pTSE-T conditions TSE on unaligned text semantic cues via TPE network for mask generation, reporting SI-SDRi of 12.16 dB.
R.; McQuinn, E.; Crow, D.; Manilow, E.; and Le Roux, J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
pTSE-T: Presentation Target Speaker Extraction using Unaligned Text Cues
pTSE-T conditions TSE on unaligned text semantic cues via TPE network for mask generation, reporting SI-SDRi of 12.16 dB.