicates the quality of speech separation task. The datasets are prepared by synthesizing Voxceleb1 data, and used for training and testing. The results show that using an objective downstream evaluation can effectively improve the overall performance, as the optimized speech separation model significantly reduced the error rate of speaker verification.

(1) Background: Voiceprint recognition technology uses individual vocal characteristics for identity authentication and faces many challenges in cross-scenario applications. The sound environment, device characteristics, and recording conditions in different scenarios cause changes in sound features, which, in turn, affect the accuracy of voiceprint recognition. (2) Methods: Based on the latest trends in deep learning, this paper uses the perceptual wavelet packet entropy (PWPE) method to extract the basic voiceprint features of the speaker before using the efficient channel attention (ECA) block and the Res2Net block to extract deep features. The PWPE block removes the effect of environmental noise on voiceprint features, so the perceptual wavelet packet entropy-guided ECA–Res2Net–Time-Delay-Neural-Network (PWPE-ECA-Res2Net-TDNN) model shows an excellent robustness. The ECA-Res2Net-TDNN block uses temporal statistical pooling with a multi-head attention mechanism to weight frame-level audio features, resulting in a weighted average of the final representation of the speech-level feature vectors. The sub-center ArcFace loss function is used to enhance intra-class compactness and inter-class differences, avoiding classification via output value alone like the softmax loss function. Based on the aforementioned elements, the PWPE-ECA-Res2Net-TDNN model for speaker recognition is designed to extract speaker feature embeddings more efficiently in cross-scenario applications. (3) Conclusions: The experimental results demonstrate that, compared to the ECAPA-TDNN model using MFCC features, the PWPE-based ECAPA-TDNN model performs better in terms of cross-scene recognition accuracy, exhibiting a stronger robustness and better noise resistance. Furthermore, the model maintains a relatively short recognition time even under the highest recognition rate conditions. Finally, a set of ablation experiments targeting each module of the proposed model is conducted. The results indicate that each module contributes to an improvement in the recognition performance.

Abstract With the sharp booming of online live streaming platforms, some anchors seek profits and accumulate popularity by mixing inappropriate content into live programs. After being blacklisted, these anchors even forged their identities to change the platform to continue live, causing great harm to the network environment. Therefore, we propose an anchor voiceprint recognition in live streaming via RawNet-SA and gated recurrent unit (GRU) for anchor identification of live platform. First, the speech of the anchor is extracted from the live streaming by using voice activation detection (VAD) and speech separation. Then, the feature sequence of anchor voiceprint is generated from the speech waveform with the self-attention network RawNet-SA. Finally, the feature sequence of anchor voiceprint is aggregated by GRU to transform into a deep voiceprint feature vector for anchor recognition. Experiments are conducted on the VoxCeleb, CN-Celeb, and MUSAN dataset, and the competitive results demonstrate that our method can effectively recognize the anchor voiceprint in video streaming.

In order to improve the recognition performance of voiceprint recognition technology? DenseNet is applied to the spectrogram to realize voiceprint recognition. DenseNet is optimized from two aspects: improving the computing efficiency of the network and enhancing the characterization ability of voiceprint features. Dep th separable convolution is used to reduce the amount of network parameters, and center loss function item is increased to improve the characterization ability of voiceprint features. The training results show that, through the depth separable convolution, the network parameters are reduced by 25. 5%, and the model size is reduced by 24. 6%; The simulation results show that the increase of the center loss item makes the clustering effect of the voiceprint feature more obvious and improves the characterization ability of voiceprint features. Therefore? the improved DenseNet can achieve good recognition results in the field of spectrogram and voiceprint recognition. [ABSTRACT FROM AUTHOR]

With the sharp booming of online live streaming platforms, some anchors seek profits and accumulate popularity by mixing inappropriate content into live programs. After being blacklisted, these anchors even forged their identities to change the platform to continue live, causing great harm to the network environment. Therefore, we propose an anchor voiceprint recognition in live streaming via RawNet-SA and gated recurrent unit (GRU) for anchor identification of live platform. First, the speech of the anchor is extracted from the live streaming by using voice activation detection (VAD) and speech separation. Then, the feature sequence of anchor voiceprint is generated from the speech waveform with the self-attention network RawNet-SA. Finally, the feature sequence of anchor voiceprint is aggregated by GRU to transform into a deep voiceprint feature vector for anchor recognition. Experiments are conducted on the VoxCeleb, CN-Celeb, and MUSAN dataset, and the competitive results demonstrate that our method can effectively recognize the anchor voiceprint in video streaming. [ABSTRACT FROM AUTHOR]

A voiceprint recognition method based on improved pooling strategy for convolutional neural networks (CNN) is proposed. For the voiceprint recognition, the voice signal is quantized and pre-emphasized, and then the processed voice information is framed and windowed, and the voiceprint information of the self-built digital voiceprint library is converted into a score map to construct a digital voiceprint database. Then an CNN based voiceprint recognition method by introducing an improved pooling method is proposed. The new pooling method is to square the activation value after the activation function, and assign the square number probability to realize the random pooling. This method can not only preserve the feature extraction of the maximum pooling method, but also absorb the advantage of random pooling. It retains the possibility of extracting hidden features, and effectively enhancing the generalization ability of the network. The traditional convolutional neural network LeNet-5 is modified by adopting the improved pooling method and introducing the Dropout idea so as to an improved LeNet-5 network. The voiceprint recognition experiments were performed by using the gray-scale digital spectrogramon in the self-built voiceprint database through the improved LeNet-5 network. The recognition experiments were performed on the VGG-16 network using the three-channel color digital spectrum map. An automatic voiceprint recognition system was built to detect voiceprints in real-time voice information. The simulation results verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The development of pressure sensors with high sensitivity and a low detection limit for subtle mechanical force monitoring and the understanding of the sensing mechanism behind subtle mechanical force monitoring are of great significance for intelligent technology. Here, we proposed a graphene-based two-stage enhancement pressure sensor (GTEPS), and we analyzed the difference between subtle mechanical force monitoring and conventional mechanical force monitoring. The GTEPS exhibited a high sensitivity of 62.2 kPa -1 and a low detection limit of 0.1 Pa. Leveraging its excellent performance, the GTEPS was successfully applied in various subtle mechanical force monitoring applications, including acoustic wave detection, voice-print recognition, and pulse wave monitoring. In acoustic wave detection, the GTEPS achieved a 100% recognition accuracy for six words. In voiceprint recognition, the sensor exhibited accurate identification of distinct voiceprints among individuals. Furthermore, in pulse wave monitoring, GTEPS demonstrated effective detection of pulse waves. By combination of the pulse wave signals with electrocardiogram (ECG) signals, it enabled the assessment of blood pressure. These results demonstrate the excellent performance of GTEPS and highlight its great potential for subtle mechanical force monitoring and its various applications. The current results indicate that GTEPS shows great potential for applications in subtle mechanical force monitoring.

In air traffic control (ATC), speech communication with radio transmission is the primary way to exchange information between the controller and aircrew. A wealth of contextual situational dynamics is embedded implicitly; thus, understanding the spoken instruction is particularly significant to the ATC research. In this paper, a comprehensive review related to spoken instruction understanding (SIU) in the ATC domain is provided from the perspective of the challenges, techniques, and applications. Firstly, a full pipeline is represented to achieve the SIU task, including automatic speech recognition, language understanding, and voiceprint recognition. A total of 10 technique challenges are analyzed based on the ATC task specificities. In succession, the common techniques for SIU tasks are categorized from common applications, and extensive works in the ATC domain are also reviewed. Finally, a series of future research topics are also prospected based on the corresponding challenges. The author sincerely hopes that this work is able to provide a clear technical roadmap for the SIU tasks in the ATC domain and further make contributions to the research community.

Voiceprint recognition is one of the most popular biometric identification technologies, which can identify a speaker based on his voice. This paper proposed CDRNN, a voiceprint recognition scheme. CDRNN combined CNN and deep RNN into a unified model and took advantages of both of them. For CNN was good at extracting characteristics from images, it could generate several spectrograms based on the original voice signal at first. And then, CNN would extract unique features from these spectrograms. Finally, deep RNN would output the speaker’s identification based on these unique features. Simulation results show that CDRNN performs better than GMM-UBM and DNN-based approach. [ABSTRACT FROM AUTHOR]

Research on Tibetan voiceprint recognition technology has just started, and it is an urgent and necessary task to establish a corpus. We design and build a corpus based on the characteristics of Tibetan language, which consists of two parts:text-dependent part and text-independent part. Texts of the corpus are collected from a variety of materials, including newspaper, literature, education, science and technology, Buddhism, and history and traditional culture. As for the recording part, we invite 50 speakers from different regions of Tibet. The corpus contains 9500 speech files and it lays a certain foundation for Tibetan voiceprint recognition. [ABSTRACT FROM AUTHOR]

Community corrections agencies across the world have adopted biometric technologies as a security tool and cost-effective monitoring strategy. This study investigates the effectiveness of the automated voiceprint recognition supervision (AVRS) curfew program for 386 Korean juvenile probationers from the Seoul Probation Office. Although the AVRS curfew program in Korea has been in effect for more than 14 years, effectiveness of the program has not been fully tested. A propensity score analysis was conducted to assess the effectiveness of the AVRS program, controlling for potential covariates of referring juveniles to the program. Contrary to expectations, a logistic regression analysis demonstrated that the innovative curfew program is a statistically significant factor in increasing the odds of recidivism. The article concludes with a discussion of implications for court-ordered juvenile curfew programs. [ABSTRACT FROM AUTHOR]

Community corrections agencies across the world have adopted biometric technologies as a security tool and cost-effective monitoring strategy. This study investigates the effectiveness of the automated voiceprint recognition supervision (AVRS) curfew program for 386 Korean juvenile probationers from the Seoul Probation Office. Although the AVRS curfew program in Korea has been in effect for more than 14 years, effectiveness of the program has not been fully tested. A propensity score analysis was conducted to assess the effectiveness of the AVRS program, controlling for potential covariates of referring juveniles to the program. Contrary to expectations, a logistic regression analysis demonstrated that the innovative curfew program is a statistically significant factor in increasing the odds of recidivism. The article concludes with a discussion of implications for court-ordered juvenile curfew programs. [ABSTRACT FROM AUTHOR]

Based on analysis of characteristics of biometric feature recognition technologies by palmprint, fingerprint, iris, face, gait and voiceprint and impacts of coal mine field on biometric features of in-pit coal mine personnel, it was pointed out that iris recognition, face recognition, gait recognition and voiceprint recognition were applicable to uniqueness detection of in-pit coal mine personnel. A scheme of uniqueness detection of in-pit coal mine personnel was proposed based on personnel location and biometric feature recognition, which embedded biometric feature recognition technology into personnel location system and used personnel location identification cards to achieve uniqueness detection of the card number and personnel identity. Key points of research on uniqueness detection technology of in-pit coal mine personnel were pointed out, which were recognition algorithms of seriously-stained face, acquisition algorithms of personnel gait images under the condition of equipment occlusion and elimination algorithms of noise in coal mine field mixing into personnel voice signals.

Voiceprint recognition is a kind of temperament recognition. It achieves judgment of temperament through analysis of voiceprint. The traditional judgment method usually recognizes the voiceprint directly, ignoring the influence of environmental noise, sound variation and other factors in the process of recognition. Study on the method of temperament accuracy judgment and intelligent processing based on voiceprint recognition is proposed because the traditional method is of low accuracy. The process includes, extraction of voiceprint main features, pretreatment of voiceprint for feature parameters, classification of the voiceprint according to the feature parameters, getting the temperament feature value through the Mel frequency cepstrum coefficient method, building the vector quantization model, introducing hypersphere extremum method to extract the sound signal features, applying LBG algorithm to classify the sound signal features, and achieving the aim of judging the temperament accurately. The experimental results show that the improved algorithm can effectively overcome the environmental noise, effectively reduce the impact of noise and sound variation, and improve the accuracy of temperament judgment. [ABSTRACT FROM AUTHOR]

In air traffic control (ATC), speech communication with radio transmission is the primary way to exchange information between the controller and aircrew. A wealth of contextual situational dynamics is embedded implicitly; thus, understanding the spoken instruction is particularly significant to the ATC research. In this paper, a comprehensive review related to spoken instruction understanding (SIU) in the ATC domain is provided from the perspective of the challenges, techniques, and applications. Firstly, a full pipeline is represented to achieve the SIU task, including automatic speech recognition, language understanding, and voiceprint recognition. A total of 10 technique challenges are analyzed based on the ATC task specificities. In succession, the common techniques for SIU tasks are categorized from common applications, and extensive works in the ATC domain are also reviewed. Finally, a series of future research topics are also prospected based on the corresponding challenges. The author sincerely hopes that this work is able to provide a clear technical roadmap for the SIU tasks in the ATC domain and further make contributions to the research community. [ABSTRACT FROM AUTHOR]