Lscodec: Low-bitrate And Speaker-decoupled Discrete Speech Codec

Abstract

Although discrete speech tokens have exhibited strong potential for language model-based speech generation, their high bitrates and redundant timbre information restrict the development of such models. In this work, we propose LSCodec, a discrete speech codec that has both low bitrate and speaker decoupling ability. LSCodec adopts a multi-stage unsupervised training framework with a speaker perturbation technique. A continuous information bottleneck is first established, followed by vector quantization that produces a discrete speaker-decoupled space. A discrete token vocoder finally refines acoustic details from LSCodec. By reconstruction evaluations, LSCodec demonstrates superior intelligibility and audio quality with only a single codebook and smaller vocabulary size than baselines. Voice conversion and speaker probing experiments prove the excellent speaker disentanglement of LSCodec, and ablation study verifies the effectiveness of the proposed training framework.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyguo2024lscodec

Related papers

• Single-codec: Single-codebook Speech Codec Towards High-performance Speech Generation (2024)9.23
• Disco-speech: Controllable Zero-shot Speech Generation With A Disentangled Speech Codec (2025)0.00
• Msr-codec: A Low-bitrate Multi-stream Residual Codec For High-fidelity Speech Generation With Information Disentanglement (2025)2.35
• Low Frame-rate Speech Codec: A Codec Designed For Fast High-quality Speech LLM Training And Inference (2024)5.24
• Socodec: A Semantic-ordered Multi-stream Speech Codec For Efficient Language Model Based Text-to-speech Synthesis (2024)6.34
• Freecodec: A Disentangled Neural Speech Codec With Fewer Tokens (2024)4.52
• Semanticodec: An Ultra Low Bitrate Semantic Audio Codec For General Sound (2024)10.97
• Language-codec: Bridging Discrete Codec Representations And Speech Language Models (2024)4.64