HH-Codec: High Compression High-fidelity Discrete Neural Codec for Spoken Language Modeling
By: Rongkun Xue , Yazhe Niu , Shuai Hu and more
Potential Business Impact:
Makes voices sound clear with less data.
Discrete speech tokenization is a fundamental component in speech codecs. However, in large-scale speech-to-speech systems, the complexity of parallel streams from multiple quantizers and the computational cost of high-time-dimensional codecs pose significant challenges. In this paper, we introduce HH-Codec, a neural codec that achieves extreme compression at 24 tokens per second for 24 kHz audio while relying on single-quantizer inference. Our approach involves a carefully designed Vector Quantization space for Spoken Language Modeling, optimizing compression efficiency while minimizing information loss. Building on this, we propose an asymmetric encoder-decoder architecture (Audio-VQ-Mel-Audio) that leverages dual supervision and progressive training to enhance reconstruction stability and fidelity. HH-Codec achieves state-of-the-art performance in speech reconstruction with an ultra-low bandwidth of 0.3 kbps. We further evaluate its effectiveness in codebook utilization and generative model adaptation, with extensive ablations validating the necessity of each module. HH-Codec is available at https://github.com/opendilab/HH-Codec.
Similar Papers
U-Codec: Ultra Low Frame-rate Neural Speech Codec for Fast High-fidelity Speech Generation
Sound
Makes voices sound real with less data.
MBCodec:Thorough disentangle for high-fidelity audio compression
Sound
Makes computer voices sound more real.
MelCap: A Unified Single-Codebook Neural Codec for High-Fidelity Audio Compression
Sound
Makes music and speech sound clear with less data.