Abstract
Recurrent Neural Network (RNN) is now widely used in speech recognition. Experiments show that it has significant advantages over traditional methods, but complex computation limits its application, especially in real-time application scenarios. Recurrent neural network is heavily dependent on the pre- and post-state in calculation process, and there is much overlap information, so overlapping information can be reduced to accelerate training. This paper construct a training acceleration structure, which reduces the computation cost and accelerates training speed by discarding the dependence of pre- and post- state of RNN. Then correcting the recognition results errors with text corrector. We verify the proposed method on the TIMIT and Librispeech datasets, which prove that this approach achieves about 3 times speedup with little relative accuracy reduction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). Book in Preparation
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Yao, K., Cohn, T., Vylomova, K., Duh, K., Dyer, C.: Depth-gated recurrent neural networks. arXiv preprint arXiv: 1508.03790v2 (2015)
Jozefowicz, R., Zaremba, W., Sutskever, I.: An empirical exploration of recurrent network architectures. In: International Conference, pp. 2342–2350 (2015)
Chung, J., Gulcehre, C., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv: 1412.35556 (2014)
Vaswani, A., Shazeer, N., Parmar, N., Polosukhin, I.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)
Wu, Y., Schuster, M., Chen, Z.: Google’s neural machine translation system: bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)
Sak, H., Senior, A., Françoise, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: INTERSPEECH (2014)
Frank, S., Li, G., Yu, D.: Conversational speech transcription using context-dependent deep neural networks. In: 12th Annual Conference of the International Speech Communication Association (Interspeech 2011), pp. 437–440, Florence, Italy (2011)
Michael, S., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, Canada, pp. 7398–7402 (2013)
Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: International Conference on Machine Learning, pp. 1764–1772 (2014)
Lei, T., Zhang, Y., Artzi, Y.: Training RNNs as fast as CNNs. arXiv preprint arXiv:1709.02755 (2017)
Graves, A., Gomez, F.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: International Conference on Machine Learning, pp. 369–376 (2016)
Zhang, Y., He, P.L., Xiang, W., Li, M.: A discriminative reranking approach to spelling correction. J. Softw. 19(3), 557–564 (2008)
Toutanova, K., Moore, R.C.: Pronunciation modeling for improved spelling correction. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, pp. 144–151 (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bai, L., Jiang, J., Dou, Y. (2018). Research on Acceleration Method of Speech Recognition Training. In: Li, C., Wu, J. (eds) Advanced Computer Architecture. ACA 2018. Communications in Computer and Information Science, vol 908. Springer, Singapore. https://doi.org/10.1007/978-981-13-2423-9_4
Download citation
DOI: https://doi.org/10.1007/978-981-13-2423-9_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2422-2
Online ISBN: 978-981-13-2423-9
eBook Packages: Computer ScienceComputer Science (R0)