Title :
Emotion recognition using LP residual at sub-segmental, segmental and supra-segmental levels
Author :
Yadav, Jainath ; Kumari, Anshu ; Rao, K. Sreenivasa
Author_Institution :
Sch. of Math., Stat. & Comput. Sci., Central Univ. of Bihar, Patna, India
Abstract :
This paper is concerned with speech signal based emotion recognition. Linear Prediction (LP) residual mainly contains source specific emotional information. LP residual is derived by inverse filtering of the speech signal. For characterizing the basic emotions, LP residual has been explored at sub-segmental level, segmental level, supra-segmental level, respectively. Gaussian mixture models (GMMs) have been used as classifier. IIT Kharagpur Simulated Emotion Speech Corpus (IITKGP-SESC) and Berlin emotional database (Berlin-EMO-DB) are used as a database for this purpose. Average emotion recognition rate is observed to be 58.4%, 65.6% and 48% at sub-segmental level, segmental level and supra-segmental level, respectively.
Keywords :
Gaussian processes; emotion recognition; mixture models; speech recognition; Berlin emotional database; GMM; Gaussian mixture models; IIT Kharagpur simulated emotion speech corpus; LP residual; inverse filtering; linear prediction residual; segmental level; speech signal based emotion recognition; sub-segmental level; supra-segmental level; Databases; Emotion recognition; Feature extraction; Gaussian mixture model; Speech; Speech recognition; Feature vector; Gaussian Mixture Model; Linear prediction analysis; Linear prediction coefficient; Probability density; Residual signal; Segmental level; Simulated database; Speech; Speech sample; Sub-segmental; Suprasegmental level;
Conference_Titel :
Communication, Information & Computing Technology (ICCICT), 2015 International Conference on
Conference_Location :
Mumbai
Print_ISBN :
978-1-4799-5521-3
DOI :
10.1109/ICCICT.2015.7045735
