Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Single-Pass Adapted Training with All-Pass Transforms

John McDonough, William Byrne

Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA

In recent work, the all-pass transform (APT) was proposed as the basis of a speaker adaptation scheme intended for use with a large vocabulary speech recognition system. It was shown that APT-based adaptation reduces to a linear transformation of cepstral means, much like the better known maximum likelihood linear regression (MLLR), but is specified by far fewer free parameters. Due to its linearity, APT-based adaptation can be used in conjunction with speaker-adapted training (SAT), an algorithm for performing maximum likelihood estimation of the parameters of an HMM when speaker adaptation is to be employed during both training and test. In this work, we propose a refinement of SAT called single-pass adapted training (SPAT) which achieves the same improvement in system performance as SAT but requires much less computation for HMM training. In a set of speech recognition experiments conducted on the Switchboard Corpus, we report a word error rate reduction of 5.3% absolute using a single, global APT.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  McDonough, John / Byrne, William (1999): "Single-pass adapted training with all-pass transforms", In EUROSPEECH'99, 2737-2740.