Cross-modal Audio-visual Co-learning for Text-independent Speaker Verification
Abstract
Visual speech (i.e., lip motion) is highly related to auditory speech due to the co-occurrence and synchronization in speech production. This paper investigates this correlation and proposes a cross-modal speech co-learning paradigm. The primary motivation of our cross-modal co-learning method is modeling one modality aided by exploiting knowledge from another modality. Specifically, two cross-modal boosters are introduced based on an audio-visual pseudo-siamese structure to learn the modality-transformed correlation. Inside each booster, a max-feature-map embedded Transformer variant is proposed for modality alignment and enhanced feature generation. The network is co-learned both from scratch and with pretrained models. Experimental results on the LRSLip3, GridLip, LomGridLip, and VoxLip datasets demonstrate that our proposed method achieves 60% and 20% average relative performance improvement over independently trained audio-only/visual-only and baseline fusion systems, respectively.
Cite
@article{arxiv.2302.11254,
title = {Cross-modal Audio-visual Co-learning for Text-independent Speaker Verification},
author = {Meng Liu and Kong Aik Lee and Longbiao Wang and Hanyi Zhang and Chang Zeng and Jianwu Dang},
journal= {arXiv preprint arXiv:2302.11254},
year = {2023}
}