Sorry, you need to enable JavaScript to visit this website.

Lexico-acoustic Neural-based Models for Dialog Act Classification

Citation Author(s):
Daniel Ortega, Ngoc Thang Vu
Submitted by:
Daniel Ortega
Last updated:
14 April 2018 - 12:45am
Document Type:
Poster
Document Year:
2018
Event:
Presenters Name:
Daniel Ortega
Paper Code:
4427

Abstract 

Abstract: 

Recent works have proposed neural models for dialog act classification in spoken dialogs.
However, they have not explored the role and the usefulness of acoustic information.
We propose a neural model that processes both lexical and acoustic features for classification.
Our results on two benchmark datasets reveal that acoustic features are helpful in improving the overall accuracy.
Finally, a deeper analysis shows that acoustic features are valuable in three cases: when a dialog act has sufficient data, when lexical information is limited and when strong lexical cues are not present.

up
0 users have voted:

Dataset Files

icassp-2018-poster.pdf

(219)