Variable Bitrate Residual Vector Quantization For Audio Coding

Abstract

Recent state-of-the-art neural audio compression models have progressively adopted residual vector quantization (RVQ). Despite this success, these models employ a fixed number of codebooks per frame, which can be suboptimal in terms of rate-distortion tradeoff, particularly in scenarios with simple input audio, such as silence. To address this limitation, we propose variable bitrate RVQ (VRVQ) for audio codecs, which allows for more efficient coding by adapting the number of codebooks used per frame. Furthermore, we propose a gradient estimation method for the non-differentiable masking operation that transforms from the importance map to the binary importance mask, improving model training via a straight-through estimator. We demonstrate that the proposed training framework achieves superior results compared to the baseline method and shows further improvement when applied to the current state-of-the-art codec.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keychae2024variable

Related papers

• ERVQ: Enhanced Residual Vector Quantization With Intra-and-inter-codebook Optimization For Neural Audio Codecs (2024)6.34
• NDVQ: Robust Neural Audio Codec With Normal Distribution-based Vector Quantization (2024)0.00
• Hifi-codec: Group-residual Vector Quantization For High Fidelity Audio Codec (2023)0.00
• Neural Speech Coding For Real-time Communications Using Constant Bitrate Scalar Quantization (2024)0.00
• CQNV: A Combination Of Coarsely Quantized Bitstream And Neural Vocoder For Low Rate Speech Coding (2023)6.34
• Enhancing Into The Codec: Noise Robust Speech Coding With Vector-quantized Autoencoders (2021)10.21
• Optimizing Neural Speech Codec For Low-bitrate Compression Via Multi-scale Encoding (2024)0.00
• Efficient And Scalable Neural Residual Waveform Coding With Collaborative Quantization (2020)8.60