Comparative experiments on large vocabulary speech recognition

This paper describes several key experiments in large vocabulary speech recognition. We demonstrate that, counter to our intuitions, given a fixed amount of training speech, the number of training speakers has little effect on the accuracy. We show how much speech is needed for speaker-independent (SI) recognition in order to achieve the same performance as speaker-dependent (SD) recognition. We demonstrate that, though the N-Best Paradigm works quite well up to vocabularies of 5,000 words, it begins to break down with 20,000 words and long sentences. We compare the performance of two feature preprocessing algorithms for microphone independence and we describe a new microphone adaptation algorithm based on selection among several codebook transformations.

[1]  Patti Price,et al.  The DARPA 1000-word resource management database for continuous speech recognition , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[2]  Chris Barry,et al.  Speaker adaptation from a speaker-independent training corpus , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[3]  Steve Austin,et al.  The forward-backward search algorithm , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[4]  Pascale Fung,et al.  The estimation of powerful language models from small and large corpora , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Richard M. Stern,et al.  Efficient Cepstral Normalization for Robust Speech Recognition , 1993, HLT.

[6]  Richard M. Schwartz,et al.  The N-Best Algorithm: Efficient Procedure for Finding Top N Sentence Hypotheses , 1989, HLT.

[7]  Francis Kubala,et al.  New uses for the N-Best sentence hypotheses within the BYBLOS speech recognition system , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Jonathan G. Fiscus,et al.  Benchmark Tests for the DARPA Spoken Language Program , 1993, HLT.

[9]  Hynek Hermansky,et al.  Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP) , 1991, EUROSPEECH.

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

[11]  R. Schwartz,et al.  A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.