Skip to main content

Advertisement

Springer Nature Link
Log in

Performance analysis of ASR system in hybrid DNN-HMM framework using a PWL euclidean activation function

  • Research Article
  • Published:
Frontiers of Computer Science Aims and scope Submit manuscript

Abstract

Automatic Speech Recognition (ASR) is the process of mapping an acoustic speech signal into a human readable text format. Traditional systems exploit the Acoustic Component of ASR using the Gaussian Mixture Model — Hidden Markov Model (GMM-HMM) approach. Deep Neural Network (DNN) opens up new possibilities to overcome the shortcomings of conventional statistical algorithms. Recent studies modeled the acoustic component of ASR system using DNN in the so called hybrid DNN-HMM approach. In the context of activation functions used to model the non-linearity in DNN, Rectified Linear Units (ReLU) and maxout units are mostly used in ASR systems. This paper concentrates on the acoustic component of a hybrid DNN-HMM system by proposing an efficient activation function for the DNN network. Inspired by previous works, euclidean norm activation function is proposed to model the non-linearity of the DNN network. Such non-linearity is shown to belong to the family of Piecewise Linear (PWL) functions having distinct features. These functions can capture deep hierarchical features of the pattern. The relevance of the proposal is examined in depth both theoretically and experimentally. The performance of the developed ASR system is evaluated in terms of Phone Error Rate (PER) using TIMIT database. Experimental results achieve a relative increase in performance by using the proposed function over conventional activation functions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Baker J M, Deng L, Glass J, Khudanpur S, Lee C H, Morgan N, O’Shaughnessy D. Developments and directions in speech recognition and understanding, Part 1 [DSP Education]. IEEE Signal Processing Magazine, 2009, 26(3): 75–80

    Article  Google Scholar 

  2. Lawrence R. Fundamentals of Speech Recognition. India: Pearson Education, 2008

    Google Scholar 

  3. Young S. A review of large vocabulary continuous speech. IEEE Signal Processing Magazine, 1996, 13(5): 45

    Article  Google Scholar 

  4. Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786): 504–507

    Article  MathSciNet  Google Scholar 

  5. McDermott E, Hazen T J, Le Roux J, Nakamura A, Katagiri S. Discriminative training for large vocabulary speech recognition using minimum classification error. IEEE Transactions on Audio, Speech and Language Processing, 2006, 15(1): 203–223

    Article  Google Scholar 

  6. Saon G, Chien J T. Large vocabulary continuous speech recognition systems: a look at some recent advances. IEEE Signal Processing Magazine, 2012, 29(6): 18–33

    Article  Google Scholar 

  7. Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527–1554

    Article  MathSciNet  Google Scholar 

  8. He K, Zhang X, Ren S, Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904–1916

    Article  Google Scholar 

  9. Chen K, Ding G, Han J. Attribute based supervised deep learning model for action recognition. Frontiers of Computer Science, 2017, 11(2): 219–229

    Article  Google Scholar 

  10. Graves A, Jaitly N. Towards end to end speech recognition with recurrent neural networks. In: Proceedings of International Conference on Machine Learning. 2014, 1764–1772

  11. Ying W, Zhang L, Deng H. Sichuan dialect speech recognition with deep LSTM network. Frontiers of Computer Science, 2020, 14(2): 378–387

    Article  Google Scholar 

  12. Yan Y, Chen Z, Liu Z. Semi-tensor product of matrices approach to reachability of finite automata with application to language recognition. Frontiers of Computer Science, 2014, 8(6): 948–957

    Article  MathSciNet  Google Scholar 

  13. Young T, Hazarika D, Poria S, Cambria E. Recent trends in deep learning based natural language processing. IEEE Computational Intelligence Magazine, 2018, 13(3): 55–75

    Article  Google Scholar 

  14. Dahl G E, Yu D, Deng L, Acero A. Context dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Transactions on Audio, Speech and Language Processing, 2011, 20(1): 30–42

    Article  Google Scholar 

  15. Zhang Q, Zhang L. Convolutional adaptive denoising autoencoders for hierarchical feature extraction. Frontiers of Computer Science, 2018, 12(6): 1140–1148

    Article  Google Scholar 

  16. Rong W, Peng B, Ouyang Y, Li C, Xiong Z. Structural information aware deep semi-supervised recurrent neural network for sentiment analysis. Frontiers of Computer Science, 2015, 9(2): 171–184

    Article  MathSciNet  Google Scholar 

  17. Peddinti V, Povey D, Khudanpur S. A time delay neural network architecture for efficient modeling of long temporal contexts. In: Proceedings of the 16th Annual Conference of the International Speech Communication Association. 2015

  18. Chan W, Jaitly N, Le Q, Vinyals O. Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: Proceedings of 2016 IEEE International Conference on Acoustics, Speech and Signal Processing. 2016, 4960–4964

  19. Bellegarda J R, Monz C. State of the art in statistical methods for language and speech processing. Computer Speech & Language, 2016, 35: 163–184

    Article  Google Scholar 

  20. Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. 2010, 249–256

  21. Zhao W, San Y. RBF neural network based on q Gaussian function in function approximation. Frontiers of Computer Science in China, 2011, 5(4): 381–386

    Article  MathSciNet  Google Scholar 

  22. Wan L, Zeiler M, Zhang S, LeCun Y, Fergus R. Regularization of neural networks using dropconnect. In: Proceedings of International Conference on Machine Learning. 2013, 1058–1066

  23. Hsu W N, Zhang Y, Glass J. Unsupervised domain adaptation for robust speech recognition via variational autoencoder based data augmentation. In: Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop. 2017, 16–23

  24. Nair V, Hinton G E. Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning. 2010, 807–814

  25. Agostinelli F, Hoffman M, Sadowski P, Baldi P. Learning activation functions to improve deep neural networks. 2014, arXiv preprint arXiv:1412.6830

  26. Springenberg J T, Riedmiller M. Improving deep neural networks with probabilistic maxout units. 2013, arXiv preprint arXiv:1312.6116

  27. Le Q V, Jaitly N, Hinton G E. A simple way to initialize recurrent networks of rectified linear units. 2015, arXiv preprint arXiv:1504.00941

  28. Graves A, Jaitly N, Mohamed A R. Hybrid speech recognition with deep bidirectional LSTM. In: Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding. 2013, 273–278

  29. Chen J, Zhang Q, Liu P, Qiu X, Huang X J. Implicit discourse relation detection via a deep architecture with gated relevance network. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2016, 1726–1735

  30. Glorot X, Bordes A, Bengio Y. Deep sparse rectifier neural networks. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. 2011, 315–323

  31. Goodfellow I J, Warde-Farley D, Mirza M, Courville A, Bengio Y. Maxout networks. In: Proceedings of International Conference on Machine Learning. 2013, 1319–1327

  32. Maas A L, Hannun A Y, Ng A Y. Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of International Conference on Machine Learning. 2013

  33. Dahl G E, Sainath T N, Hinton G E. Improving deep neural networks for LVCSR using rectified linear units and dropout. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. 2013, 8609–8613

  34. Zhang X, Trmal J, Povey D, Khudanpur S. Improving deep neural network acoustic models using generalized maxout networks. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. 2014, 215–219

  35. Cai M, Liu J. Maxout neurons for deep convolutional and LSTM neural networks in speech recognition. Speech Communication, 2016, 77: 53–64

    Article  Google Scholar 

  36. Aggarwal C C, Hinneburg A, Keim D A. On the surprising behavior of distance metrics in high dimensional space. In: Proceedings of International Conference on Database Theory. 2001, 420–434

  37. Hinton G, Deng L, Yu D, Dahl G E, Mohamed A R, 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

    Article  Google Scholar 

  38. Gales M, Young S. The application of hidden Markov models in speech recognition. Foundations and Trends in Signal Processing, 2008, 1(3): 195–304

    Article  Google Scholar 

  39. Montufar G, Pascanu R, Cho K, Bengio Y. On the number of linear regions of deep neural networks. In: Proceedings of the 27th International Conference on Neural Information Processing Systems. 2014, 2924–2932

  40. Pascanu R, Montufar G, Bengio Y. On the number of response regions of deep feed forward networks with piece wise linear activations. 2013, arXiv preprint arXiv:1312.6098

  41. Srivastava R K, Masci J, Gomez F, Schmidhuber J. Understanding locally competitive networks. 2014, arXiv preprint arXiv:1410.1165

  42. Arora R, Basu A, Mianjy P, Mukherjee A. Understanding deep neural networks with rectified linear units. In: Proceedings of International Conference on Learning Pepresentation. 2018

  43. Stallings J. The piecewise linear structure of euclidean space. In: Proceedings of the Cambridge Philosophical Society. 1962, 481–488

  44. Amin H, Curtis K M, Hayes-Gill B R. Piecewise linear approximation applied to nonlinear function of a neural network. IEE Proceedings-Circuits, Devices and Systems, 1997, 144(6): 313–317

    Article  Google Scholar 

  45. Serra T, Tjandraatmadja C, Ramalingam S. Bounding and counting linear regions of deep neural networks. In: Proceedings of International Conference on Machine Learning. 2018, 4558–4566

  46. Beyer K, Goldstein J, Ramakrishnan R, Shaft U. When is “nearest neighbor” meaningful? In: Proceedings of International Conference on Database Theory. 1999, 217–235

  47. Gold B, Morgan N, Ellis D. Speech and Audio Signal Processing: Processing and Perception of Speech and Music. John Wiley & Sons, 2011

  48. Rath S P, Povey D, Vesely K, Cernocky J. Improved feature processing for deep neural networks. In: Proceedings of the 14th Annual Conference of the International Speech Communication Association. 2013, 109–113

  49. Povey D, Zhang X, Khudanpur S. Parallel training of DNNs with natural gradient and parameter averaging. 2014, arXiv preprint arXiv:1410.7455

  50. Garofolo J S, Lamel L F, Fisher W M, Fiscus J G, Pallett D S. DARPA TIMIT acoustic phonetic continous speech corpus CD ROM. NIST Speech Disc 1–1.1. NASA STI/Recon Technical Report n, 1993

  51. Hifny Y, Renals S. Speech recognition using augmented conditional random fields. IEEE Transactions on Audio, Speech and Language Processing, 2009, 17(2): 354–365

    Article  Google Scholar 

  52. Povey D, Ghoshal A, Boulianne G, Burget L, Glembek O, Goel N, Hannemann M, Motlicek P, Qian Y, Schwarz P, Silovsky J. The Kaldi speech recognition toolkit. In: Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding. 2011

  53. Goodfellow I, Bengio Y, Courville A. Deep Learning. MIT Press, 2016

  54. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436–444

    Article  Google Scholar 

  55. Huang P S, Avron H, Sainath T N, Sindhwani V, Ramabhadran B. Kernel methods match deep neural networks on timit. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, 2014, 205–209

Download references

Acknowledgements

This work was an outcome of the R&D work undertaken project under the Visvesvaraya PhD Scheme of Ministry of Electronics & Information Technology, Government of India, being implemented by Digital India Corporation. We are thankful to Electronics and Communication Engineering Department, National Institute of Technology Meghalaya for giving us the opportunity to use the necessary equipments required to conduct the research.

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, National Institute of Technology Meghalaya, Shillong, 793003, India

    Anirban Dutta, Gudmalwar Ashishkumar & Ch V. Rama Rao

Authors
  1. Anirban Dutta
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Gudmalwar Ashishkumar
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Ch V. Rama Rao
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Anirban Dutta.

Additional information

Anirban Dutta is currently a PhD scholar in the Department of Electronics and Communication Engineering, National Institute of Technology Meghalaya, India. During his PhD tenure he has made significant contribution in speech processing, neural networks and its applications. His domain of research includes automatic speech recognition, pattern recognition and deep neural networks.

Gudmalwar Ashishkumar received the BTech degree in Electronics and Communication Engineering from SRTMU, India in 2015, and MTech degree in VLSI design from the National Institute of Technology Meghalaya, India in 2017, where he is currently pursuing PhD degree with the Department of Electronics and communication Engineering. His research interests include speech processing, speech emotion recognition and signal processing.

Ch V Rama Rao received the PhD degree from JNTU Hyderabad, India. He is currently an assistant professor in the Department of Electronics and Communication Engineering at National Institute of Technology Meghalaya, India. During his PhD, he has made significant contributions in the field of speech enhancement. His research interest include speech technology, pattern recognition, statistical signal processing, signal processing issues in advanced communication systems and design and development of advanced wireless communication systems.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dutta, A., Ashishkumar, G. & Rao, C.V.R. Performance analysis of ASR system in hybrid DNN-HMM framework using a PWL euclidean activation function. Front. Comput. Sci. 15, 154705 (2021). https://doi.org/10.1007/s11704-020-9419-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11704-020-9419-z

Keywords