Artificial word insertions and deletions in news text, used as self-supervised pretraining tasks, transfer to human-annotated disfluency detection and cut the labeled-data requirement to 1,000 sentences.
Giving Attention to the Unexpected: Using Prosody Innovations in Disfluency Detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Disfluencies in spontaneous speech are known to be associated with prosodic disruptions. However, most algorithms for disfluency detection use only word transcripts. Integrating prosodic cues has proved difficult because of the many sources of variability affecting the acoustic correlates. This paper introduces a new approach to extracting acoustic-prosodic cues using text-based distributional prediction of acoustic cues to derive vector z-score features (innovations). We explore both early and late fusion techniques for integrating text and prosody, showing gains over a high-accuracy text-only model.
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Task Self-Supervised Learning for Disfluency Detection
Artificial word insertions and deletions in news text, used as self-supervised pretraining tasks, transfer to human-annotated disfluency detection and cut the labeled-data requirement to 1,000 sentences.