Skip to Main content Skip to Navigation

Du signal au concept : réseaux de neurones profonds appliqués à la compréhension de la parole

Abstract : This thesis is part of the deep learning applied to spoken language understanding. Until now, this task was performed through a pipeline of components implementing, for example, a speech recognition system, then different natural language processing, before involving a language understanding system on enriched automatic transcriptions. Recently, work in the field of speech recognition has shown that it is possible to produce a sequence of words directly from the acoustic signal. Within the framework of this thesis, the aim is to exploit these advances and extend them to design a system composed of a single neural model fully optimized for the spoken language understanding task, from signal to concept. First, we present a state of the art describing the principles of deep learning, speech recognition, and speech understanding. Then, we describe the contributions made along three main axes. We propose a first system answering the problematic posed and apply it to a task of named entities recognition. Then, we propose a transfer learning strategy guided by a curriculum learning approach. This strategy is based on the generic knowledge learned to improve the performance of a neural system on a semantic concept extraction task. Then, we perform an analysis of the errors produced by our approach, while studying the functioning of the proposed neural architecture. Finally, we set up a confidence measure to evaluate the reliability of a hypothesis produced by our system.
Document type :
Complete list of metadata
Contributor : Abes Star :  Contact
Submitted on : Tuesday, March 23, 2021 - 3:08:07 PM
Last modification on : Wednesday, March 24, 2021 - 3:14:29 AM


Version validated by the jury (STAR)


  • HAL Id : tel-03177996, version 1


Antoine Caubriere. Du signal au concept : réseaux de neurones profonds appliqués à la compréhension de la parole. Informatique et langage [cs.CL]. Université du Maine, 2021. Français. ⟨NNT : 2021LEMA1001⟩. ⟨tel-03177996⟩



Record views


Files downloads