Preprint
Oct 2026
Phonology-Aware Speaker Extraction Frontend for Audio LLMs
Target speaker extraction (TSE) is a key frontend for enabling audio large language models (LLMs) to recognize and understand a designated speaker in overlapping speech. However, multilingual mixtures exhibit heterogeneous extraction demands, causing fixed-depth systems to either under-process challenging inputs or was...
Yan-Xiang Chen, Hao-Yuan Deng, Jin-Yu Wang et al.
· 0 citations