Stochastic Pronunciation Modeling from Hand-labelled Phonetic Corpora

Stochastic Pronunciation Modeling from Hand-labelled Phonetic Corpora” by M. Riley, W. Byrne, M. Finke, S. Khudanpur, A. Ljolje, J. McDonough, H. Nock, M. Saraclar, C. Wooters, and G. Zavaliagkos. Speech Communication, Nov. 1999, pp. 109-116 (8 pages).


In the early '90s, the availability of the TIMIT read-speech phonetically transcribed corpus led to work at AT&T on the automatic inference of pronunciation variation. This work, briefly summarized here, used stochastic decisions trees trained on phonetic and linguistic features, and was applied to the DARPA North American Business News read-speech ASR task. More recently, the ICSI spontaneous-speech phonetically transcribed corpus was collected at the behest of the 1996 and 1997 LVCSR Summer Workshops held at Johns Hopkins University. A 1997 workshop (WS97) group focused on pronunciation inference from this corpus for application to the DoD Switchboard spontaneous telephone speech ASR task. We describe several approaches taken there. These include (1) one analogous to the AT&T approach, (2) one, inspired by work at WS96 and CMU, that involved adding pronunciation variants of a sequence of one or more words (`multiwords') in the corpus (with corpus-derived probabilities) into the ASR lexicon, and (1+2) a hybrid approach in which a decision-tree model was used to automatically phonetically transcribe a much larger speech corpus than ICSI and then the multiword approach was used to construct an ASR recognition pronunciation lexicon.

BibTeX entry:

   author = {M. Riley and W. Byrne and M. Finke and S. Khudanpur and A.
	Ljolje and J. McDonough and H. Nock and M. Saraclar and C. Wooters
	and G. Zavaliagkos},
   title = {Stochastic Pronunciation Modeling from Hand-labelled Phonetic
   journal = {Speech Communication},
   pages = {109--116 (8 pages)},
   month = nov,
   year = {1999},
   url = {}

Back to Bill Byrne publications.