Introduction of semantic model to help speech recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Introduction of semantic model to help speech recognition


Current Automatic Speech Recognition (ASR) systems mainly take into account acoustic, lexical and local syntactic information. Long term semantic relations are not used. ASR systems significantly decrease performance when the training conditions and the testing conditions differ due to the noise, etc. In this case the acoustic information can be less reliable. To help noisy ASR system, we propose to supplement ASR system with a semantic module. This module re-evaluates the N-best speech recognition hypothesis list and can be seen as a form of adaptation in the context of noise. For the words in the processed sentence that could have been poorly recognized, this module chooses words that correspond better to the semantic context of the sentence. To achieve this, we introduced the notions of a context part and possibility zones that measure the similarity between the semantic context of the document and the corresponding possible hypothesis. The proposed methodology uses two continuous representations of words: word2vec and FastText. We conduct experiments on the publicly available TED conferences dataset (TED-LIUM) mixed with real noise. The proposed method achieves a significant improvement of the word error rate (WER) over the ASR system without semantic information.
Fichier principal
Vignette du fichier
TSD.pdf (239.37 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02862245 , version 1 (09-06-2020)


  • HAL Id : hal-02862245 , version 1


Stephane Level, Irina Illina, Dominique Fohr. Introduction of semantic model to help speech recognition. TSD 2020 - Twenty-third International Conference on Text, Speech and Dialogue, Sep 2020, Brno, Czech Republic. ⟨hal-02862245⟩
180 View
385 Download


Gmail Facebook Twitter LinkedIn More