Neural Architecture Search for LF-MMI Trained Time Delay Neural Networks

Hu, Shoukang; Xie, Xurong; Liu, Shansong; Cui, Mingyu; Liu, Xunying; Meng, Helen

doi:10.1109/taslp.2022.3153253

Cited by 15 publications

(3 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hu et al [86] applied neural architecture search (NAS) to automatically learn the two hyper-parameters of factored time-delay neural networks (TDNN-Fs), namely the left and right splicing context offsets and the dimensionality of the bottleneck linear projection at each hidden layer. These techniques included the differentiable neural architecture search (DARTS) to integrate architecture learning with lattice-free MMI training; Gumbel-Softmax and Pipelined DARTS to reduce the confusion over candidate architectures and improve the generalization of architecture selection; and penalized DARTS to incorporate resource constraints to balance the trade-off between system performance and complexity.…”

Section: Acoustic Model Of Asr For Dysarthric Speechmentioning

confidence: 99%

A Survey of Automatic Speech Recognition for Dysarthric Speech

Qian,

Xiao

2023

Electronics

View full text Add to dashboard Cite

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.

show abstract

Section: Acoustic Model Of Asr For Dysarthric Speechmentioning

confidence: 99%

A Survey of Automatic Speech Recognition for Dysarthric Speech

Qian,

Xiao

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Hu, et al [100] applied neural architecture search (NAS) to automatically learn the two hyper-parameters of factored time delay neural networks (TDNN-Fs), namely the left and right splicing context offsets and the dimensionality of the bottleneck linear projection at each hidden layer. They utilized differentiable neural architecture search (DARTS) to integrate architecture learning with lattice-free maximum mutual information (LF-MMI) training, Gumbel-Softmax and Pipelined DARTS to reduce confusion over candidate architectures and improve generalization of architecture selection, and penalized DARTS to incorporate resource constraints to balance the trade-off between system performance and complexity.…”

Section: Deep Learning Technologies Of Asr For Dysarthric Speechmentioning

confidence: 99%

A survey of technologies for automatic Dysarthric speech recognition

Qian,

Xiao,

2023

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

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.

show abstract

“…the NAS was used to automatically learn two hyperparameters of factorized TDNN, namely left-right splicing and contextual offset, and the linear projection dimension of each hidden layer, allowing TDNN to perform in different systems through parameter sharing effective search. Experimental results show that its word error rate is large and model size is greatly reduced, and speech recognition performance is improved [9]. [1] used TDNN to predict the active power demand on a P4 bus in President Prudente.…”

Section: Introductionmentioning

confidence: 99%

A Study of Blockchain and Machine Learning-Enabled IoT Security in Time-Delayed Neural Network Vocal Pattern Recognition to Improve Web-Based Vocal Teaching

Long

2024

SCPE

View full text Add to dashboard Cite

With the development of information technology, online vocal teaching is becoming more and more popular, but the sound quality of teaching is also becoming more and more demanding. As online vocal instruction becomes more popular, the need for high-quality sound in these digital environments becomes more critical. This research tackles the problem of improving sound quality in real-time vocal teaching by integrating advanced technologies such as Blockchain and Machine Learning within the Internet of Things (IoT) security framework. We created a vocal recognition model using Time-Delay Neural Network (TDNN) and improved it with Generated Feature Vector (GFV). This integration yields a strong GTDNN vocal recognition system that is specifically designed to secure and optimize web-based vocal teaching. Our experiments show that GTDNN outperforms traditional TDNN and i-vector methods in feature vector extraction, adapting well to different speech environments. In various speech settings, GTDNN's Error Rates (EERs) are impressively low at 11.3%, 12.0%, 4.9%, 6.2%, and 6.1%, indicating superior performance over comparison models. GTDNN has an EER of 9.6% for short-duration speech and 2.3% for long-duration speech. Furthermore, the GTDNN system achieves an overall pass rate of 94% for target speech and an impressive rejection rate for non-target speech, ensuring high accuracy in a variety of speech environments.

show abstract

Neural Architecture Search for LF-MMI Trained Time Delay Neural Networks

Cited by 15 publications

References 67 publications

A Survey of Automatic Speech Recognition for Dysarthric Speech

A Survey of Automatic Speech Recognition for Dysarthric Speech

A survey of technologies for automatic Dysarthric speech recognition

A Study of Blockchain and Machine Learning-Enabled IoT Security in Time-Delayed Neural Network Vocal Pattern Recognition to Improve Web-Based Vocal Teaching

Contact Info

Product

Resources

About