A causal flow-matching model renders streaming binaural speech from mono audio and speaker/listener poses, reaching a 42% confusion rate against real recordings in an AB test.
However, we observe that setting coefficients greater than 0, which shifts the time steps to the second half, results in better qualitative outcomes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models
A causal flow-matching model renders streaming binaural speech from mono audio and speaker/listener poses, reaching a 42% confusion rate against real recordings in an AB test.