arrow
返回

USEV: Universal Speaker Extraction With Visual Cue

delete2022-01-01
delete18
delete
OA
AI
Z
Zexu Pan
M
Meng Ge *
H
Haizhou Li
DOI:10.1109/TASLP.2022.3205759delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
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.
Keyword:
General speech mixture
multi-modal
scenarioaware differentiated loss
sparsely overlapped speech
target speaker extraction

期刊

I
IEEE-ACM Transactions on Audio Speech and Language Processing
IF:
5.1
论文数:
2.6K
被引数:
1.1W

机构

T
tianjin university
学者数:
8.0W
论文数: 5.8W
被引数: 88
T
The Chinese University of Hong Kong, Shenzhen
学者数:
4.3K
论文数: 4.0K
被引数: 7
N
National University of Singapore
学者数:
7.6W
论文数: 6.5W
被引数: 11.4W
学者 查看更多机构
引用论文

引用论文

err2003-01-01
err0
PREAI
errA. Joshi
err分享
err收藏
Industrial clays of Brazil
err2003-01-01
err0
PREAI
errPérsio de Souza Santos
err分享
err收藏
err分享
err收藏
学者 查看更多内容