1. Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization
- Author
-
Tao, Ruijie, Shi, Zhan, Jiang, Yidi, Truong, Duc-Tuan, Chng, Eng-Siong, Alioto, Massimo, and Li, Haizhou
- Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing - Abstract
The human brain has the capability to associate the unknown person's voice and face by leveraging their general relationship, referred to as ``cross-modal speaker verification''. This task poses significant challenges due to the complex relationship between the modalities. In this paper, we propose a ``Multi-stage Face-voice Association Learning with Keynote Speaker Diarization''~(MFV-KSD) framework. MFV-KSD contains a keynote speaker diarization front-end to effectively address the noisy speech inputs issue. To balance and enhance the intra-modal feature learning and inter-modal correlation understanding, MFV-KSD utilizes a novel three-stage training strategy. Our experimental results demonstrated robust performance, achieving the first rank in the 2024 Face-voice Association in Multilingual Environments (FAME) challenge with an overall Equal Error Rate (EER) of 19.9%. Details can be found in https://github.com/TaoRuijie/MFV-KSD.
- Published
- 2024