E2E-SINCNET: TOWARD FULLY END-TO-END SPEECH RECOGNITION - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

E2E-SINCNET: TOWARD FULLY END-TO-END SPEECH RECOGNITION

Mohamed Morchid
Georges Linares

Résumé

Modern end-to-end (E2E) Automatic Speech Recognition (ASR) systems rely on Deep Neural Networks (DNN) that are mostly trained on handcrafted and pre-computed acoustic features such as Mel-filter-banks or Mel-frequency cepstral coefficients. Nonetheless , and despite worse performances, E2E ASR models processing raw waveforms are an active research field due to the lossless nature of the input signal. In this paper, we propose the E2E-SincNet, a novel fully E2E ASR model that goes from the raw waveform to the text transcripts by merging two recent and powerful paradigms: SincNet and the joint CTC-attention training scheme. The conducted experiments on two different speech recognition tasks show that our approach outperforms previously investigated E2E systems relying either on the raw waveform or pre-computed acoustic features, with a reported top-of-the-line Word Error Rate (WER) of 4.7% on the Wall Street Journal (WSJ) dataset.
Fichier principal
Vignette du fichier
ICASSP_2020___E2E_SINCNET-5.pdf (385.81 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02484600 , version 1 (19-02-2020)

Identifiants

  • HAL Id : hal-02484600 , version 1

Citer

Titouan Parcollet, Mohamed Morchid, Georges Linares. E2E-SINCNET: TOWARD FULLY END-TO-END SPEECH RECOGNITION. ICASSP, May 2020, Barcelone, Spain. ⟨hal-02484600⟩

Collections

UNIV-AVIGNON LIA
276 Consultations
801 Téléchargements

Partager

Gmail Facebook X LinkedIn More