Work

A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System

Year: 2018

Type: conference-paper

Abstract: In spoken dialog systems (SDSs), dialog act (DA) segmentation and recognition provide essential information for response generation.A majority of previous works assumed ground-truth segmentation of DA units, which is not available from automatic speech recognition (ASR) in SDS.We propose a unified architecture based on neural networks, which consists of a sequence tagger for segmentation and a classifier for recognition.The DA recognition model is based on hierarchical neural networks to incorporate the context of preceding sentences.We investigate sharing some layers of the two components so that they can be trained jointly and learn generalized features from both tasks.An evaluation on the Switchboard Dialog Act (SwDA) corpus shows that the jointly-trained models outperform independently-trained models, single-step models, and other reported results in DA segmentation, recognition, and joint tasks.

Source: Annual SIGdial Meeting on Discourse and Dialogue (SIGDIAL)

DOI: 10.18653/v1/w18-5021

Authors: Tianyu Zhao, Tatsuya Kawahara

Institution: Kyoto University

Language: English

Topic: Speech and dialogue systems

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Exploratory Research for Advanced Technology

Award: G2281142962