Language and Pronunciation Modeling in the CMU 1996 Hub 4 Evaluation

We describe several language and pronunciation modeling techniques that were applied to the 1996 Hub 4 Broadcast News transcription task. These include topic adaptation, the use of remote corpora, vocabulary size optimization, n-gram cutoff optimization, modeling of spontaneous speech, handling of unknown linguistic boundaries, higher order n-grams, weight optimization in rescoring, and lexical modeling of phrases and acronyms.

[1]  G Salton,et al.  Developments in Automatic Text Retrieval , 1991, Science.

[2]  Ralph Grishman,et al.  NYU Language Modeling Experiments for the 1995 CSR Evaluation , 1995 .

[3]  Mari Ostendorf,et al.  Integration of Diverse Recognition Methodologies Through Reevaluation of N-Best Sentence Hypotheses , 1991, HLT.

[4]  Hermann Ney,et al.  Improved backing-off for M-gram language modeling , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[5]  Anthony J. Robinson,et al.  Language model adaptation using mixtures and an exponentially decaying cache , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Slava M. Katz,et al.  Estimation of probabilities from sparse data for the language model component of a speech recognizer , 1987, IEEE Trans. Acoust. Speech Signal Process..

[7]  Mari Ostendorf,et al.  Modeling long distance dependence in language: topic mixtures vs. dynamic cache models , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[8]  Ronald Rosenfeld,et al.  Optimizing lexical and N-gram coverage via judicious use of linguistic data , 1995, EUROSPEECH.