ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition

April 13-16, 2003
Tokyo Institute of Technology, Tokyo, Japan

Flexible Parameter Tying for Conversational Speech Recognition

Hua Yu, Alex Waibel

Interactive Systems Lab, Carnegie Mellon University, Pittsburgh, PA, USA

Modeling pronunciation variation is key for recognizing conversational speech. Previous efforts on pronunciation modeling by modifying dictionaries only yielded marginal improvement. Due to complex interaction between dictionaries and acoustic models, we believe a pronunciation modeling scheme is plausible only when closely coupled with the underlying acoustic model. This paper explores the use of flexible parameter tying for pronunciation modeling. In particular, two new techniques are investigated: Gaussian tying and flexible tree clustering. We report a 1.3% absolute WER improvement over the traditional modeling framework on the Switchboard task.

Full Paper

Bibliographic reference.  Yu, Hua / Waibel, Alex (2003): "Flexible parameter tying for conversational speech recognition", in SSPR-2003, paper MAP4.