3 papers
eess.AS2026
MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
Junjie Li, Jing Peng, Yangui Fang +2
LLM-based ASR overcomes multilingual data scarcity by projecting speech representations into the LLM space to leverage its robust semantic and reasoning capabilities. However, whil…
eess.AS2026
TASU: Text-Only Alignment for Speech Understanding
Jing Peng, Yi Yang, Xu Li +5
Recent advances in Speech Large Language Models (Speech LLMs) have paved the way for unified architectures across diverse speech understanding tasks. However, prevailing alignment…
cs.CL2025
EM2LDL: A Multilingual Speech Corpus for Mixed Emotion Recognition through Label Distribution Learning
Xingfeng Li, Xiaohan Shi, Junjie Li +4
This study introduces EM2LDL, a novel multilingual speech corpus designed to advance mixed emotion recognition through label distribution learning. Addressing the limitations of pr…