Deep neural networks for automatic speech processing: a survey from large corpora to limited data - Archive ouverte HAL Access content directly
Journal Articles EURASIP Journal on Audio, Speech, and Music Processing Year : 2022

Deep neural networks for automatic speech processing: a survey from large corpora to limited data

Abstract

Most state-of-the-art speech systems use deep neural networks (DNNs). These systems require a large amount of data to be learned. Hence, training state-of-the-art frameworks on under-resourced speech challenges are difficult tasks. As an example, a challenge could be the limited amount of data to model impaired speech. Furthermore, acquiring more data and/or expertise is time-consuming and expensive. In this paper, we focus on the following speech processing tasks: automatic speech recognition, speaker identification, and emotion recognition. To assess the problem of limited data, we firstly investigate state-of-the-art automatic speech recognition systems, as this is the hardest task (due to the wide variability in each language). Next, we provide an overview of techniques and tasks requiring fewer data. In the last section, we investigate few-shot techniques by interpreting under-resourced speech as a few-shot problem. In that sense, we propose an overview of few-shot techniques and the possibility of using such techniques for the speech problems addressed in this survey. It is true that the reviewed techniques are not well adapted for large datasets. Nevertheless, some promising results from the literature encourage the usage of such techniques for speech processing.
Fichier principal
Vignette du fichier
e55778f3-dc17-4859-96ae-ce82ce871671.pdf (1.78 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03755976 , version 1 (22-08-2022)

Licence

Identifiers

Cite

Vincent Roger, Jérôme Farinas, Julien Pinquier. Deep neural networks for automatic speech processing: a survey from large corpora to limited data. EURASIP Journal on Audio, Speech, and Music Processing, 2022, article 19, pp.1-15. ⟨10.1186/s13636-022-00251-w⟩. ⟨hal-03755976⟩
72 View
39 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More