Large vocabulary natural language continuous speech recognition
L.R. Bahl, R. Bakis, J.R. Bellegarda, Peter F. Brown, David Burshtein, Subrata Kumar Das, P.V. de Souza, Ponani S. Gopalakrishnan, F. Jelinek, Dimitri Kanevsky, R. L. Mercer, Arthur J. Nadas, D. Nahamoo, Michael Picheny · International Conference on Acoustics, Speech, and Signal Processing · 2003
A description is presented of the authors' current research on automatic speech recognition of continuously read sentences from a naturally-occurring corpus: office correspondence. The recognition system combines features from their current isolated-word recognition system and from their previously developed continuous-speech recognition system. It consists of an acoustic processor, an acoustic channel model, a language model, and a linguistic decoder. Some new features in the recognizer relative to the isolated-word speech recognition system include the use of a fast match to prune rapidly to a manageable number the candidates considered by the detailed match, multiple pronunciations of all function words, and modeling of interphone coarticulatory behavior. The authors recorded training and test data from a set of ten male talkers. The perplexity of the test sentences was found to be 93; none of sentences was part of the data used to generate the language model. Preliminary (speaker-dependent) recognition results on these talkers yielded an average word error rate of 11.0%.>