{"ID":3006012,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-04T17:52:58.968687531Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.02739","arxiv_id":"2606.02739","title":"EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement","abstract":"Audio tokenizers serve as the discrete interface between continuous audio and Audio Language Models (ALMs), but existing tokenizers often struggle to support both understanding and generation. Reconstruction-oriented codecs preserve acoustic fidelity but lack rich semantics, while semantic-aware tokenizers typically rely on separate semantic and acoustic streams, introducing redundancy or misalignment. We propose \\textbf{EntangleCodec}, a unified discrete audio tokenizer that learns caption-aligned semantic-acoustic representations before quantization. By aligning audio with rich captions rather than ASR transcripts, EntangleCodec captures linguistic content, speaker identity, emotion, prosody, and acoustic scenes within a compact token stream. A flow-matching diffusion decoder further enables high-quality reconstruction across speech, music, and general audio. EntangleCodec achieves reconstruction quality competitive with specialized codecs, outperforms all codec-based baselines on audio understanding by up to \\textbf{+7.4\\%} on MMAR, and supports both TTS and TTA generation in a unified framework. Furthermore, EntangleCodec-based audio language models demonstrate strong scaling behavior: even at \\textit{0.6B} parameters, the model surpasses specialized continuous-representation LLMs with over \\textit{13B} parameters across three benchmarks using \\textbf{22$\\times$} fewer parameters; scaling to \\textit{8B} further establishes new state-of-the-art results on MMAR, highlighting that representation quality is as critical as model scale in audio language modeling. Code and model weights are available at https://github.com/luckyerr/EntangleCodec.","short_abstract":"Audio tokenizers serve as the discrete interface between continuous audio and Audio Language Models (ALMs), but existing tokenizers often struggle to support both understanding and generation. Reconstruction-oriented codecs preserve acoustic fidelity but lack rich semantics, while semantic-aware tokenizers typically re...","url_abs":"https://arxiv.org/abs/2606.02739","url_pdf":"https://arxiv.org/pdf/2606.02739v1","authors":"[\"Hui Li\",\"Yangfan Gao\",\"Junlin Shang\",\"Changhao Jiang\",\"Tao Gui\",\"Qi Zhang\",\"Xuanjing Huang\"]","published":"2026-06-01T18:05:18Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\",\"eess.AS\"]","methods":"[\"Diffusion Model\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":612744,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-03T03:09:48.883664427Z","DeletedAt":null,"paper_id":3006012,"paper_url":"https://arxiv.org/abs/2606.02739","paper_title":"EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement","repo_url":"https://github.com/luckyerr/EntangleCodec","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}