DOI QR코드

DOI QR Code

Performance Improvement of Speaker Recognition Using Enhanced Feature Extraction in Glottal Flow Signals and Multiple Feature Parameter Combination

Glottal flow 신호에서의 향상된 특징추출 및 다중 특징파라미터 결합을 통한 화자인식 성능 향상

  • Kang, Jihoon (Department of Electronics Engineering/ERI, Gyeongsang National University) ;
  • Kim, Youngil (Department of Electronics Engineering/ERI, Gyeongsang National University) ;
  • Jeong, Sangbae (Department of Electronics Engineering/ERI, Gyeongsang National University)
  • Received : 2015.10.22
  • Accepted : 2015.11.23
  • Published : 2015.12.31

Abstract

In this paper, we utilize source mel-frequency cepstral coefficients (SMFCCs), skewness, and kurtosis extracted in glottal flow signals to improve speaker recognition performance. Generally, because the high band magnitude response of glottal flow signals is somewhat flat, the SMFCCs are extracted using the response below the predefined cutoff frequency. The extracted SMFCC, skewness, and kurtosis are concatenated with conventional feature parameters. Then, dimensional reduction by the principal component analysis (PCA) and the linear discriminat analysis (LDA) is followed to compare performances with conventional systems under equivalent conditions. The proposed recognition system outperformed the conventional system for large scale speaker recognition experiments. Especially, the performance improvement was more noticeable for small Gaussan mixtures.

본 논문에서는 화자 인식의 성능을 개선하기 위해서 glottal flow로부터 source mel-frequency cepstral coefficient (SMFCC), 왜도, 첨도를 추출하여 활용하였다. 일반적으로 glottal flow의 고주파 대역은 응답의 크기가 평탄하므로 미리 정한 차단주파수 미만에 대해서만 SMFCC를 추출한다. 추출된 SMFCC, 왜도, 첨도는 종래의 특징 파라미터와 결합된 후 종래의 화자인식 시스템과 동등한 조건에서의 성능 비교를 위하여 principal component analysis (PCA) 및 linear discriminiat analysis (LDA)를 통한 차원축소가 행해진다. 대용량의 화자인식 실험결과를 통해서 제안된 인식 시스템이 종래의 화자인식 시스템 보다 더 좋은 성능을 나타냄을 확인할 수 있었으며, 특히 가우시안 혼합이 낮을 때 더 높은 성능향상을 나타내었다.

Keywords

References

  1. T. Kinnunen and H. Li, "An overview of text-independent speaker recognition: From features to supervectors," Speech Communication, Vol. 52, No. 1, pp. 12-40, 2010. https://doi.org/10.1016/j.specom.2009.08.009
  2. B. Putra and Suyanto, "Implementation of secure speaker verification at web login page using Mel Frequency Cepstral coefficient-Gaussian Mixture Model (MFCCGMM)," ICA, pp. 358-363, 2011.
  3. N. Ahmed, "How I came up with the discrete cosine transform," Digital Signal Processing, Vol. 1, No. 1, pp. 4-9, 1991. https://doi.org/10.1016/1051-2004(91)90086-Z
  4. D. Raynolds and R. Rose, "Robust text-independent speaker identification using Gaussian mixture speaker models," IEEE Trans. Speech and Audio Proc., Vol. 3, No. 1, pp. 72-83, 1995. https://doi.org/10.1109/89.365379
  5. L. Rabiner and B. H. Juang, Fundamental of Speech Recognition, Signal Processing Series, Prentice Hall, New Jersey, 1993.
  6. T. Kinnunen and P. Alku, "On separation glottal source and vocal tract information in telephony speaker verification," ICASSP, pp. 4545-4548, 2009.
  7. J. Markel and A. Gray Jr., Linear Prediction of Speech, Springer-Verlag, New York, 1976.
  8. P. Alku, H. Tiitinen and R. Naatanen, "A method for generating natural-sounding speech stimuli for cognitive brain research," CLINPH, pp. 1329-1333, 1999.
  9. W. Kleijin and K. Paliwal, Speech Coding and Synthesis, 2nd ed., Elsevier, 1998.
  10. C. Nikias and A. Petropulu, Higher-Order Spectra Analysis, Prentice Hall, 1993.
  11. Martinez, A.M. and Kak, A.C., "PCA versus LDA," IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 23, No. 2, pp. 228-233, 2001. https://doi.org/10.1109/34.908974
  12. Md Jahangir Alam, T. Kinnunen, P. Kenny, P. Ouellet and D. O'Shaughnessy, "Multitaper MFCC and PLP features for speaker verification using i-vectors," Speech Communication, Vol. 55, No. 2, pp. 237-251, 2013. https://doi.org/10.1016/j.specom.2012.08.007
  13. H. Hermanski, "Perceptually linear predictive(PLP) analysis of speech," J. Acoust. Soc. Am., Vol. 87. No. 4, Apr. 1990.