Automatic Generation of Pronunciation Lexicons for Mandarin Casual Speech

Download: PDF.

“Automatic Generation of Pronunciation Lexicons for Mandarin Casual Speech” by W. Byrne, V. Venkataramani, T. Kamm, T.F. Zheng, Z. Song, P. Fung, Y. Lui, and U. Ruhi. In IEEE Conference on Acoustics, Speech and Signal Processing, (Salt Lake City, Utah), 2001, pp. 569-572 (4 pages), IEEE.

Abstract

Pronunciation modeling for large vocabulary speech recognition attempts to improve recognition accuracy by identifying and modeling pronunciations that are not in the ASR systems pronunciation lexicon. Pronunciation variability in spontaneous Mandarin is studied using the newly created CASS corpus of phonetically annotated spontaneous speech. Pronunciation modeling techniques developed in English are applied to this corpus to train pronunciaton models when are then applied in Mandarin Broadcast News transcription.

Download: PDF.

BibTeX entry:

@inproceedings{mcs2000_icassp01,
   author = {W. Byrne, and V. Venkataramani, and T. Kamm, and T.F. Zheng,
	and Z. Song, and P. Fung, and Y. Lui, and U. Ruhi,},
   title = {Automatic Generation of Pronunciation Lexicons for {M}andarin
	Casual Speech},
   booktitle = {IEEE Conference on Acoustics, Speech and Signal Processing},
   volume = {1},
   pages = {569-572 (4 pages)},
   address = {Salt Lake City, Utah},
   year = {2001},
   organization = {IEEE}
}

Back to Bill Byrne publications.