Combining voice-conversion and text-to-speech anonymisation preserves suicide-risk detection accuracy near the original baseline (0.692 vs 0.702) while raising speaker-verification EER toward chance.
Dataset The dataset used in this study consists of voice recordings collected from 1,223 Chinese adolescents aged 10-18 [8, 4]
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
background 1representative citing papers
citing papers explorer
-
Speaker Anonymisation for Speech-based Suicide Risk Detection
Combining voice-conversion and text-to-speech anonymisation preserves suicide-risk detection accuracy near the original baseline (0.692 vs 0.702) while raising speaker-verification EER toward chance.