Title :
A HMM-based fuzzy affective model for emotional speech synthesis
Author :
Qin, Yuqiang ; Zhang, Xueying ; Ying, Hui
Author_Institution :
Taiyuan Univ. of Sci. & Technol., Taiyuan, China
Abstract :
Existing emotional speech synthesis applications usually distinguish between a small number of emotions in speech. However this set of so called basic emotions in speech varies from one application to another depending on their according needs. In order to support such differing application needs an emotional speech fuzzy model is presented. In addition to existing models it supports also the synthesis of derived emotions which are combinations of basic emotions in speech. We show the application of this model by a prosody based Hidden Markov Models(HMM). The approach is based on emotional speech corpus database that trained by HMM. This approach use three kinds of emotional speech corpus (anger, happiness, and sadness) from recordings of a male and a female speaker of Chinese and English. Both the selection of features and the design of the synthesis are addressed.
Keywords :
emotion recognition; fuzzy set theory; hidden Markov models; natural languages; speech synthesis; Chinese language; English language; HMM-based fuzzy affective model; anger; emotional speech corpus database; emotional speech fuzzy model; emotional speech synthesis; female speaker; happiness; hidden Markov model; sadness; Databases; Hidden Markov models; Hypercubes; Psychology; Speech; Speech synthesis; Training; Hidden Markov Models(HMM); emotion computing; emotional speech synthesis; fuzzy emotion hypercube;
Conference_Titel :
Signal Processing Systems (ICSPS), 2010 2nd International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4244-6892-8
Electronic_ISBN :
978-1-4244-6893-5
DOI :
10.1109/ICSPS.2010.5555658