Adding a linguistic-constraint loss from pretrained speech or text models during training improves audio-visual target speaker extraction across languages and visual degradation, with no inference overhead.
Dataset In this study, several experimental settings are considered: •Training Set:A two-speaker mixture training set is simu- lated following previous work [1, 6, 2, 3]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction
Adding a linguistic-constraint loss from pretrained speech or text models during training improves audio-visual target speaker extraction across languages and visual degradation, with no inference overhead.