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 setting tests wh ether our metric can distinguish between speakers undistinguish - able with speech rate
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
-
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.