AI RESEARCH

UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception

arXiv CS.CL

ArXi:2605.31521v1 Announce Type: new Semantic speech tokenizers have become a widely used interface for Audio-LLMs, owing to their compact single-codebook design and strong linguistic alignment. However, their focus on linguistic abstraction induces acoustic blindness, limiting their applicability beyond speech-centric tasks. We propose UniAudio-Token, a framework that empowers semantic tokenizers with general audio perception without compromising speech ability.