8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Parameter Tuning for Fast Speech Recognition

Thomas Colthurst, Tresi Arvizo, Chia-Lin Kao, Owen Kimball, Stephen A. Lowe, David R. H. Miller, Jim Van Sciver

BBN Technologies, USA

We describe a novel method for tuning the decoding parameters of a speech-to-text system so as to minimize word error rate (WER) subject to an over-all time constraint. When applied to three sub-realtime systems for recognizing English conversational telephone speech, the method gave speed improvements of up to 21.1% while at the same time reducing WER by up to 6.7%.

Full Paper

Bibliographic reference.  Colthurst, Thomas / Arvizo, Tresi / Kao, Chia-Lin / Kimball, Owen / Lowe, Stephen A. / Miller, David R. H. / Sciver, Jim Van (2007): "Parameter tuning for fast speech recognition", In INTERSPEECH-2007, 1477-1480.