“SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound”, 2024-04-30 ():
Large language models (LLMs) have advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling 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 modeling.
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 3 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 outperforms the state-of-the-art Descript codec on reconstruction quality. Our results also suggest that SemantiCodec contains richer semantic information than all evaluated audio codecs, even at lower bitrates.
Our code and demos are available at https://haoheliu.github.io/SemantiCodec/.