Showing 2026Show all
2 papers · 1 filter
cs.SD2026
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…
cs.AI2026
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.…