End-to-end Speech Recognition Based on BGRU-CTC
Authors: 
Yu Yan, Xizhong ShenAuthors Info & Claims
Yu Yan, Xizhong ShenAuthors Info & ClaimsPages 48 - 52
Abstract
In recent years, the end-to-end speech recognition model has gradually become the development trend of large-scale continuous speech recognition because of its simplicity and easy training characteristics. In this paper, we use the good performance of bidirectional gated recurrent unit (BGRU), a variant of long short term memory (LSTM), in the field of speech recognition. At the same time, we use connectionist temporal classification (CTC) algorithm to train the model, build an end-to-end speech recognition system, and carry out speech recognition experiments on TIMIT. The results show that, compared with the traditional recognition model, the accuracy of the improved end-to-end model is improved by about 2.4%.
References
[1]
Billa, J. (2017). Improving LSTM-CTC based ASR performance in domains with limited training data. arXiv preprint arXiv:1707.00722.
[2]
Dey, R., & Salem, F. M. (2017). Gate-variants of gated recurrent unit (GRU) neural networks. Paper presented at the 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS).
[3]
Do, C.-T., Zhang, S., & Hain, T. (2021). Selective adaptation of end-to-end speech recognition using hybrid CTC/attention architecture for noise robustness. Paper presented at the 2020 28th European Signal Processing Conference (EUSIPCO).
[4]
Graves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006). Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. Paper presented at the Proceedings of the 23rd international conference on Machine learning.
[5]
Graves, A., & Jaitly, N. (2014). Towards end-to-end speech recognition with recurrent neural networks. Paper presented at the International conference on machine learning.
[6]
Hinton, G., Deng, L., Yu, D., Dahl, G. E., Mohamed, A.-r., Jaitly, N., . . . Sainath, T. N. (2012). Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal processing magazine, 29(6), 82-97.
[7]
Kahn, J., Lee, A., & Hannun, A. (2020). Self-training for end-to-end speech recognition. Paper presented at the ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[8]
Kim, S., Hori, T., & Watanabe, S. (2017). Joint CTC-attention based end-to-end speech recognition using multi-task learning. Paper presented at the 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP).
[9]
Mohamed, A.-r., Hinton, G., & Penn, G. (2012). Understanding how deep belief networks perform acoustic modelling. Paper presented at the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[10]
Rodríguez, E., Ruíz, B., García-Crespo, Á., & García, F. (1997). Speech/speaker recognition using a HMM/GMM hybrid model. Paper presented at the International Conference on Audio-and Video-Based Biometric Person Authentication.
[11]
Wang, D., Wang, X., & Lv, S. (2019). End-to-end mandarin speech recognition combining CNN and BLSTM. Symmetry, 11(5), 644.
[12]
Yu, D., & Deng, L. (2010). Deep learning and its applications to signal and information processing [exploratory dsp]. IEEE Signal processing magazine, 28(1), 145-154.
[13]
Zeyer, A., Doetsch, P., Voigtlaender, P., Schlüter, R., & Ney, H. (2017). A comprehensive study of deep bidirectional LSTM RNNs for acoustic modeling in speech recognition. Paper presented at the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[14]
Zhang, Y., Pezeshki, M., Brakel, P., Zhang, S., Bengio, C. L. Y., & Courville, A. (2017). Towards end-to-end speech recognition with deep convolutional neural networks. arXiv preprint arXiv:1701.02720.
Recommendations
Robust AAM-based audio-visual speech recognition against face direction changes
MM '12: Proceedings of the 20th ACM international conference on MultimediaAs one of the techniques for robust speech recognition under noisy environments, audio-visual speech recognition (AVSR) using lip dynamic scene information together with audio information is attracting attention, and the research has advanced in recent ...
Speech-Input Speech-Output Communication for Dysarthric Speakers Using HMM-Based Speech Recognition and Adaptive Synthesis System
Dysarthria is a motor speech disorder that causes inability to control and coordinate one or more articulators. This makes it difficult for a dysarthric speaker to utter certain speech sound units, thereby producing poorly articulated, slurred, and ...
Regularized minimum variance distortionless response-based cepstral features for robust continuous speech recognition
We study the low-variance and robust features for speech recognition system on the AURORA-4 corpus.We propose to compute cepstral features from a regularized MVDR (RMVDR) spectral estimates, denoted as RMVDR-based Cepstral Coefficient (RMCC) features.A ...
Comments
Information & Contributors
Information
Published In
October 2021
81 pages
ISBN:9781450385725
DOI:10.1145/3502814
Copyright © 2021 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 11 April 2022
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
SSIP 2021
SSIP 2021: 2021 4th International Conference on Sensors, Signal and Image Processing
October 15 - 17, 2021
Nanjing, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 31Total Downloads
- Downloads (Last 12 months)5
- Downloads (Last 6 weeks)0
Reflects downloads up to 08 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format