1HETEROGENEOUS LEXICAL UNITS FOR AUTOMATIC SPEECH RECOGNITION: PRELIMINARY INVESTIGATIONS

This paper explores the use of the phone and syllable as primary units of representation in the rst stage of a two-stage recognizer. A nite-state transducer speech rec-ognizer is utilized to congure the recognition as a two-stage process, where either phone or syllable graphs are computed in the rst stage, and passed to the second stage to determine the most likely word hypotheses. Preliminary experiments in a weather information speech understanding domain show that a syllable representation with either bi-gram or trigram language models provides more constraint than a phonetic representation with a higher-order n-gram language model (up to a 6-gram), and approaches the per-formance of a more conventional single-stage word-based con guration. 1