Novel Gammatone Filterbank Based Spectro-Temporal Features for Robust Phoneme Recognition

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10597)

Abstract

Recently, Automatic Speech Recognition (ASR) technology is being used in practical scenarios and hence, robustness of ASR is becoming increasingly important. State-of-the-art Mel Frequency Cepstral Coefficients (MFCC) features are known to be affected by acoustic noise whereas physiologically motivated features such as spectro-temporal Gabor filterbank (GBFB) features intend to perform better in signal degradation conditions. The spectro-temporal GBFB feature extraction incorporates mel filterbank to mimic frequency mapping in the Basilar Membrane (BM) in the inner ear. In this paper, Gammatone filterbank is used and a comparison is done between GBFB with mel filterbank (GBFBmel) features and GBFB with Gammatone filterbank (GBFBGamm) features. MFCC features and Gammatone Frequency Cepstral Coefficients (GFCC) features are concatenated with GBFBmel and GBFBGamm features, respectively, to improve recognition performance. Experiments are carried out to calculate phoneme recognition accuracy (PRA), on TIMIT database (without ‘sa’ sentences), with additive white, volvo and high frequency noises at various SNR levels from −5 dB to 20 dB. Results show that, with acoustic modeling only, proposed feature set (GBFBGamm+GFCC) performs better (in terms of PRA %), than GBFBmel+MFCC features by an average of 1%, 0.2% and 0.8% for white, volvo and high frequency noises, respectively.

Keywords

Robust ASR Gabor filterbank (GBFB) features Gammatone filterbank MFCC Acoustic model Language model 

References

  1. 1.
    Hermansky, H., Sharma, S.: Temporal patterns (TRAPS) in ASR of noisy speech. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP), Phoenix, Arizona, USA, vol. 1, pp. 289–292 (1999)Google Scholar
  2. 2.
    Davis, S.B., Mermelstein, P.: Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357–366 (1980)CrossRefGoogle Scholar
  3. 3.
    Hermansky, H.: Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 87(4), 1738–1752 (1990)CrossRefGoogle Scholar
  4. 4.
    Schadler, M., Meyer, B., Kollmeier, B.: Spectro-temporal modulation subspace spanning filter bank features for robust automatic speech recognition. J. Acoust. Soc. Am. 131(5), 4134–4151 (2012)CrossRefGoogle Scholar
  5. 5.
    Slaney, M.: Auditory Toolbox, version 2. http://engineering.purdue.edu/malcolm/interval/1998-010/. Accessed 7 Apr 2015
  6. 6.
    Shao, Y., Jin, Z., Wang, D., Srinivasan, S.: An auditory-based feature for robust speech recognition. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, pp. 4625–4628 (2009)Google Scholar
  7. 7.
    Chi, T., Ru, P., Shamma, S.A.: Multiresolution spectrotemporal analysis of complex sounds. J. Acoust. Soc. Am. 118(2), 887–906 (2005)CrossRefGoogle Scholar
  8. 8.
    Depireux, D.A., Ru, P., Shamma, S.A., Simon, J.Z.: Response-field dynamics in the auditory pathway. In: Computational Neuroscience, pp. 1–6 (1998)Google Scholar
  9. 9.
    Lee, K., Hon, H.: Speaker-independent phone recognition using hidden Markov Models. IEEE Trans. Acoust. Speech Signal Process. 37(11), 1642–1648 (1989)Google Scholar
  10. 10.
    Chi, T., Gao, Y., Gutyon, M.C., Ru, P., Shamma, S.A.: Spectro-temporal modulation transfer functions and speech intelligibility. J. Acoust. Soc. Am. 106(5), 2719–2732 (1999)CrossRefGoogle Scholar
  11. 11.
    Hermansky, H., Morgan, N.: RASTA processing of speech. IEEE Trans. Speech Audio Process. 2(4), 578–589 (1994)CrossRefGoogle Scholar
  12. 12.
    Young, S.J., Evermann, G., Gales, M.J.F., et al.: The HTK book for HTK version 3.4. Microsoft Corporation (2006)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Dhirubhai Ambani Institute of Information and Communication TechnologyGandhinagarIndia

Personalised recommendations