A spoken dialogue system with situation and emotion detection based on anthropomorphic learning for warming healthcare d

Author

Bo-Hao Su ; Ping-Wen Fu ; Po-Chuan Lin ; Po-Yi Shih ; Yuh-Chung Lin ; Jhing-Fa Wang ; An-Chao Tsai

fYear

2014

fDate

20-23 Sept. 2014

Firstpage

133

Lastpage

136

Abstract

This work presents a spoken dialogue system with situation and emotion detection based on anthropomorphic learning for warming healthcare. To provide more warming feedback of the system, we combine situation and emotion detection with spoken dialogue system. Situation and emotion detection are based on lexical category using Partial-Matching Spoken Sentence Retrieval (PMSSR). Moreover, an anthropomorphic learning mechanism is proposed to improve the performance of emotion and situation detection. The mechanism based on out-of-vocabulary (OOV) detection is used to update emotion and situation database with new lexicon through interaction with user and internet. The experimental results show that the anthropomorphic learning mechanism increases the accuracy rate of situation and emotion detection by 30% and 20%, respectively.

Keywords

emotion recognition; health care; interactive systems; speech recognition; Internet; OOV detection; PMSSR; anthropomorphic learning; emotion detection; lexical category; out-of-vocabulary detection; partial-matching spoken sentence retrieval; performance improvement; situation database; situation detection; spoken dialogue system; warming feedback; warming healthcare; Accuracy; Databases; HTML; Learning systems; Medical services; Speech recognition; Vocabulary; Anthropomorphic Learning; Emotion Detection; Situation Detection; Spoken Dialogue System;

fLanguage

English

Publisher

ieee

Conference_Titel

Orange Technologies (ICOT), 2014 IEEE International Conference on

Conference_Location

Xian

Type

conf

DOI

10.1109/ICOT.2014.6956617

Filename

6956617