Phonetics and Speech Sciences (말소리와 음성과학)

Korean Society of Speech Sciences (한국음성학회)
권호 표지
DOI QR코드

DOI QR Code

Selective pole filtering based feature normalization for performance improvement of short utterance recognition in noisy environments

잡음 환경에서 짧은 발화 인식 성능 향상을 위한 선택적 극점 필터링 기반의 특징 정규화

  • 최보경 (부산대학교 전자전기컴퓨터공학과) ;
  • 반성민 (SK텔레콤 AI사업단 음성인식기술팀) ;
  • 김형순 (부산대학교)
  • Received : 2017.04.29
  • Accepted : 2017.06.25
  • Published : 2017.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

The pole filtering concept has been successfully applied to cepstral feature normalization techniques for noise-robust speech recognition. In this paper, it is proposed to apply the pole filtering selectively only to the speech intervals, in order to further improve the recognition performance for short utterances in noisy environments. Experimental results on AURORA 2 task with clean-condition training show that the proposed selectively pole-filtered cepstral mean normalization (SPFCMN) and selectively pole-filtered cepstral mean and variance normalization (SPFCMVN) yield error rate reduction of 38.6% and 45.8%, respectively, compared to the baseline system.

Keywords

References

  1. Li, J., Deng, L., Gong, Y., & Haeb-Umbach, R. (2014). An overview of noise-robust automatic speech recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 22(4), 745-777. https://doi.org/10.1109/TASLP.2014.2304637
  2. Atal, B. (1974). Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification. Journal of the Acoustical Society of America, 55(6), 1304-1312. https://doi.org/10.1121/1.1914702
  3. Viikki, O., Bye, D., & Laurila, K. (1998). A recursive feature vector normalization approach for robust speech recognition in noise. Proceedings of the IEEE ICASSP (pp. 733-736).
  4. Alam, J., Ouellet, P., Kenny, P., & O'Shaughnessy, D. (2011). Comparative evaluation of feature normalization techniques for speaker verification. Proceedings of the International Conference on Nonlinear Speech Processing (pp. 246-253).
  5. Molau, S., Hilger, F., & Ney, H. (2003). Feature space normalization in adverse acoustic conditions. Proceedings of the IEEE ICASSP (pp. 656-659).
  6. Choi, B., Ban, S., & Kim, H. (2015). Pole-filtered cepstral normalization methods for robust speech recognition. Proceedings of the 2015 Spring Conference of the Korean Society of Speech Sciences (pp. 101-102). (최보경.반성민.김형순 (2015). 강인한 음성인식을 위한 극점 필터링된 켑스트럼 정규화 방식. 한국음성학회 2015 봄학술대회 논문집, 101-102.)
  7. Choi, B., Ban, S., & Kim, H. (2015). Cepstral feature normalization methods using pole filtering and scale normalization for robust speech recognition. The Journal of the Acoustical Society of Korea, 34(4), 316-320. (최보경.반성민.김형순 (2015). 강인한 음성인식을 위한 극점 필터링 및 스케일정규화를 이용한 켑스트럼 특징 정규화 방식. 한국음향학회지, 34(4), 316-320.) https://doi.org/10.7776/ASK.2015.34.4.316
  8. Naik, D. (1995). Pole-filtered cepstral mean subtraction. Proceedings of the IEEE ICASSP (pp. 157-160).
  9. Schroeder, M. R. (1981). Direct (nonrecursive) relations between cepstrum and predictor coefficients. IEEE Transactions on Acoustics, Speech, and Signal Processing, 29(2), 297-301. https://doi.org/10.1109/TASSP.1981.1163546
  10. Hirsch, H. G., & Pearce, D. (2000). The aurora experimental framework for the performance evaluations of speech recognition systems under noisy conditions. Proceedings of the ASR2000-Automatic Speech Recognition: Challenges for the New Millenium ISCA Tutorial and Research Workshop (pp. 181-188).
  11. Acero, A., & Huang, X. (1995). Augmented cepstral normalization for robust speech recognition. Proceedings of the IEEE Automatic Speech Recognition Workshop (pp. 146-147).
  12. Compernolle, D. V. (1989). Noise adaptation in a hidden Markov model speech recognition system. Computer Speech and Language, 3(2), 151-167. https://doi.org/10.1016/0885-2308(89)90027-2
  13. Ying, D., Yan, Y., Dang, J., & Soong, F. K. (2011). Voice activity detection based on an unsupervised learning framework. IEEE Transactions on Audio, Speech, and Language Processing, 19(8), 2624-2633. https://doi.org/10.1109/TASL.2011.2125953
  14. ETSI Standard (2003). Speech processing, transmission and quality aspects (STQ); distributed speech recognition; advanced frontend feature extraction algorithm; compression algorithms. ETSI Technical Report ES 202 050, 1.1.3.
  15. Abdel-Hamid, O., Mohamed, A., Jiang, H., Deng, L., Penn, G., & Yu, D. (2014). Convolutional neural networks for speech recognition. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 22(10), 1533-1545. https://doi.org/10.1109/TASLP.2014.2339736