aiqbench analysis
EntangleCodec introduces a unified discrete audio tokenizer that resolves the traditional trade-off between acoustic fidelity and semantic richness by aligning representations with captions rather than ASR transcripts. This approach enables a compact 0.6B parameter model to outperform specialized 13B parameter baselines on audio understanding benchmarks, demonstrating that representation quality is as critical as model scale for Audio Language Models. The method supports a unified framework for both speech and music tasks, offering a significant efficiency gain for developers building next-generation audio generation and understanding systems.
EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement
arXiv:2606.02739v1 Announce Type: cross 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.
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 this https URL.
Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
arXiv:2606.02739 [cs.SD]
(or arXiv:2606.02739v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2606.02739 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 302 words
Related coverage
EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement
arXiv · Sep 5, 2026
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling
arXiv · Aug 6, 2026
LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
arXiv · Jun 17, 2026
LoSATok: Low-Dimensional Semantic-Acoustic Tokenizer for Cross-Domain Audio Understanding and Generation
arXiv · Sep 16, 2026