ASR2000 - Automatic Speech Recognition: Challenges for the new Millenium September 18-20, 2000 Paris, France

Theory and Practice of Acoustic Confusability

Harry Printz and Peder Olsen

IBM T. J. Watson Research Center, Yorktown Heights, NY, USA

In this paper we define two alternatives to the familiar perplexity statistic (hereafter lexical perplexity), which is widely applied both as a measure-of-goodness and as an objective function for training language models. These alternatives, respectively acoustic perplexity and the synthetic acoustic word error rate, fuse information from both the language model and the acoustic model. We show how to compute these statistics by effectively synthesizing a large acoustic corpus, demonstrate their superiority to lexical perplexity as predictors of language model performance, and investigate their use as objective functions for training language models. We present results from a simple speech recognition experiment that demonstrate a small reduction in word error rate.

Full Paper (PDF)   Full Paper (Zipped Postscript)

Bibliographic reference.  Printz, Harry / Olsen, Peder (2000): "Theory and practice of acoustic confusability", In ASR-2000, 77-84.