CopyPaste-based parallel data, cosine similarity loss, and energy-based emotion masking reduce speaker verification EER by 19.29% relative on the Dusha emotional speech corpus.
We first verified that emotional utterances degrade SV performance, with cross-emotion test trails performed worse than same-emotion test trails
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learning Emotion-Invariant Speaker Representations for Speaker Verification
CopyPaste-based parallel data, cosine similarity loss, and energy-based emotion masking reduce speaker verification EER by 19.29% relative on the Dusha emotional speech corpus.