4 papers
Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding
Quanwei Tang, Dong Zhang, Shoushan Li +1
While long-form audio meeting understanding (LAMU) is garnering growing attention, task-specific question answering (QA) datasets remain scarce. Existing speech QA paradigms and st…
Relative Time Intervals Representation for Word-level Timestamping with Masked Training
Quanwei Tang, Zhiyu Tang, Xu Li +3
Although Speech Large Language Models (SpeechLLMs) excel at speech understanding and generation, their capacity for fine-grained, temporally aligned outputs remains underexplored.…
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…
A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment
Quanwei Tang, Sophia Yat Mei Lee, Junshuang Wu +4
Recent advancements in retrieval-augmented generation (RAG) have enhanced large language models in question answering by integrating external knowledge. However, challenges persist…