Parsing Speech: a Neural Approach to Integrating Lexical and Acoustic-Prosodic Information

Trang Tran, Shubham Toshniwal, Mohit Bansal, Kevin Gimpel, Karen Livescu, Mari Ostendorf


Abstract
In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features using a convolutional neural network over energy and pitch trajectories coupled with an attention-based recurrent neural network that accepts text and prosodic features. We find that different types of acoustic-prosodic features are individually helpful, and together give statistically significant improvements in parse and disfluency detection F1 scores over a strong text-only baseline. For this study with known sentence boundaries, error analyses show that the main benefit of acoustic-prosodic features is in sentences with disfluencies, attachment decisions are most improved, and transcription errors obscure gains from prosody.
Anthology ID:
N18-1007
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
69–81
Language:
URL:
https://www.aclweb.org/anthology/N18-1007
DOI:
10.18653/v1/N18-1007
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N18-1007.pdf
Video:
 http://vimeo.com/276439724