Switchcodec: Adaptive residual-expert sparse quantization for high-fidelity neural audio coding
This work addresses the challenge of high-fidelity audio coding for variable audio content, offering a novel method to enhance compression efficiency without retraining for multi-bitrate operation.
The paper tackled the problem of suboptimal fixed codebook usage in neural audio compression by proposing SwitchCodec, which uses adaptive residual-expert sparse quantization to improve compression efficiency, achieving superior performance in objective metrics and subjective listening tests compared to existing baselines.
Recent neural audio compression models often rely on residual vector quantization for high-fidelity coding, but using a fixed number of per-frame codebooks is suboptimal for the wide variability of audio content-especially for signals that are either very simple or highly complex. To address this limitation, we propose SwitchCodec, a neural audio codec based on Residual Experts Vector Quantization (REVQ). REVQ combines a shared quantizer with dynamically routed expert quantizers that are activated according to the input audio, decoupling bitrate from codebook capacity and improving compression efficiency. This design ensures full training and utilization of each quantizer. In addition, a variable-bitrate mechanism adjusts the number of active expert quantizers at inference, enabling multi-bitrate operation without retraining. Experiments demonstrate that SwitchCodec surpasses existing baselines on both objective metrics and subjective listening tests.