Papers
arxiv:2510.16841

SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization

Published on Oct 19
Authors:
,
,
,
,
,
,
,
,
,
,

Abstract

SAC, a neural speech codec with dual-stream quantization, enhances both speech reconstruction quality and semantic representation, outperforming existing codecs and SSL embeddings.

AI-generated summary

Speech codecs that convert continuous speech signals into discrete tokens have become essential for speech language models (SLMs). However, existing codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks. In this work, we propose SAC, a neural speech codec with semantic-acoustic dual-stream quantization. By disentangling semantic and acoustic modeling into two dedicated streams, SAC enables each to be optimized for its respective role. Comprehensive evaluations show that SAC achieves strong reconstruction performance across diverse bitrates under both clean and noisy conditions, with particularly high scores on UTMOS and WER, demonstrating superior perceptual quality and intelligibility. Moreover, SAC substantially outperforms state-of-the-art codecs in semantic representation, achieving a level comparable to that of self-supervised learning (SSL) continuous embeddings. Finally, our analysis of speech disentanglement highlights the effectiveness of the dual-stream design, offering new potential for controllable speech applications.

Community

Sign up or log in to comment

Models citing this paper 2

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2510.16841 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2510.16841 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.