Towards the use of full covamance models for missing data speaker recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2008, Pages 4537-4540

  Kühne, Marco ^a   Pullella, Daniel ^a   Togneri, Roberto ^a   Nordholm, Sven ^b  

^a UNIVERSITY OF WESTERN AUSTRALIA   (Australia)

^b Western Australian Telecommunications Research Institute   (Australia)

Author keywords

Missing data; Robustness; Speaker recognition

Indexed keywords

INTERNATIONAL CONFERENCES; MARGINALIZATION; MISSING DATA; ROBUSTNESS; SPEAKER RECOGNITION;

ACOUSTICS; LOUDSPEAKERS; SIGNAL PROCESSING; SPEECH; SPEECH PROCESSING;

MATHEMATICAL MODELS;

EID: 51449118248     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2008.4518665     Document Type: Conference Paper

References (11)

1. D. Reynolds and R. Rose, "Robust text-independent speaker identification using gaussian mixture speaker models," IEEE Trans. Speech Audio Process., vol. 3, no. 1, 1995.
2. A. Morris, M. Cooke, and P. Green, "Some solution to the missing feature problem in dataclassification, with application to noise robust asr," in Proc. ICASSP, Seattle, USA, 1998.
3. M. Cooke, P. Green, L. Josifovski, and A. Vizinho, "Robust automatic speech recognition with missing and unreliable acoustic data," Speech Communication, vol. 34, 2001.
4. A. Drygajlo and M. El-Maliki, "Speaker verification in noisy environments with combined spectral substraction and missing feature theory," in Proc. ICASSP, Seattle, USA, 1998.
5. Y. Shao and D. Wang, "Robust speaker recognition using binary time-frequency masks," in Proc. ICASSP, Toulouse, France, 2006.
6. M. Cooke, A. Morris, and P. Green, "Missing data techniques for robust speech recognition," in Proc. ICASSP, Munich, Germany, 1997.
7. Y. Tong, The multivariate normal distribution, Springer Series in Statistics. Springer-Verlag, New York, 1990.
8. M. Kühne, R. Togneri, and S. Nordholm, "Smooth soft melspectrographic masks based on blind sparse source separation," in Interspeech, Antwerp, Belgium, 2007.
9. M. van Segbroeck and H. van Hamme, "Vector-quantization based mask estimation for missig data automatic speech recognition," in Interspeech, Antwerp, Belgium, 2007.
10. D. Pullella, M. Kühne, and R. Togneri, "Robust speaker identification using combined feature selection and missing data recognition," in Proc. ICASSP, Las Vegas, USA, 2008, (accepted for publication).
11. R. Wang et al., "Fast likelihood computation method using block-diagonal covariance matrices in hidden markov model," in Proc. ISCSLP, Taipei, Taiwan, 2002.