Switchcodec: Adaptive residual-expert sparse quantization for high-fidelity neural audio coding
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V
W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and strongly timestep-dependent activation dis…
SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference
Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern accelerators, yet combining them for LLM activation compression remains challenging: activations contain input-dependent ou…
Video GenerationRQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression
Vector quantization is a fundamental tool for compressing high-dimensional embeddings, yet existing multi-codebook methods rely on static codebooks that limit expressiveness under heterogeneous data geometry. While recen…
HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression
Post-training quantization is essential for deploying Large Language Models (LLMs) on resource-constrained devices. However, standard integer quantization (e.g., INT4) fundamentally degrades performance by imposing a uni…
MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization
Recently, residual reconstruction-based model quantization methods have achieved promising performance in low-bit post-training quantization (PTQ) by introducing cross-layer residuals to reduce error accumulated from pre…