English

Cross-modal Audio-visual Co-learning for Text-independent Speaker Verification

Sound 2023-02-23 v1 Computer Vision and Pattern Recognition Machine Learning Audio and Speech Processing Image and Video Processing

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.

Keywords

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}
}
R2 v1 2026-06-28T08:46:38.278Z