Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations 事件

Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations arXiv:2606.06740v1 Announce Type: cross Abstract: Discrete speech units obtained via k-means clustering of self supervised embeddings entangle phonetic, speaker, and language information, causing speaker mixing and cross-lingual interference in multilingual multi-speaker speech generation. Despite growing use in Audio LLMs and speech to speech systems, unit vocoders remain underexplored. We analyz