Automatic Speech Recognition

  • Xugang LuEmail author
  • Sheng Li
  • Masakiyo Fujimoto
Part of the SpringerBriefs in Computer Science book series (BRIEFSCOMPUTER)


The main task of automatic speech recognition (ASR) is to convert voice signals to text transcriptions. It is one of the most important research fields in natural language processing (NLP). With more than a half century of endeavor, the word error rate (WER), which is a metric unit for transcription performance, has significantly been reduced. Particularly in recent years, due to the increase of computational power, large quantity of collected data, and efficient neural learning algorithms, the dominant power of deep learning technology further enhanced the performance of ASR systems to a practical level. However, there are still many issues that need to be further investigated for these systems to be adapted to a wide range of applications. In this chapter, we will introduce the main stream and pipeline of ASR frameworks, particularly the two dominant frameworks, i.e., Hidden Markov Model (HMM) with Gaussian Mixture model (GMM)-based ASR which dominated the field in the early decades, and deep learning model-based ASR which dominates the techniques used now. In addition, noisy robustness, which is one of the most important challenges for ASR in real applications, will also be introduced.


  1. 1.
    Xiong, W., Wu, L., Alleva, F., Droppo, J., Huang, X., Stolcke, A.: The Microsoft 2016 conversational speech recognition system. Microsoft Technical Report MSR-TR-2017-39.
  2. 2.
    Dixon, P.R., Hori, C., Kashioka, H.: Development of the SprinTra WFST speech decoder. NICT Res. J., 15–20 (2012)Google Scholar
  3. 3.
    Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29, 82–97 (2012)CrossRefGoogle Scholar
  4. 4.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  5. 5.
    Cho, K., Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. In: The 8th Workshop on Syntax, Semantics and Structure in Statistical Translation, SSST-8 (2014)Google Scholar
  6. 6.
    Sainath, T.N., Vinyals, O., Senior, A., Sak, H.: Convolutional, long short-term memory, fully connected deep neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2015).
  7. 7.
    Csáji, B.C.: Approximation with artificial neural networks. Faculty of Sciences; Eötvös Loránd University, Hungary (2001)Google Scholar
  8. 8.
    Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Proceedings Advances in Neural Information Processing Systems (NIPS) (2012)Google Scholar
  9. 9.
    Srivastava, R.K., Greff, K., Schmidhuber, J.: Training very deep networks. In: Proceedings of NIPS (2015)Google Scholar
  10. 10.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)Google Scholar
  11. 11.
    Graves, A., Fernandez, S., Gomez, F., Shmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the International Conference on Machine Learning (ICML) (2006)Google Scholar
  12. 12.
    Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: Proceedings of the International Conference on Machine Learning (ICML) (2014)Google Scholar
  13. 13.
    Chorowski, J., Bahdanau, D., Cho, K., Bengio, Y.: End-to-end continuous speech recognition using attention-based recurrent NN: First results. arXiv preprint arXiv:14121602 (2014)
  14. 14.
    Miao, Y., Gowayyed, M., Metze, F.: EESEN: end-to-end speech recognition using deep RNN models and WFST-based decoding. In: Proceedings of IEEE-ASRU (2015)Google Scholar
  15. 15.
    Kanda, N., Lu, X., Kawai, H.: Maximum a posteriori based decoding for CTC acoustic models. In: Proceedings of INTERSPEECH, pp. 1868–1872 (2016)Google Scholar
  16. 16.
    Boll, S.F.: Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Audio Speech Signal Process. 27(2), 113–120 (1979)CrossRefGoogle Scholar
  17. 17.
    Ephraim, Y., Malah, D.: Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator. IEEE Trans. Audio Speech Signal Process. 32, 1109–1121 (1984)CrossRefGoogle Scholar
  18. 18.
    Lu, X., Tsao, Y., Matsuda, S, Hori, C.: Speech enhancement based on deep denoising autoencoder. In: Proceedings of Interspeech ’13, pp. 436–440, August 2013Google Scholar
  19. 19.
    Yoshioka, T., Nakatani, T.: Generalization of multi-channel linear prediction methods for blind MIMO impulse response shortening. IEEE Trans. Audio Speech Lang. Process. 20(10), 2707–2720 (2012)CrossRefGoogle Scholar
  20. 20.
    Wölfel, M., McDonough, M.: Minimum variance distortionless response spectral estimation. IEEE Signal Process. Mag. 22(5) (2005)Google Scholar
  21. 21.
    Liao, H.: Speaker adaptation of context dependent deep neural networks. In: Proceedings of ICASSP ’13, pp. 7947–7951, May 2013Google Scholar
  22. 22.
    Seltzer, M., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: Proceedings of ICASSP ’13, pp. 7398–7402, May 2013Google Scholar
  23. 23.
    Wang, Z., Wang, D.: A joint training framework for robust automatic speech recognition. IEEE/ACM Transa. Audio Speech Lang. Process. (2016)Google Scholar
  24. 24.
    Li, L., Sim, K.C.: Improving robustness of deep neural networks via spectral masking for automatic speech recognition. In: Proceedings of ASRU ’13, pp. 279–284, December 2013Google Scholar

Copyright information

© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Advanced Speech Technology Laboratory, Advanced Speech Translation Research and Development Promotion CenterNational Institute of Information and Communications TechnologyKyotoJapan

Personalised recommendations