Role of non-linear data processing on speech recognition task in the framework of reservoir computing - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Article Dans Une Revue Scientific Reports Année : 2020

Role of non-linear data processing on speech recognition task in the framework of reservoir computing

Résumé

the reservoir computing neural network architecture is widely used to test hardware systems for neuromorphic computing. one of the preferred tasks for bench-marking such devices is automatic speech recognition. this task requires acoustic transformations from sound waveforms with varying amplitudes to frequency domain maps that can be seen as feature extraction techniques. Depending on the conversion method, these transformations sometimes obscure the contribution of the neuromorphic hardware to the overall speech recognition performance. Here, we quantify and separate the contributions of the acoustic transformations and the neuromorphic hardware to the speech recognition success rate. We show that the non-linearity in the acoustic transformation plays a critical role in feature extraction. We compute the gain in word success rate provided by a reservoir computing device compared to the acoustic transformation only, and show that it is an appropriate benchmark for comparing different hardware. Finally, we experimentally and numerically quantify the impact of the different acoustic transformations for neuromorphic hardware based on magnetic nano-oscillators.
Fichier principal
Vignette du fichier
s41598-019-56991-x.pdf (1.55 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03041228 , version 1 (04-12-2020)

Identifiants

Citer

Flavio Abreu Araujo, Mathieu Riou, Jacob Torrejon, Sumito Tsunegi, Damien Querlioz, et al.. Role of non-linear data processing on speech recognition task in the framework of reservoir computing. Scientific Reports, 2020, 10 (1), ⟨10.1038/s41598-019-56991-x⟩. ⟨hal-03041228⟩
21 Consultations
35 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More