Abstract
In speech recognition research, because of the variety of languages, corresponding speech recognition systems need to be constructed for different languages. Especially in a dialect speech recognition system, there are many special words and oral language features. In addition, dialect speech data is very scarce. Therefore, constructing a dialect speech recognition system is difficult. This paper constructs a speech recognition system for Sichuan dialect by combining a hidden Markov model (HMM) and a deep long short-term memory (LSTM) network. Using the HMM-LSTM architecture, we created a Sichuan dialect dataset and implemented a speech recognition system for this dataset. Compared with the deep neural network (DNN), the LSTM network can overcome the problem that the DNN only captures the context of a fixed number of information items. Moreover, to identify polyphone and special pronunciation vocabularies in Sichuan dialect accurately, we collect all the characters in the dataset and their common phoneme sequences to form a lexicon. Finally, this system yields a 11.34% character error rate on the Sichuan dialect evaluation dataset. As far as we know, it is the best performance for this corpus at present.
Similar content being viewed by others
References
Berndt D J, Clikord J. Using dynamic time warping to find patterns in time series. In: Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining. 1994, 359–370
Tyagi V. Maximum accept and reject (mars) training of hmm-gmm speech recognition systems. In: Proceedings of the 9th Annual Conference of the International Speech Communication Association. 2008, 956–959
Woodland P C, Odell J J, Valtchev V, Young S J. Large vocabulary continuous speech recognition using UTK. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. 1994, 125–128
Gales M J F. Maximum likelihood linear transformations for hmm-based speech recognition. Computer Speech & Language, 1998, 12(2): 75–98
Rabiner L R. A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 1989, 77(2): 257–286
Gales M, Young S. The application of hidden markov models in speech recognition. Foundations and Trends in Signal Processing, 2008, 1(3): 195–304
Jurafsky D. Speech & Language Processing. India: Pearson Education, 2000
Zhang L, Zhang Y, Amari S. Theoretical study of oscillator neurons in recurrent neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(11): 5242–5248
Zhang Y. Foundations of implementing the competitive layer model by lotka-volterra recurrent neural networks. IEEE Transactions on Neural Networks, 2010, 21(3): 494–507
Zhang L, Zhang Y. Dynamical properties of background neural networks with uniform firing rate and background input. Chaos, Solitons & Fractals, 2007, 33(3): 979–985
Wang J, Zhang L, Guo Q, Zhang Y. Recurrent neural networks with auxiliary memory units. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(5): 1652–1661
Guo Q, Jia J, Shen G Y, Zhang L, Cai L H, Zhang Y. Learning robust uniform features for cross-media social data by using cross autoen-coders. Knowledge-Based Systems, 2016, 102: 64–75
Wang L, Zhang L, Zhang Y. Trajectory predictor by using recurrent neural networks in visual tracking. IEEE Transactions on Cybernetics, 2017, 47(10): 3172–3183
Hinton G, Deng L, Yu D, Dahl G H, Mohamed A, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath T N, Kingsbury B. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Processing Magazine, 2012, 29(6): 82–97
Mohamed S, Dahl G E, Hinton G. Acoustic modeling using deep belief networks. IEEE Transactions on Audio, Speech, and Language Processing, 2012, 20(1): 14–22
Huang Y, Slaney M, Seltzer M L, Gong Y F. Towards better performance with heterogeneous training data in acoustic modeling using deep neural networks. In: Proceedings of the 15th Annual Conference of the International Speech Communication Association. 2014, 845–849
Manohar V, Povey D, Khudanpur S. Semi-supervised maximum mutual information training of deep neural network acoustic models. In: Proceedings of the 6th Annual Conference of the International Speech Communication Association. 2015, 2630–2634
Prabhavalkar R, Rao K, Sainath T, Li B, Johnson L, Jaitly N. A comparison of sequence-to-sequence models for speech recognition. In: Proceedings of the 8th Annual Conference of the International Speech Communication Association. 2017, 939–943
Amodei D, Ananthanarayanan S, Anubhai R, Bai J L, Battenberg E, Case C, Casper J, Catanzaro B, Cheng Q, Chen G L, et al. Deep speech 2: end-to-end speech recognition in english and mandarin. In: Proceedings of the 33rd International Conference on Machine Learning. 2016, 173–182
Xiong W, Wu L, Alleva F, Droppo J, Huang X, Stolcke A. The microsoft 2017 conversational speech recognition system. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing. 2018, 5934–5938
Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997, 9(8): 1735–1780
Bilmes J A. A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models. International Computer Science Institute, 1998, 4(510): 126–406
Hori T, Nakamura A. Speech recognition algorithms using weighted finite-state transducers. Synthesis Lectures on Speech and Audio Processing, 2013, 9(1): 1–162
Forney G D. The viterbi algorithm. Proceedings of the IEEE, 1973, 61(3): 268–278
Graves A. Supervised Sequence Labelling with Recurrent Neural Networks. Berlin: Springer, 2012
Graves A, Liwicki M, Fernández S, Bertolami R, Bunke H, Schmidhuber J. A novel connectionist system for unconstrained handwriting recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(5): 855–868
Brown P F, Desouza P V, Mercer R L, Pietra V J D, Lai J C. Class-based n-gram models of natural language. Computational Linguistics, 1992, 18(4): 467–479
Senior A, Sak H, Shafran I. Context dependent phone models for LSTM RNN acoustic modelling. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing. 2015, 4585–4589
Povey D, Ghoshal A, Boulianne G, Burget L, Glembek O, Goel N, Hannemann M, Motlicek P, Qian Y, Schwarz P, Silovsky J, Stemmer G, Vesely K. The Kaldi speech recognition toolkit. In: Proceedings of IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. 2011
Logan B. Mel frequency cepstral coeffcients for music modeling. In: Proceedings of International Conference on Music Information Retrieval. 2000, 1–11
Williams R J, Zipser D. Gradient-based learning algorithms for recurrent networks and their computational complexity. Backpropagation: Theory, Architectures, and Applications, 1995, 433–486
Bottou L, Curtis F E, Nocedal J. Optimization methods for large-scale machine learning. Society for Industrial and Applied Mathematics, 2018, 60(2): 223–311
Acknowledgments
This work was supported by the National Key R&D Program of China (2016YFC0801800); General Program of the National Natural Science Foundation of China (Grant No. 61772353); the Key Program of the National Natural Science Foundation of China (Grant No. 61332002); and Fok Ying Tung Education Foundation (151068).
Author information
Authors and Affiliations
Corresponding author
Additional information
Wangyang Ying received his BS degree in computer science from Sichuan University, China in 2016. Currently, he is working toward a MS degree at the Machine Intelligence Laboratory, College of Computer Science, Sichuan University, China. His current research interests include neural network, deep learning, and speech recognition.
Lei Zhang received the BS and MS degrees in mathematics and the PhD degree in computer science from the University of Electronic Science and Technology of China, China in 2002, 2005, and 2008, respectively. She was a post-doctoral research fellow with the Department of Computer Science and Engineering, Chinese University of Hong Kong, China from 2008 to 2009. She is currently a professor with Sichuan University, China. Her current research interests include theory and applications of neural networks based on neocortex computing and big data analysis methods by infinity deep neural networks.
Hongli Deng received her MS degree in University of Science and Technology of China, China in 2008. Currently, she is working toward a PhD degree at the Machine Intelligence Laboratory, College of Computer Science, Sichuan University, China. Her current research interests include neural network, deep learning, and natural language processing.
Electronic supplementary material
Rights and permissions
About this article
Cite this article
Ying, W., Zhang, L. & Deng, H. Sichuan dialect speech recognition with deep LSTM network. Front. Comput. Sci. 14, 378–387 (2020). https://doi.org/10.1007/s11704-018-8030-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11704-018-8030-z