The LIMSI Continuous Speech Dictation Systemt

The LIMSI Continuous Speech Dictation Systemt J.L. Gauvain, L.F. Lamel, G. Adda, M. Adda-Decker LIMSI-CNRS, BP 133 91403 Orsay cedex, FRANCE {gauvain,lamel,adda,madda}@limsi.fr ABSTRACT A major axis of research at LIMSI is directed at multilingual, speaker-independent, large vocabulary speech dictation. In this pa- per the LIMSI recognizer which was evaluated in the ARPA NOV93 CSR test is described, and experimental results on the WSJ and BREF corpora under closely matched conditions are reported. For both corpora word recognition expenrnents were carried out with vocabularies containing up to 20k words. The recognizer makes use of continuous density HMM with Gaussian mixture for acous- tic modeling and n-gram statistics estimated on the newspaper texts for language modeling. The recognizer uses a time-synchronous graph-search strategy which is shown to still be viable with a 20k- word vocabulary when used with bigram back-off language models. A second forward pass, which makes use of a word graph generated with the bigram, incorporates a trigram language model. Acoustic modeling uses cepstrum-based features, context-dependent phone models (intra and interword), phone duration models, and sex- dependent models. INTRODUCTION Speech recognition research at LIMSI aims to develop rec- ognizers that are task-, speaker-, and vocabulary-independent so as to be easily adapted to a variety of applications. The applicability of speech recognition techniques used for one language to other languages is of particular importance in Europe. The multilingual aspects are in part carried out in the context of the LRE SQALE (Speech recognizer Qual- ity Assessment for Linguistic Engineering) project, which is aimed at assessing language dependent issues in multilin- gual recognizer evaluation. In this project, the same system will be evaluated on comparable tasks in different languages (English, French and German) to determine cross-lingual dif- ferences, and different recognizers will be compared on the same language to compare advantages of different recogni- tion strategies. In this paper some of the primary issues in large vocabu- lary, speaker-independent, continuous speech recognition for dictation are addressed. These issues include language mod- eling, acoustic modeling, lexical representation, and search. Acoustic modeling makes use of continuous density HMM with Gaussian mixture of context-dependent phone models. For language modeling n-gram statistics are estimated on tThis work is partially funded by the LRE project 62-058 SQALE. 319 text material. To deal with phonological variability alter- nate pronunciations are included in the lexicon, and optional phonological rules are applied during training and recogni- tion. The recognizer uses a time-synchronous graph-search strategy[16] for a first pass with a bigram back-off language model (LM)[10]. A trigram LM is used in a second acoustic decoding pass which makes use of the word graph generated using the bigram LM[6]. Experimental results are reported on the ARPA Wall Street Journal (WSJ)[19] and BREF[14] corpora, using for both corpora over 37k utterances for acous- tic training and more than 37 million words of newspaper text for language model training. While the number of speakers is larger for WSJ, the total amount of acoustic training ma- terial is about the same (see Table 1). …

Content truncated to 500 words