Abstract

As speech recognition moves from labs into the real world, the sloppy speech problem emerges as a major challenge. Sloppy speech, or conversational speech, refers to the speaking style people typically use in daily conversations. The recognition error rate for sloppy speech has been found to double that of read speech in many circumstances. Previous work on sloppy speech has focused on modeling pronunciation changes, primarily by adding pronunciation variants to the dictionary. The improvement, unfortunately, has been unsatisfactory. To improve

Citations

139	Tree-based state tying for high accuracy acoustic modelling - Young, Odell, et al. - 1994
62	A Review of Large Vocabulary Continuous Speech Recognition - Young - 1996
17	Effect of speaking style on LVCSR performance - Weintraub, Taussig, et al. - 1996
12	New developments in automatic meeting transcription - Yu, Tomokiyo, et al. - 2000
11	Progress in automatic meeting transcription - Yu, Finke, et al. - 1999
7	Statistical modeling in continuous speech recognition (CSR - Young - 2001
6	The use of cepstral means in conversational speech recognition - Westphal - 1997
6	Experiments in automatic meeting transcription using JRTK - Yu, Clark, et al. - 1998
3	Implicit trajectory modeling through gaussian transition models for speech recognition - Yu, Schultz - 2003