Pronunciation Modelling Using a Hand-Labelled Corpus for Conversational Speech Recognition

Download: PDF.

“Pronunciation Modelling Using a Hand-Labelled Corpus for Conversational Speech Recognition” by W. Byrne, M. Finke, S. Khudanpur, J. Mc{D}onough, H. Nock, M. Riley, M. Saraclar, C. Wooters, and G. Zavaliagkos. In IEEE International Conference on Acoustics, Speech and Signal Processing, 1998, IEEE.

Abstract

Accurately modelling pronunciation variability in conversational speech is an important component of an automatic speech recognition system. We describe some of the projects undertaken in this direction during and after WS97, the Fifth LVCSR Summer Workshop, held at Johns Hopkins University, Baltimore, in July- August, 1997. We first illustrate a use of hand-labelled phonetic transcriptions of a portion of the Switchboard corpus, in conjunction with statistical techniques, to learn alternatives to canonical pronunciations of words. We then describe the use of these alternate pronunciations in an automatic speech recognition system. We demonstrate that the improvement in recognition performance from pronunciation modelling persists as the system is enhanced with better acoustic and language models.

Download: PDF.

BibTeX entry:

@inproceedings{pmod_icassp98,
   author = {W. Byrne and M. Finke and S. Khudanpur and J. Mc{D}onough and
	H. Nock and M. Riley and M. Saraclar and C. Wooters and G.
	Zavaliagkos},
   title = {Pronunciation Modelling Using a Hand-Labelled Corpus for
	Conversational Speech Recognition},
   booktitle = {IEEE International Conference on Acoustics, Speech and
	Signal Processing},
   pages = {(4 pages)},
   year = {1998},
   organization = {IEEE}
}

Back to Bill Byrne publications.