SenSE adds language-model semantic guidance to flow-matching generative speech enhancement via a dual-path masked conditioning strategy and reports SOTA results on distorted speech.
B.4 COMPARISON OFSPEECHTOKENIZERS In our experiments, we adoptS 3 Tokenizer v1 50hz as the speech tokenizer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement
SenSE adds language-model semantic guidance to flow-matching generative speech enhancement via a dual-path masked conditioning strategy and reports SOTA results on distorted speech.