HiFi-Codec：用于高保真音频编解码器的分组残差向量量化
HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec
AI总结：
本文提出分组残差向量量化（GRVQ）技术，构建仅需4个码本的高保真音频编解码器HiFi-Codec，在重建性能上优于Encodec，并开源AcademiCodec工具包以促进研究。
摘要：
音频编解码器模型作为将音频压缩为离散表示的关键技术，被广泛应用于音频通信。如今，音频编解码器模型越来越多地被用作生成领域的中间表示。例如，AudioLM 是一种音频生成模型，它使用 SoundStream 的离散表示作为训练目标，而 VALL-E 则采用 Encodec 模型作为中间特征来辅助 TTS 任务。尽管这些模型很有用，但仍存在两个挑战：（1）由于缺乏公开可用的训练流程以及需要大规模数据和 GPU，训练这些音频编解码器模型可能很困难；（2）要实现良好的重建性能需要大量码本，这增加了生成模型的负担。在本研究中，我们提出了一种分组残差向量量化（GRVQ）技术，并利用它开发了一种新颖的高保真音频编解码器模型 HiFi-Codec，该模型仅需 4 个码本。我们使用公开可用的 TTS 数据（如 LibriTTS、VCTK、AISHELL 等）训练所有模型，总时长超过 1000 小时，使用 8 块 GPU。我们的实验结果表明，尽管 HiFi-Codec 仅需 4 个码本，但其重建性能优于 Encodec。为了促进音频编解码器和生成领域的研究，我们推出了 AcademiCodec，这是第一个开源音频编解码器工具包，提供 Encodec、SoundStream 和 HiFi-Codec 的训练代码和预训练模型。代码和预训练模型可在 https://github.com/yangdongchao/AcademiCodec 上找到。
英文摘要：
Audio codec models are widely used in audio communication as a crucial technique for compressing audio into discrete representations. Nowadays, audio codec models are increasingly utilized in generation fields as intermediate representations. For instance, AudioLM is an audio generation model that uses the discrete representation of SoundStream as a training target, while VALL-E employs the Encodec model as an intermediate feature to aid TTS tasks. Despite their usefulness, two challenges persist: (1) training these audio codec models can be difficult due to the lack of publicly available training processes and the need for large-scale data and GPUs; (2) achieving good reconstruction performance requires many codebooks, which increases the burden on generation models. In this study, we propose a group-residual vector quantization (GRVQ) technique and use it to develop a novel \textbf{Hi}gh \textbf{Fi}delity Audio Codec model, HiFi-Codec, which only requires 4 codebooks. We train all the models using publicly available TTS data such as LibriTTS, VCTK, AISHELL, and more, with a total duration of over 1000 hours, using 8 GPUs. Our experimental results show that HiFi-Codec outperforms Encodec in terms of reconstruction performance despite requiring only 4 codebooks. To facilitate research in audio codec and generation, we introduce AcademiCodec, the first open-source audio codec toolkit that offers training codes and pre-trained models for Encodec, SoundStream, and HiFi-Codec. Code and pre-trained model can be found on: \href{https://github.com/yangdongchao/AcademiCodec}{https://github.com/yangdongchao/AcademiCodec}
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
