Communication Dans Un Congrès Année : 2025

Bringing Interpretability to Neural Audio Codecs

Résumé

The advent of neural audio codecs has increased in popularity due to their potential for efficiently modeling audio with transformers. Such advanced codecs represent audio from a highly continuous waveform to low-sampled discrete units. In contrast to semantic units, acoustic units may lack interpretability because their training objectives primarily focus on reconstruction performance. This paper proposes a two-step approach to explore the encoding of speech information within the codec tokens. The primary goal of the analysis stage is to gain deeper insight into how speech attributes such as content, identity, and pitch are encoded. The synthesis stage then trains an AnCoGen network for post-hoc explanation of codecs to extract speech attributes from the respective tokens directly.

Fichier principal
Vignette du fichier
Bringing_Interpretability_to_Neural_Audio_Codecs.pdf (1.86 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05098131 , version 1 (05-06-2025)

Licence

Identifiants

Citer

Samir Sadok, Julien Hauret, Eric Bavu. Bringing Interpretability to Neural Audio Codecs. Interspeech 2025 - 26th edition of the Interspeech Conference, ISCA - International Speech Communication Association, Aug 2025, Rotterdam, Netherlands. pp.1-5. ⟨hal-05098131⟩
482 Consultations
394 Téléchargements

Altmetric

Partager

  • More