Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization
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.
Keywords
Cite
@article{arxiv.2407.17902,
title = {Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization},
author = {Ruijie Tao and Zhan Shi and Yidi Jiang and Duc-Tuan Truong and Eng-Siong Chng and Massimo Alioto and Haizhou Li},
journal= {arXiv preprint arXiv:2407.17902},
year = {2024}
}