论文信息 - Frame and frame dimension reduction techniques for automatic speech recognition

Frame and frame dimension reduction techniques for automatic speech recognition

Concentrates on techniques for parameter and frame reduction. Standard parameter sets of contemporary speech recognition systems include some set of basic parameters (e.g. cepstra and energy), their time derivatives, and their second time derivatives. The large number of parameters (typically 25 to 45) induces the investigation of methods for reducing the amount of computation, without loss of recognition accuracy. The paper presents the variable frame rate analysis, a technique for leaving out frames that are too resemblant, and describes methods for decreasing the number of parameters in a frame. >

Dirk Van Compernolle | P Le Cerf | D. Van Compernolle | P. L. Cerf

[1] S. M. Peeling,et al. The use of variable frame rate analysis in speech recognition , 1991 .

[2] Peter F. Brown,et al. The acoustic-modeling problem in automatic speech recognition , 1987 .

[3] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[4] Dirk Van Compernolle. The ESAT hidden Markov model speech recognition system , 1990 .

[5] Dirk Van Compernolle,et al. Speech parameter data reduction for recognition purposes , 1991 .

[6] Wendy J. Holmes,et al. Speech Synthesis and Recognition , 1988 .

[7] S. M. Peeling,et al. Variable frame rate analysis in the ARM continuous speech recognition system , 1991, Speech Commun..

[8] Dirk Van Compernolle,et al. Reduction techniques for frames and frame dimensions in automatic speech recognition , 1992 .

[9] John Makhoul,et al. BYBLOS: The BBN continuous speech recognition system , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.