轻量级音频编解码器L3AC，用单量化器实现高保真压缩。
L3AC: Towards a Lightweight and Lossless Audio Codec
- 采用单量化器和高效网络结构，降低模型复杂度。
- 在多个数据集上重建质量超越或媲美领先编码器。
- 计算开销减少一个数量级，适合生成任务下游应用。
神经音频编解码器近年来因其能够压缩高保真音频并生成离散标记以支持生成建模而受到关注。然而，现有主流方法通常依赖资源密集型模型和复杂的多量化器架构，限制了其在实际应用中的可行性。本文提出L3AC，一种轻量级神经音频编解码器，通过单一量化器和高效架构解决上述问题。为在保持重建保真度的同时最小化模型复杂度，L3AC探索了简化的卷积网络与局部Transformer模块，并引入TConv——一种新结构，用于捕捉多时间尺度上的声学变化。尽管设计紧凑，广泛实验表明，L3AC在多个数据集上达到或超过领先编码器的重建质量，同时将计算开销降低一个数量级。单量化器设计也进一步提升了其在下游任务中的适应性。源代码已公开于 https://github.com/zhai-lw/L3AC。
原文摘要 · Abstract (English)
Neural audio codecs have recently gained traction for their ability to compress high-fidelity audio and provide discrete tokens for generative modeling. However, leading approaches often rely on resource-intensive models and complex multi-quantizer architectures, limiting their practicality in real-world applications. In this work, we introduce L3AC, a lightweight neural audio codec that addresses these challenges by leveraging a single quantizer and a highly efficient architecture. To enhance reconstruction fidelity while minimizing model complexity, L3AC explores streamlined convolutional networks and local Transformer modules, alongside TConv--a novel structure designed to capture acoustic variations across multiple temporal scales. Despite its compact design, extensive experiments across diverse datasets demonstrate that L3AC matches or exceeds the reconstruction quality of leading codecs while reducing computational overhead by an order of magnitude. The single-quantizer design further enhances its adaptability for downstream tasks. The source code is publicly available at https://github.com/zhai-lw/L3AC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。