Dynamic Lexicon for a Very Large Vocabulary Vocal Dictation

Abstract : For very large vocabulary vocal dictation systems, we present a decoding strategy useful to reduce the lexical decoding cost. For each test-utterance, a sub-lexicon is selected from a very large recognition vocabulary. Such a recognition sub-lexicon is called Dynamic Lexicon (DL). Various algorithms of DL selection are developed and tested in terms of coverage rate of textual corpus. From these experiments, we describe a DL constitution we choose to use in D-DAL, our HMM-based recognizer competing for the first campaign of french vocal dictation supported by AUPELF. The contribution made by this original DL is a posteriori confirmed through the AUPELF-B1 test-dictation.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01627669
Contributor : Lip6 Publications <>
Submitted on : Thursday, November 2, 2017 - 11:24:06 AM
Last modification on : Wednesday, May 15, 2019 - 10:12:14 AM

Identifiers

  • HAL Id : hal-01627669, version 1

Citation

Marie-Josée Caraty, Claude Montacié, Fabrice Lefevre. Dynamic Lexicon for a Very Large Vocabulary Vocal Dictation. EUROSPEECH 1997 - Fifth European Conference of Speech Communication and Technology, Sep 1997, Rhodes, Greece. pp.2691-2694. ⟨hal-01627669⟩

Share

Metrics

Record views

32