Using character-duration sequences from WhisperX, a transformer identifies speakers with balanced accuracy of 0.39 on LibriSpeech but only 0.03 on VoxCeleb1, and fusion with x-vectors does not improve accuracy.
Discussion Our results are consistent with prior works [2, 3] that have suggested rhythm features do convey useful information about a speaker’s identity
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
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Rhythm Features for Speaker Identification
Using character-duration sequences from WhisperX, a transformer identifies speakers with balanced accuracy of 0.39 on LibriSpeech but only 0.03 on VoxCeleb1, and fusion with x-vectors does not improve accuracy.