Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modelling techniques to audio data. However, traditional codecs often operate at high bitrates or within narrow domains such as speech and lack the semantic clues required for efficient language modelling. Addressing these challenges, we introduce SemantiCodec, a novel codec designed to compress audio into fewer than a hundred tokens per second across diverse audio types, including speech, general audio, and music, without compromising quality. SemantiCodec features a dual-encoder architecture: a semantic encoder using a self-supervised AudioMAE, discretized using k-means clustering on extensive audio data, and an acoustic encoder to capture the remaining details. The semantic and acoustic encoder outputs are used to reconstruct audio via a diffusion-model-based decoder. SemantiCodec is presented in three variants with token rates of 25, 50, and 100 per second, supporting a range of ultra-low bit rates between 0.31 kbps and 1.43 kbps. Experimental results demonstrate that SemantiCodec significantly outperforms the state-of-the-art Descript codec on reconstruction quality. Our results also suggest that SemantiCodec contains significantly richer semantic information than all evaluated audio codecs, even at significantly lower bitrates. Our code and demos are available at https://haoheliu.github.io/SemantiCodec/.

翻译：大型语言模型（LLMs）通过将音频转换为离散令牌的音频编解码器，显著推动了音频处理的发展，使得语言建模技术得以应用于音频数据。然而，传统编解码器往往以高比特率运行或局限于语音等狭窄领域，且缺乏高效语言建模所需的语义线索。针对这些挑战，我们提出SemantiCodec——一种新颖的编解码器，旨在将多种音频类型（包括语音、通用音频和音乐）压缩至每秒不足一百个令牌，同时不牺牲质量。SemantiCodec采用双编码器架构：语义编码器使用基于自监督AudioMAE模型并通过k-means聚类在大量音频数据上离散化处理，声学编码器则用于捕捉剩余细节。语义和声学编码器的输出通过基于扩散模型的解码器重建音频。SemantiCodec提供三种变体，令牌速率分别为每秒25、50和100，支持0.31 kbps至1.43 kbps的超低比特率范围。实验结果表明，SemantiCodec在重建质量上显著优于最先进的Descript编解码器。我们的结果还表明，即使比特率显著降低，SemantiCodec仍包含比所有评估的音频编解码器更丰富的语义信息。我们的代码和演示可在https://haoheliu.github.io/SemantiCodec/获取。