Advertisement

An Experimental Study on Fundamental Frequency Detection in Reverberated Speech with Pre-trained Recurrent Neural Networks

  • Andrei Alfaro-Picado
  • Stacy Solís-Cerdas
  • Marvin Coto-JiménezEmail author
Conference paper
  • 22 Downloads
Part of the Communications in Computer and Information Science book series (CCIS, volume 1087)

Abstract

The detection of the fundamental frequency (\(f_{0}\)) in speech signals is relevant in areas such as automatic speech recognition and identification, with multiple potential applications. For example, in virtual assistants, assistive technology devices and biomedical applications. It has been acknowledged that the extraction of this parameter is affected in adverse conditions, for example, when reverberation or background noise is present. In this paper, we present a new method to improve the detection of the \(f_{0}\) in speech signals with reverberation, based on initialized Long Short-term Memory (LSTM) neural networks. In previous works, LSTM has used weights initialized with random numbers. We propose an initialization in the form of an auto-associative memory, which learns the identity function from non-reverberated data. The advantages of our proposal are shown using different objective quality measures, in particular, in the detection of segments with and without \(f_{0}\).

Keywords

Deep learning Fundamental frequency LSTM Reverberation 

Notes

Acknowledgments

This work was supported by the University of Costa Rica (UCR), Project No. 322-B9-105.

References

  1. 1.
    Abdel-Hamid, O., Mohamed, A.R., Jiang, H., Penn, G.: Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4277–4280. IEEE (2012)Google Scholar
  2. 2.
    Baek, J., Cho, S.: Bankruptcy prediction for credit risk using an auto-associative neural network in Korean firms. In: 2003 Proceedings of the IEEE International Conference on Computational Intelligence for Financial Engineering, 2003. pp. 25–29. IEEE (2003)Google Scholar
  3. 3.
    Bagchi, D., Mandel, M.I., Wang, Z., He, Y., Plummer, A., Fosler-Lussier, E.: Combining spectral feature mapping and multi-channel model-based source separation for noise-robust automatic speech recognition. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 496–503. IEEE (2015)Google Scholar
  4. 4.
    Bengio, Y., Frasconi, P., Simard, P.: The problem of learning long-term dependencies in recurrent networks. In: IEEE International Conference on Neural Networks, pp. 1183–1188. IEEE (1993)Google Scholar
  5. 5.
    Coto-Jiménez, M.: Pre-training long short-term memory neural networks for efficient regression in artificial speech postfiltering. In: 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI), pp. 1–7. IEEE (2018)Google Scholar
  6. 6.
    Coto-Jiménez, M.: Improving post-filtering of artificial speech using pre-trained lstm neural networks. Biomimetics 4(2), 39 (2019)CrossRefGoogle Scholar
  7. 7.
    Coto-Jiménez, M., Goddard-Close, J.: LSTM deep neural networks postfiltering for enhancing synthetic voices. Int. J. Pattern Recogn. Artif. Intell. 32(01), 1860008 (2018)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Coto-Jiménez, M., Goddard-Close, J., Martínez-Licona, F.: Improving automatic speech recognition containing additive noise using deep denoising autoencoders of LSTM networks. In: Ronzhin, A., Potapova, R., Németh, G. (eds.) SPECOM 2016. LNCS (LNAI), vol. 9811, pp. 354–361. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-43958-7_42CrossRefGoogle Scholar
  9. 9.
    Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30–42 (2011)CrossRefGoogle Scholar
  10. 10.
    Du, J., Wang, Q., Gao, T., Xu, Y., Dai, L.R., Lee, C.H.: Robust speech recognition with speech enhanced deep neural networks. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)Google Scholar
  11. 11.
    Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11(Feb), 625–660 (2010)MathSciNetzbMATHGoogle Scholar
  12. 12.
    Erro, D., Sainz, I., Navas, E., Hernáez, I.: Improved HNM-based vocoder for statistical synthesizers. In: Twelfth Annual Conference of the International Speech Communication Association (2011)Google Scholar
  13. 13.
    Erro, D., Sainz, I., Saratxaga, I., Navas, E., Hernáez, I.: MFCC+ F0 extraction and waveform reconstruction using HNM: preliminary results in an hmm-based synthesizer. In: Proceeding of the FALA, pp. 29–32 (2010)Google Scholar
  14. 14.
    Fan, Y., Qian, Y., Xie, F.L., Soong, F.K.: TTS synthesis with bidirectional LSTM based recurrent neural networks. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)Google Scholar
  15. 15.
    Feng, X., Zhang, Y., Glass, J.: Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1759–1763. IEEE (2014)Google Scholar
  16. 16.
    Gers, F.A., Schraudolph, N.N., Schmidhuber, J.: Learning precise timing with LSTM recurrent networks. J. Mach. Learn. Res. 3(Aug), 115–143 (2002)MathSciNetzbMATHGoogle Scholar
  17. 17.
    Graves, A., Fernández, S., Schmidhuber, J.: Bidirectional LSTM networks for improved phoneme classification and recognition. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 799–804. Springer, Heidelberg (2005).  https://doi.org/10.1007/11550907_126CrossRefGoogle Scholar
  18. 18.
    Graves, A., Jaitly, N., Mohamed, A.R.: Hybrid speech recognition with deep bidirectional LSTM. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 273–278. IEEE (2013)Google Scholar
  19. 19.
    Han, K., He, Y., Bagchi, D., Fosler-Lussier, E., Wang, D.: Deep neural network based spectral feature mapping for robust speech recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)Google Scholar
  20. 20.
    Hansen, J.H., Pellom, B.L.: An effective quality evaluation protocol for speech enhancement algorithms. In: Fifth International Conference on Spoken Language Processing (1998)Google Scholar
  21. 21.
    Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)CrossRefGoogle Scholar
  22. 22.
    Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
  23. 23.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  24. 24.
    Huang, J., Kingsbury, B.: Audio-visual deep learning for noise robust speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7596–7599. IEEE (2013)Google Scholar
  25. 25.
    Ishii, T., Komiyama, H., Shinozaki, T., Horiuchi, Y., Kuroiwa, S.: Reverberant speech recognition based on denoising autoencoder. In: Interspeech, pp. 3512–3516 (2013)Google Scholar
  26. 26.
    Kumar, A., Florencio, D.: Speech enhancement in multiple-noise conditions using deep neural networks. arXiv preprint arXiv:1605.02427 (2016)
  27. 27.
    Li, J., Zhao, R., Huang, J.T., Gong, Y.: Learning small-size DNN with output-distribution-based criteria. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)Google Scholar
  28. 28.
    Li, K., Mao, S., Li, X., Wu, Z., Meng, H.: Automatic lexical stress and pitch accent detection for L2 English speech using multi-distribution deep neural networks. Speech Commun. 96, 28–36 (2018)CrossRefGoogle Scholar
  29. 29.
    Liu, B., Tao, J., Zhang, D., Zheng, Y.: A novel pitch extraction based on jointly trained deep BLSTM recurrent neural networks with bottleneck features. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 336–340. IEEE (2017)Google Scholar
  30. 30.
    Narayanan, A., Wang, D.: Ideal ratio mask estimation using deep neural networks for robust speech recognition. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7092–7096. IEEE (2013)Google Scholar
  31. 31.
    Naylor, P.A., Gaubitch, N.D.: Speech Dereverberation. Springer, London (2010).  https://doi.org/10.1007/978-1-84996-056-4
  32. 32.
    Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: International Conference on Machine Learning, pp. 1310–1318 (2013)Google Scholar
  33. 33.
    Ribas, D., Llombart, J., Miguel, A., Vicente, L.: Deep speech enhancement for reverberated and noisy signals using wide residual networks. arXiv preprint arXiv:1901.00660 (2019)
  34. 34.
    Seltzer, M.L., 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), pp. 7398–7402. IEEE (2013)Google Scholar
  35. 35.
    Stahl, J., Mowlaee, P.: A pitch-synchronous simultaneous detection-estimation framework for speech enhancement. IEEE/ACM Trans. Audio Speech Langu. Process. (TASLP) 26(2), 436–450 (2018)CrossRefGoogle Scholar
  36. 36.
    Tang, Z., Wang, D., Zhang, Z.: Recurrent neural network training with dark knowledge transfer. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5900–5904. IEEE (2016)Google Scholar
  37. 37.
    Valentini-Botinhao, C.: Noisy reverberant speech database for training speech enhancement algorithms and TTS models, 2016 [dataset] (2017).  https://doi.org/10.7488/ds/2139
  38. 38.
    Van Den Oord, A., Dieleman, S., Schrauwen, B.: Transfer learning by supervised pre-training for audio-based music classification. In: Conference of the International Society for Music Information Retrieval (ISMIR 2014) (2014)Google Scholar
  39. 39.
    Veselỳ, K., Hannemann, M., Burget, L.: Semi-supervised training of deep neural networks. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 267–272. IEEE (2013)Google Scholar
  40. 40.
    Weninger, F., Geiger, J., Wöllmer, M., Schuller, B., Rigoll, G.: Feature enhancement by deep LSTM networks for ASR in reverberant multisource environments. Comput. Speech Lang. 28(4), 888–902 (2014)CrossRefGoogle Scholar
  41. 41.
    Weninger, F., Watanabe, S., Tachioka, Y., Schuller, B.: Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4623–4627. IEEE (2014)Google Scholar
  42. 42.
    Wu, K., Zhang, D., Lu, G.: iPEEH: Improving pitch estimation by enhancing harmonics. Expert Syst. Appl. 64, 317–329 (2016)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.PRIS-Lab, Escuela de Ingeniería EléctricaUniversidad de Costa RicaSan JoseCosta Rica

Personalised recommendations