Download pdf
Comparative analysis between application of transformer and recurrent neural network in speech recognition
- 1 University of Nottingham, Ningbo, China, 315100
* Author to whom correspondence should be addressed.
Abstract
Transformer is a deep learning model applying self-attention mechanism which is widely used in solving sequence-to-sequence questions, including speech recognition. After Transformer was proposed, it has been greatly developed and made great progress in the field of speech recognition. Recurrent Neural Network (RNN) is also a model that can be used in speech recognition. Speech recognition is a kind of sequence-to-sequence question that can transform human speech into text form. Both RNN and Transformer use encoder-decoder architecture to solve sequence-to-sequence questions. However, RNN is a recurrent model, weak in parallel training, and it will not perform quite well as Transformer in sequence-to-sequence question, which is a non-recurrent model. This paper mainly analyzes the accuracy Transformer and RNN in automatic speech recognition. It shows that Transformer performs better than RNN in speech recognition area, having higher accuracy, and it therefore provides evidence that Transformer can be an efficacious approach to automatic speech recognition as well as a practical substitution for traditional ways like RNN.
Keywords
Transformer, Recurrent Neural Network, Comparative Analysis.
[1]. Vaswani A. et al. (2017) Attention is all you need, Advances in Neural Information Processing Systems, 30, pp. 5998–6008.
[2]. Zhang L. et al. (2020) Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation, IEEE transactions on medical imaging, 39(7), pp. 2531–2540.
[3]. Yan R. (2018). Chitty-Chitty-Chat Bot, Deep Learning for Conversational AI. In IJCAI, 18, pp. 5520-5526.
[4]. Karita S., et al. (2019) A Comparative Study on Transformer vs RNN in Speech Applications, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 449- 456.
[5]. Vathsala M.K. and Holi G. (2020) RNN based machine translation and transliteration for Twitter data, International journal of speech technology, 23(3), pp. 499–504.
[6]. Sun L. et al. (2017) GMU: A Novel RNN Neuron and Its Application to Handwriting Recognition, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 1, pp. 1062–1067.
[7]. Dong L., Xu S. and Xu B. (2018) Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018, pp. 5884–5888.
[8]. Zeyer A. et al. (2018) Improved training of end-to-end attention models for speech recognition, arXiv preprint, arXiv:1805.03294.
[9]. Chen N. et al. (2021) Non-Autoregressive Transformer for Speech Recognition, IEEE signal processing letters, 28, pp. 121–125.
[10]. Bu H. et al. (2017) AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline, 2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (OCOCOSDA), pp. 1–5.
[11]. Maekawa K. et al. (2000) Spontaneous Speech Corpus of Japanese, LREC, 6, pp. 1-5.
[12]. Panayotov V. et al. (2015) Librispeech: An ASR corpus based on public domain audio books, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206–5210
[13]. Bahdanau D., Cho K. and Bengio Y. (2014) Neural Machine Translation by Jointly Learning to Align and Translate, arXiv preprint, arXiv:1409.0473.
[14]. Hori T., Cho J. and Watanabe S. (2018) End-to-end Speech Recognition with Word-based RNN Language Models, 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 389-396.
[15]. Zeiler M.D. (2012) ADADELTA: An Adaptive Learning Rate Method, arXiv preprint, arXiv:1212.5701.
Cite this article
Liao,Z. (2023). Comparative analysis between application of transformer and recurrent neural network in speech recognition. Applied and Computational Engineering,6,524-529.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 3rd International Conference on Signal Processing and Machine Learning
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).