论文信息 - Language model representations for beam-search decoding

Language model representations for beam-search decoding

This paper presents an efficient way of representing a bigram language model for a beam-search based, continuous speech, large vocabulary HMM recognizer. The tree-based topology considered takes advantage of a factorization of the bigram probability derived from the bigram interpolation scheme, and of a tree organization of all the words that can follow a given one. Moreover, an optimization algorithm is used to considerably reduce the space requirements of the language model. Experimental results are provided for two 10,000-word dictation tasks: radiological reporting (perplexity 27) and newspaper dictation (perplexity 120). In the former domain 93% word accuracy is achieved with real-time response and 23 Mb process space. In the newspaper dictation domain, 88.1% word accuracy is achieved with 1.41 real-time response and 38 Mb process space. All recognition tests were performed on an HP-735 workstation.

Giuliano Antoniol | Fabio Brugnara | Mauro Cettolo | Marcello Federico

[1] Steve J. Young,et al. A One Pass Decoder Design For Large Vocabulary Recognition , 1994, HLT.

[2] Vassilios Digalakis,et al. Techniques to Achieve an Accurate Real-Time Large-Vocabulary Speech Recognition System , 1994, HLT.

[3] Maurizio Omologo,et al. Speaker independent continuous speech recognition using an acoustic-phonetic Italian corpus , 1994, ICSLP.

[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] Alfred V. Aho,et al. The Design and Analysis of Computer Algorithms , 1974 .

[6] Giuliano Antoniol,et al. Radiological reporting by speech recognition: the a.re.s. system , 1994, ICSLP.

[7] Giuliano Antoniol,et al. Language model estimations and representations for real-time continuous speech recognition , 1994, ICSLP.

[8] H. Ney,et al. Improvements in beam search for 10000-word continuous speech recognition , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.