The paper proposes MindDiffuser, a two-stage framework that significantly improves image reconstruction from brain activity by combining semantic guidance from text-to-image models with structural ref…

ImmersiveTTS is an environment-aware text-to-speech model that generates natural speech seamlessly integrated within environmental contexts by explicitly modeling cross-modal interactions, achieving s…

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages…

The paper introduces PlanAudio, a unified LLM-based framework that directly synthesizes natural, composite audio containing speech and sounds from unconstrained free-form text prompts, outperforming e…

UniAudio-Token is a framework that enhances existing semantic speech tokenizers with general audio perception, allowing them to handle diverse audio types while maintaining high-fidelity speech capabi…