M. Bacchiani and M. Ostendorf,
``Joint Lexicon, Acoustic Unit Inventory and Model Design,''
Speech Communication, vol. 29, no. 2-4, pp. 99-114. (invited paper)

Although most parameters in a speech recognition system are estimated from data by use of an objective function, the unit inventory and lexicon are generally hand crafted and therefore unlikely to be optimal. This paper proposes a joint solution to the related problems of learning a unit inventory and corresponding lexicon from data. On a speaker-independent read speech task with a 1k vocabulary, the proposed algorithm outperforms phone-based systems at both high and low complexities.


Return to SSLI Lab Publications