ASV embeddings used to judge whether synthesized speech matches a target speaker mostly encode static spectral traits and miss rhythm, so the authors introduce U3D, a duration-distribution metric for speaker rhythm.
This reflects the lower bound of our metric, where we expect the smallest distances
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Analyzing and Improving Speaker Similarity Assessment for Speech Synthesis
ASV embeddings used to judge whether synthesized speech matches a target speaker mostly encode static spectral traits and miss rhythm, so the authors introduce U3D, a duration-distribution metric for speaker rhythm.