Vocabulary and language model adaptation using information retrieval - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2004

Vocabulary and language model adaptation using information retrieval

Résumé

The goal of vocabulary optimization is to construct a vocabulary with exactly those words that are the most likely to appear in the test data. We will present a new approach to reduce the out-of-vocabulary (OOV) rate by adapting the vocabulary model during the ASR process. This method can also be used for the statistical language model (SLM) adaptation. An information retrieval system is used after the first pass of the ASR system to obtain a set of relevant documents. These documents are then used to generate the new vocabulary and/or corpus. In this paper, we propose a new retrieving method well-adapted for this purpose. Experiments were carried out on French with a 28% OOV rate reduction. Experiments were also carried out on English for the SLM adaptation, with 7.9% perplexity reduction, and minor WER improvement.
Fichier non déposé

Dates et versions

hal-01392515 , version 1 (04-11-2016)

Identifiants

  • HAL Id : hal-01392515 , version 1

Citer

Brigitte Bigi, Yan Huang, Renato de Mori. Vocabulary and language model adaptation using information retrieval. International Conference on Spoken Language Processing, 2004, Jeju Island, South Korea. pp.1361-1364. ⟨hal-01392515⟩

Collections

UNIV-AVIGNON LIA
137 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More