Skip to Main content Skip to Navigation
New interface
Conference papers

Evaluating grapheme-to-phoneme converters in automatic speech recognition context

Denis Jouvet 1 Dominique Fohr 1 Irina Illina 1 
1 PAROLE - Analysis, perception and recognition of speech
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This paper deals with the evaluation of grapheme-to-phoneme (G2P) converters in a speech recognition context. The precision and recall rates are investigated as potential measures of the quality of the multiple generated pronunciation variants. Very different results are obtained whether or not we take into account the frequency of occurrence of the words. Since G2P systems are rarely evaluated on a speech recognition performance basis, the originality of this paper consists in using a speech recognition system to evaluate the G2P pronunciation variants. The results show that the training process is quite robust to some errors in the pronunciation lexicon, whereas pronunciation lexicon errors are harmful in the decoding process. Noticeable speech recognition performance improvements are achieved by combining two different G2P converters, one based on conditional random fields and the other on joint multigram models, as well as by checking the pronunciation variants of the most frequent words.
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download
Contributor : Denis Jouvet Connect in order to contact the contributor
Submitted on : Monday, September 14, 2015 - 11:41:22 AM
Last modification on : Saturday, June 25, 2022 - 7:46:01 PM
Long-term archiving on: : Tuesday, December 29, 2015 - 1:31:43 AM


Files produced by the author(s)



Denis Jouvet, Dominique Fohr, Irina Illina. Evaluating grapheme-to-phoneme converters in automatic speech recognition context. ICASSP - 2012 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Mar 2012, Kyoto, Japan. pp.4821 - 4824, ⟨10.1109/ICASSP.2012.6288998⟩. ⟨hal-00753364⟩



Record views


Files downloads