Cancan Li
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Sound×1AI×1Audio and Speech Processing×1
Frequent co-authors
Research Timeline
2026
From Voiceprints to User Entities: Online Speaker-Memory Construction for Multi-User Spoken Agents
This paper introduces EvoSpeakerMem, a training-free layer for personalized spoken agents, and LoCoMo-ID, a spoken-memory benchmark.
Highlighted terms show continued research focus across papers
Papers
cs.SDcs.AIeess.ASEmpiricalRecentOct 27, 2026
From Voiceprints to User Entities: Online Speaker-Memory Construction for Multi-User Spoken Agents
Yucong Zhang, Cancan Li, Bo Xiao, Ke Zeng +1 more
This paper introduces EvoSpeakerMem, a training-free layer for personalized spoken agents, and LoCoMo-ID, a spoken-memory benchmark.
View →