Communication Dans Un Congrès Année : 2024

Speech quality evaluation of neural audio codecs

Evaluation de la qualité de la parole générée par autoencodeurs neuronaux

Résumé

This paper presents speech quality results to characterize the state of the art and technological advance of recent neural audio codecs targeting low bitrates. Audio quality was evaluated in one clean speech experiment (in French). Degradation Mean Opinion Score (DMOS) results are reported and discussed for neural audio codecs (LPCNet, Lyra V2, EnCodec, AudioCraft, AudioDec, Descript Audio Codec) -traditional codecs (Opus, EVS) are also included as performance yardsticks. We also discuss observed codec complexity to complement subjective test results.

Fichier principal
Vignette du fichier
InterSpeech_2024_final_version.pdf (222.69 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04921755 , version 1 (30-01-2025)

Licence

Identifiants

  • HAL Id : hal-04921755 , version 1

Citer

Thomas Muller, Stéphane Ragot, Laetitia Gros, Pierrick Philippe, Pascal Scalart. Speech quality evaluation of neural audio codecs. INTERSPEECH, Sep 2024, Kos Island, Greece. ⟨hal-04921755⟩
220 Consultations
574 Téléchargements

Partager

  • More