Communication Dans Un Congrès Année : 2026

QINCODEC: Neural Audio Compression with Implicit Neural Codebooks

Résumé

Neural audio codecs, neural networks which compress a waveform into discrete tokens, play a crucial role in the recent development of audio generative models. State-of-the-art codecs rely on the end-to-end training of an autoencoder and a quantization bottleneck. However, this approach restricts the choice of the quantization methods as it requires to define how gradients propagate through the quantizer and how to update the quantization parameters online. In this work, we revisit the common practice of joint training and propose to quantize the latent representations of a pre-trained autoencoder offline, followed by an optional finetuning of the decoder to mitigate degradation from quantization. This strategy allows to consider any off-the-shelf quantizer, especially state-of-the-art trainable quantizers with implicit neural codebooks such as QINCO2. We demonstrate that with the latter, our proposed codec termed QINCODEC, is competitive with baseline codecs while being notably simpler to train. Finally, our approach provides a general framework that amortizes the cost of autoencoder pretraining, and enables more flexible codec design.

Fichier principal
Vignette du fichier
Qincodec Neural Audio Compression with Neural Implicit Codebooks.pdf (552.05 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04995360 , version 1 (18-03-2025)

Licence

Identifiants

  • HAL Id : hal-04995360 , version 1

Citer

Zineb Lahrichi, Gaëtan Hadjeres, Gael Richard, Geoffroy Peeters. QINCODEC: Neural Audio Compression with Implicit Neural Codebooks. 33rd European Signal Processing Conference (EUSIPCO 2025), Sep 2025, Palermo, Italy. ⟨hal-04995360⟩
187 Consultations
322 Téléchargements

Partager

  • More