SpeechBrain: A General-Purpose Speech Toolkit - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

SpeechBrain: A General-Purpose Speech Toolkit

Aku Rouhe
  • Fonction : Auteur
Szu-Wei Fu
  • Fonction : Auteur
Chien-Feng Liao
  • Fonction : Auteur
Elena Rastorgueva
  • Fonction : Auteur

Résumé

SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to facilitate the research and development of neural speech processing technologies by being simple, flexible, user-friendly, and well-documented. This paper describes the core architecture designed to support several tasks of common interest, allowing users to naturally conceive, compare and share novel speech processing pipelines. SpeechBrain achieves competitive or state-of-the-art performance in a wide range of speech benchmarks. It also provides training recipes, pretrained models, and inference scripts for popular speech datasets, as well as tutorials which allow anyone with basic Python proficiency to familiarize themselves with speech technologies.

Dates et versions

hal-03601303 , version 1 (08-03-2022)

Identifiants

Citer

Titouan Parcollet, Mirco Ravanelli, Peter Plantinga, Aku Rouhe, Samuele Cornell, et al.. SpeechBrain: A General-Purpose Speech Toolkit. 2022. ⟨hal-03601303⟩
449 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More