DocumentCode
3026400
Title
A study on emotional feature extraction and analysis in speech
Author
Chen, Yanxiang ; Wu, Xi
Author_Institution
Sch. of Comput. Sci. & Inf., Hefei Univ. of Technol., Hefei, China
fYear
2011
fDate
26-28 July 2011
Firstpage
3374
Lastpage
3377
Abstract
Analyses the features of the time, amplitude, fundamental frequency and formant constructions involving 5 emotions as happiness, anger, surprise, sorrow and neutrality. Through speech parameters extracted from emotional database of German, this paper sums up the distribution laws of emotional features of different emotional speech signal and presents practically theoretical data for processing and recognition of emotional speech.
Keywords
emotion recognition; feature extraction; speech recognition; amplitude; anger; emotional database; emotional feature extraction; emotional speech processing; emotional speech recognition; emotional speech signal; fundamental frequency; happiness; neutrality; sorrow; speech analysis; speech parameter; surprise; time; Databases; Emotion recognition; Feature extraction; Speech; Speech processing; Speech recognition; Time frequency analysis; amplitude construction; emotional feature; formant construction; fundamental frequency construction; time construction;
fLanguage
English
Publisher
ieee
Conference_Titel
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location
Hangzhou
Print_ISBN
978-1-61284-771-9
Type
conf
DOI
10.1109/ICMT.2011.6001876
Filename
6001876
Link To Document