Single-Pass adapted training with All-Pass transforms

Download: PDF.

“Single-Pass adapted training with All-Pass transforms” by J. Mc{D}onough and W. Byrne. In Proc. of the European Conference on Speech Communication and Technology (EUROSPEECH), 1999.


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 trainingB (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.

Download: PDF.

BibTeX entry:

   author = {J. Mc{D}onough and W. Byrne},
   title = {Single-Pass adapted training with All-Pass transforms},
   booktitle = {Proc. of the European Conference on Speech Communication
	and Technology (EUROSPEECH)},
   pages = {(4 pages)},
   year = {1999}

Back to Bill Byrne publications.