Blind multi-channel speech separation can be solved with a single-speaker diffusion prior plus an estimated likelihood, without knowing array geometry or using paired training data.
A., Fontaine, M., and Yoshii, K
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior
Blind multi-channel speech separation can be solved with a single-speaker diffusion prior plus an estimated likelihood, without knowing array geometry or using paired training data.