Comparison of various feature decorrelation techniques in automatic speech recognition

CITSA 2006 - 3rd Int. Conf. on Cybernetics and Information Technol., Systems and Applications, Jointly with the 4th Int. Conf. on Computing, Communications and Control Technologies, CCCT 2006 - Proc.

Volumn 1, Issue , 2006, Pages 165-168

  Psutka, J V ^a   Müller, Luděk ^a  

^a UNIVERSITY OF WEST BOHEMIA   (Czech Republic)

Author keywords

Decorrelation techniques; Maximum linear likelihood transform; Speech parameterization

Indexed keywords

CYBERNETICS; INFORMATION TECHNOLOGY; MAXIMUM LIKELIHOOD; SPEECH PROCESSING; SPEECH RECOGNITION;

AUTOMATIC SPEECH RECOGNITION; AUTOMATIC SPEECH RECOGNITION SYSTEM; DECORRELATION TECHNIQUE; FRONT-END MODULE; MATRIX CLUSTERING; RESEARCH TEAMS;

MATHEMATICAL TRANSFORMATIONS;

EID: 84879874288     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. Psutka, J.V., Muïller, L,.: Optimization of some parameters in the speech-processing module developed for the speaker independent ASR system. -In: Proceedings of the 7,th World Multtconference on Systemics. Cybernetics and Informatics SCI'2003, Orlando, U.S.A., 2003. pp. 414-418.
2. Psutka, J.V., Muïller, L.: Building Robust PLP-based Acoustic Module for ASR Application. -In: Proceedings of the 10th International Conference Speech and Computer SPECOM'2005, Patras, Greece, 2005, pp.761-764.
3. Pražák, A., et al.:: Automatic Online Subtitling of the Czech Parliament Meetings. TSD 2006. Lecture Notes in Artificial Intelligence. Springer-Verlag, Berlin, Heidelberg, 2006.
4. Gales, M.J.F.: Semi-Tied Covariance Matrices for Hidden Markov Models. IEEE Trans, on Speech and Audio Proc, vol.7, no.3, 1999, pp.272-281.
5. Olsen, P.A., Gopinath, R.A.: Extended MLLT for Gaussian Mixture Models or Modeling Inverse Covariances by Basis Expansion. IEEE Trans, on Speech and Audio Processing, January 2004.