English

USEV: Universal Speaker Extraction with Visual Cue

Audio and Speech Processing 2022-09-01 v2 Sound

Abstract

A speaker extraction algorithm seeks to extract the target speaker's speech from a multi-talker speech mixture. The prior studies focus mostly on speaker extraction from a highly overlapped multi-talker speech mixture. However, the target-interference speaker overlapping ratios could vary over a wide range from 0% to 100% in natural speech communication, furthermore, the target speaker could be absent in the speech mixture, the speech mixtures in such universal multi-talker scenarios are described as general speech mixtures. The speaker extraction algorithm requires an auxiliary reference, such as a video recording or a pre-recorded speech, to form top-down auditory attention on the target speaker. We advocate that a visual cue, i.e., lip movement, is more informative than an audio cue, i.e., pre-recorded speech, to serve as the auxiliary reference for speaker extraction in disentangling the target speaker from a general speech mixture. In this paper, we propose a universal speaker extraction network with a visual cue, that works for all multi-talker scenarios. In addition, we propose a scenario-aware differentiated loss function for network training, to balance the network performance over different target-interference speaker pairing scenarios. The experimental results show that our proposed method outperforms various competitive baselines for general speech mixtures in terms of signal fidelity.

Keywords

Cite

@article{arxiv.2109.14831,
  title  = {USEV: Universal Speaker Extraction with Visual Cue},
  author = {Zexu Pan and Meng Ge and Haizhou Li},
  journal= {arXiv preprint arXiv:2109.14831},
  year   = {2022}
}

Comments

Accepted by TASLP

R2 v1 2026-06-24T06:30:16.784Z