2 papers
cs.SD2026
MOSS-Audio Technical Report
Chen Yang, Chufan Yu, Hanfu Chen +27
MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped trans…
cs.CL2025
BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR
Guodong Ma, Wenxuan Wang, Lifeng Zhou +3
Recently, the Mixture of Expert (MoE) architecture, such as LR-MoE, is often used to alleviate the impact of language confusion on the multilingual ASR (MASR) task. However, it sti…