Skip to Main content Skip to Navigation
Theses

Réseaux de neurones profonds appliqués à la compréhension de la parole

Abstract : This thesis is a part of the emergence of deep learning and focuses on spoken language understanding assimilated to the automatic extraction and representation of the meaning supported by the words in a spoken utterance. We study a semantic concept tagging task used in a spoken dialogue system and evaluated with the French corpus MEDIA. For the past decade, neural models have emerged in many natural language processing tasks through algorithmic advances or powerful computing tools such as graphics processors. Many obstacles make the understanding task complex, such as the difficult interpretation of automatic speech transcriptions, as many errors are introduced by the automatic recognition process upstream of the comprehension module. We present a state of the art describing spoken language understanding and then supervised automatic learning methods to solve it, starting with classical systems and finishing with deep learning techniques. The contributions are then presented along three axes. First, we develop an efficient neural architecture consisting of a bidirectional recurrent network encoder-decoder with attention mechanism. Then we study the management of automatic recognition errors and solutions to limit their impact on our performances. Finally, we envisage a disambiguation of the comprehension task making the systems more efficient.
Complete list of metadatas

Cited literature [188 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02077011
Contributor : Abes Star :  Contact
Submitted on : Friday, March 22, 2019 - 3:34:08 PM
Last modification on : Tuesday, March 31, 2020 - 3:21:58 PM
Document(s) archivé(s) le : Sunday, June 23, 2019 - 3:31:17 PM

File

2019LEMA1006.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02077011, version 1

Citation

Edwin Simonnet. Réseaux de neurones profonds appliqués à la compréhension de la parole. Informatique et langage [cs.CL]. Université du Maine, 2019. Français. ⟨NNT : 2019LEMA1006⟩. ⟨tel-02077011⟩

Share

Metrics

Record views

392

Files downloads

924