The framework of the speech communication system with emotion processing

Authors:
Masaki Kurematsu;Jun Hakura;Hamido Fujita
Affiliations:
Faculty of Software and Information Science, Iwate Prefectual University, Iwate, Japan;Faculty of Software and Information Science, Iwate Prefectual University, Iwate, Japan;Faculty of Software and Information Science, Iwate Prefectual University, Iwate, Japan
Venue:
AIKED'07 Proceedings of the 6th Conference on 6th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases - Volume 6
Year:
2007

Citing 4
Cited 3

Affective computing

Affective computing
The production and recognition of emotions in speech: features and algorithms

International Journal of Human-Computer Studies - Application of affective computing in human—Computer interaction
Generating contextually appropriate intonation

EACL '93 Proceedings of the sixth conference on European chapter of the Association for Computational Linguistics
Fast methods for kernel-based text analysis

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1

Emotion based recognition for Miyzawa-Kenji virtual model

AIKED'07 Proceedings of the 6th Conference on 6th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases - Volume 6
The framework of the Turkish syllable-based concatenative text-to-speech system with exceptional case handling

WSEAS Transactions on Computers
Recognizing emotion in speech using neural networks

Telehealth/AT '08 Proceedings of the IASTED International Conference on Telehealth/Assistive Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, We proposed the speech communication system with emotion processing. Our system speaks a given document emotionally based on emotion extracted from speech and text. The difference point between our system and a speech dialogue system is to process emotion. When this system speaks given documents, it uses rules made from speech techniques and the analysis result of professional acting. In order to select these rules, the system extracts emotion from a document and speech. To extract emotion from a document, it uses a word emotion dictionary which shows similarity between a word and a basic emotion word in a concept hierarchy. To extract emotion from speech, it uses a speech emotion database based on the analysis result of speech. This system connects speech synthesize technique with emotion estimation technique. Now we are developing this system. After developing them, we should evaluate the effectiveness of these modules by experiments.