论文信息 - Some comments on the design and implementation of FIR filterbanks for speech recognition

Some comments on the design and implementation of FIR filterbanks for speech recognition

A program has been written which can generate banks of FIR filters using optimal-equiripple design. The composite responses of these filterbanks are very flat and have a stopband rejection of approximately 60 dB. Also, for purposes of speech recognition, energy estimates from filterbank output are frequently used, and are derived from oversampled, rectified input. A very substantial reduction in the number of calculations can be made if filter outputs are decimated while introducing a tolerable amount of error. This idea has been experimentally evaluated.

Harvey F. Silverman | Jay T. Rubinstein

[1] L. Rabiner,et al. A computer program for designing optimum FIR linear phase digital filters , 1973 .

[2] Harvey F. Silverman,et al. What are the significant variables in dynamic programming for discrete utterance recognition? , 1981, ICASSP.

[3] Harvey F. Silverman,et al. A comparison of three feature vector clustering procedures in a speech recognition paradigm , 1983, ICASSP.

[4] L. R. Rabiner,et al. Fir digital filter banks for speech analysis , 1975, The Bell System Technical Journal.

[5] Harvey F. Silverman,et al. Study of human and machine discrete utterance recognition (DUR) , 1982, ICASSP.

[6] L. Rabiner,et al. FIR digital filter design techniques using weighted Chebyshev approximation , 1975, Proceedings of the IEEE.

[7] Harvey F. Silverman,et al. State constrained dynamic programming (SCDP) for discrete utterance recognition , 1980, ICASSP.