Skip to Main content Skip to Navigation
Theses

Étude sur les représentations continues de mots appliquées à la détection automatique des erreurs de reconnaissance de la parole

Abstract : My thesis concerns a study of continuous word representations applied to the automatic detection of speech recognition errors. Our study focuses on the use of a neural approach to improve ASR errors detection, using word embeddings. The exploitation of continuous word representations is motivated by the fact that ASR error detection consists on locating the possible linguistic or acoustic incongruities in automatic transcriptions. The aim is therefore to find the appropriate word representation which makes it possible to capture pertinent information in order to be able to detect these anomalies. Our contribution in this thesis concerns several initiatives. First, we start with a preliminary study in which we propose a neural architecture able to integrate different types of features, including word embeddings. Second, we propose a deep study of continuous word representations. This study focuses on the evaluation of different types of linguistic word embeddings and their combination in order to take advantage of their complementarities. On the other hand, it focuses on acoustic word embeddings. Then, we present a study on the analysis of classification errors, with the aim of perceiving the errors that are difficult to detect. Perspectives for improving the performance of our system are also proposed, by modeling the errors at the sentence level. Finally, we exploit the linguistic and acoustic embeddings as well as the information provided by our ASR error detection system in several downstream applications.
Complete list of metadatas

Cited literature [106 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01661491
Contributor : Abes Star :  Contact
Submitted on : Wednesday, January 31, 2018 - 11:30:10 AM
Last modification on : Tuesday, March 31, 2020 - 3:21:37 PM
Document(s) archivé(s) le : Tuesday, May 1, 2018 - 12:17:16 PM

File

2017LEMA1019_vers02.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01661491, version 1

Citation

Sahar Ghannay. Étude sur les représentations continues de mots appliquées à la détection automatique des erreurs de reconnaissance de la parole. Informatique et langage [cs.CL]. Université du Maine, 2017. Français. ⟨NNT : 2017LEMA1019⟩. ⟨tel-01661491⟩

Share

Metrics

Record views

641

Files downloads

2873