5 papers
Effective User-defined Keyword Spotting with Dual-stage Matching, Multi-modal Enrollment, and Continual Adaptation
Zhiqi Ai, Han Cheng, Shiyi Mu +3
User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable…
From Stateless to Situated: Building a Psychological World for LLM-Based Agents
Boning Zhao, Yutong Hu, Xinnuo Li
In psychological support and emotional companionship scenarios, the core limitation of large language models (LLMs) lies not merely in response quality, but in their reliance on lo…
VoxAging: Continuously Tracking Speaker Aging with a Large-Scale Longitudinal Dataset in English and Mandarin
Zhiqi Ai, Meixuan Bao, Zhiyong Chen +3
The performance of speaker verification systems is adversely affected by speaker aging. However, due to challenges in data collection, particularly the lack of sustained and large-…
Enhancing Open-Set Speaker Identification through Rapid Tuning with Speaker Reciprocal Points and Negative Sample
Zhiyong Chen, Zhiqi Ai, Xinnuo Li +1
This paper introduces a novel framework for open-set speaker identification in household environments, playing a crucial role in facilitating seamless human-computer interactions.…
StyleFusion TTS: Multimodal Style-control and Enhanced Feature Fusion for Zero-shot Text-to-speech Synthesis
Zhiyong Chen, Xinnuo Li, Zhiqi Ai +1
We introduce StyleFusion-TTS, a prompt and/or audio referenced, style and speaker-controllable, zero-shot text-to-speech (TTS) synthesis system designed to enhance the editability…