Segment-wise waveform reversal, combined with voice activity detection and source separation, reduces speech intelligibility in environmental audio (97.9% WER) while preserving source detectability (2.7% SCAD drop) and audio quality (FAD 1.40).
Librispeech: an asr corpus based on public domain audio books,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Enforcing Speech Content Privacy in Environmental Sound Recordings using Segment-wise Waveform Reversal
Segment-wise waveform reversal, combined with voice activity detection and source separation, reduces speech intelligibility in environmental audio (97.9% WER) while preserving source detectability (2.7% SCAD drop) and audio quality (FAD 1.40).