A single-channel model extracts target speech using only a query distance as the clue, leveraging distance-dependent reverberation cues and without any speaker-specific enrollment.
Separate in the speech chain: Cross-modal conditional audio-visual target speech extraction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Distance Based Single-Channel Target Speech Extraction
A single-channel model extracts target speech using only a query distance as the clue, leveraging distance-dependent reverberation cues and without any speaker-specific enrollment.