Title :
Recognition of emotional state from spoken sentences
Author :
Lin, Xiao ; Chen, Yanqiu ; Lim, Soonleng ; Lim, Choonban
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
Abstract :
In this paper, we investigate methods for the extraction of non-textual information from spoken sentences in order to identify the emotional state of the speaker. We propose a method based on judging the flatness of the pitch contour. The results of our experiments show that the proposed method achieves reasonably good recognition rates: more than 90% for male speakers and around 80% for female speakers
Keywords :
human factors; speech processing; speech recognition; emotional state recognition; female speakers; male speakers; nontextual information extraction; pitch contour flatness; recognition rates; spoken sentences; Cardiology; Data mining; Databases; Emotion recognition; Frequency; Microphones; Mood; Signal processing; Speech recognition; Timing;
Conference_Titel :
Multimedia Signal Processing, 1999 IEEE 3rd Workshop on
Conference_Location :
Copenhagen
Print_ISBN :
0-7803-5610-1
DOI :
10.1109/MMSP.1999.793892
