Saved in:
Bibliographic Details
Main Authors: Chen, Yushen, Hu, Kai, Zhou, Long, Feng, Shulin, Yang, Xusheng, Chen, Hangting, Chen, Xie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.21968
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916971506827264
author Chen, Yushen
Hu, Kai
Zhou, Long
Feng, Shulin
Yang, Xusheng
Chen, Hangting
Chen, Xie
author_facet Chen, Yushen
Hu, Kai
Zhou, Long
Feng, Shulin
Yang, Xusheng
Chen, Hangting
Chen, Xie
contents We propose AUV, a unified neural audio codec with a single codebook, which enables a favourable reconstruction of speech and further extends to general audio, including vocal, music, and sound. AUV is capable of tackling any 16 kHz mixed-domain audio segment at bit rates around 700 bps. To accomplish this, we guide the matryoshka codebook with nested domain-specific partitions, assigned with corresponding teacher models to perform distillation, all in a single-stage training. A conformer-style encoder-decoder architecture with STFT features as audio representation is employed, yielding better audio quality. Comprehensive evaluations demonstrate that AUV exhibits comparable audio reconstruction ability to state-of-the-art domain-specific single-layer quantizer codecs, showcasing the potential of audio universal vector quantization with a single codebook. The pre-trained model and demo samples are available at https://swivid.github.io/AUV/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21968
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AUV: Teaching Audio Universal Vector Quantization with Single Nested Codebook
Chen, Yushen
Hu, Kai
Zhou, Long
Feng, Shulin
Yang, Xusheng
Chen, Hangting
Chen, Xie
Audio and Speech Processing
Sound
We propose AUV, a unified neural audio codec with a single codebook, which enables a favourable reconstruction of speech and further extends to general audio, including vocal, music, and sound. AUV is capable of tackling any 16 kHz mixed-domain audio segment at bit rates around 700 bps. To accomplish this, we guide the matryoshka codebook with nested domain-specific partitions, assigned with corresponding teacher models to perform distillation, all in a single-stage training. A conformer-style encoder-decoder architecture with STFT features as audio representation is employed, yielding better audio quality. Comprehensive evaluations demonstrate that AUV exhibits comparable audio reconstruction ability to state-of-the-art domain-specific single-layer quantizer codecs, showcasing the potential of audio universal vector quantization with a single codebook. The pre-trained model and demo samples are available at https://swivid.github.io/AUV/.
title AUV: Teaching Audio Universal Vector Quantization with Single Nested Codebook
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2509.21968