MLLR Adaptation Techniques for Pronunciation Modeling

Download: PDF.

“MLLR Adaptation Techniques for Pronunciation Modeling” by V. Venkataramani and W. Byrne. In IEEE Workshop on Automatic Speech Recognition and Understanding, (Madonna di Campiglio, Italy), 2001.

Abstract

Multiple regression class MLLR transforms are investigated for use with pronunciation models that predict variation in the observed pronunciations given the phonetic context. Regression classes can be constructed so that MLLR transforms can be estimated and used to model specific acoustic changes associated with pronunciation variation. The effectiveness of this modeling approach is evaluated on the phonetically transcribed portion of the SWITCHBOARD conversational speech corpus.

Download: PDF.

BibTeX entry:

@inproceedings{mllrpm_asru01,
   author = {V. Venkataramani, and W. Byrne,},
   title = {{MLLR} Adaptation Techniques for Pronunciation Modeling},
   booktitle = {IEEE Workshop on Automatic Speech Recognition and
	Understanding},
   pages = {(4 pages)},
   address = {Madonna di Campiglio, Italy},
   year = {2001}
}

Back to Bill Byrne publications.