Duration modeling for emotional speech

Authors:
Wen-Hsing Lai;Siou-Lin Wang
Affiliations:
Dept. of Computer and Communication Engineering, National Kaohsiung First University of Science and Technology, Kaohsiung, Taiwan;Dept. of Computer and Communication Engineering, National Kaohsiung First University of Science and Technology, Kaohsiung, Taiwan
Venue:
ICICA'12 Proceedings of the Third international conference on Information Computing and Applications
Year:
2012

Citing 8
Cited 0

Baby ears: a recognition system for affective vocalizations

Speech Communication
A corpus-based speech synthesis system with emotion

Speech Communication - Special issue on speech and emotion
Emotion Recognition of Affective Speech Based on Multiple Classifiers Using Acoustic-Prosodic Information and Semantic Labels

IEEE Transactions on Affective Computing
Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge

Speech Communication
Emotion recognition using a hierarchical binary decision tree approach

Speech Communication
Expressing degree of activation in synthetic speech

IEEE Transactions on Audio, Speech, and Language Processing
Audio–Visual Affective Expression Recognition Through Multistream Fused HMM

IEEE Transactions on Multimedia
Feature Analysis and Evaluation for Automatic Emotion Identification in Speech

IEEE Transactions on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

Human interaction involves exchanging not only explicit content, but also implicit information about the affective state of the interlocutor. In recent years, researchers attempt to endow the computers or robots with humanity. Various affective computing models have been proposed, which covers the areas of emotion recognition, interpretation, management and generation. Therefore, to analyze and predict the prosodic information of different emotions is very important for the future applications. In this article, a duration modeling approach for emotional speech is presented. Seven kinds of emotion including natural, scare, angry, elation, sadness, surprise, and disgust are adopted. According to the statistics performed on a corpus with seven emotions, a question set considering acoustic and linguistic factors is designed. Experimental results show that the root mean squared errors (RMSEs) of syllable are 0.0725s and 0.0802 s for training and testing sets correspondingly. From the results, the impact of factors related to different emotions can be explored.