Skip to Main content Skip to Navigation
Conference papers

Combinaison de systèmes pour la phonétisation automatique de noms propres

Abstract : Large vocabulary automatic speech recognition (ASR) technologies perform well in known, controlled contexts. However recognition of proper nouns is commonly considered as a difficult task. Accurate phonetic transcription of a proper noun is difficult to obtain, although it can be one of the most important resources for a recognition system. In this article, we propose methods of automatic phonetic transcription applied to proper nouns. The methods are based on combinations of the rule-based phonetic transcription generator LIA PHON and an acoustic-phonetic decoding system. On the ESTER corpus, we observed that the combined system obtained better results than our reference system (LIA PHON). The WER decreased on segments of speech containing proper nouns, without affecting negatively the results on the rest of the corpus.
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01450912
Contributor : Hakim Amokrane <>
Submitted on : Tuesday, March 28, 2017 - 2:05:20 PM
Last modification on : Tuesday, April 4, 2017 - 1:07:05 AM
Document(s) archivé(s) le : Thursday, June 29, 2017 - 4:21:25 PM

File

038_jep_1625.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-01450912, version 1

Collections

Citation

Antoine Laurent, Sylvain Meignier, Yannick Estève, Paul Deléglise. Combinaison de systèmes pour la phonétisation automatique de noms propres. XXVIIe Journées d'étude sur la parole (JEP 2008), Jun 2008, Avignon, France. pp.4. ⟨hal-01450912⟩

Share

Metrics

Record views

127

Files downloads

126