World Journal of Engineering Research and Technology (WJERT) has indexed with various reputed international bodies like : Google Scholar , Index Copernicus , Indian Science Publications , SOCOLAR, China , International Institute of Organized Research (I2OR) , Cosmos Impact Factor , Research Bible, Fuchu, Tokyo. JAPAN , Scientific Indexing Services (SIS) , Jour Informatics (Under Process) , UDLedge Science Citation Index , International Impact Factor Services , International Scientific Indexing, UAE , International Society for Research Activity (ISRA) Journal Impact Factor (JIF) , International Innovative Journal Impact Factor (IIJIF) , Science Library Index, Dubai, United Arab Emirates , Scientific Journal Impact Factor (SJIF) , Science Library Index, Dubai, United Arab Emirates , Eurasian Scientific Journal Index (ESJI) , Global Impact Factor (0.342) , IFSIJ Measure of Journal Quality , 

World Journal of Engineering
Research and Technology

An International Peer Reviewed Journal for Engineering Research and Technology

ISSN 2454-695X

Impact Factor : 5.218

ICV : 79.45

News & Updation

  • Article Invited for Publication

    Article are invited for publication in WJERT Coming Issue

  • WJERT New Impact Factor

    Its our Pleasure to Inform you that WJERT Impact Factor has been increased from 4.236 to 5.218 due to high quality Publication at International Level

  • ICV

    WJERT Rank with Index Copernicus Value 79.45 due to high reputation at International Level

  • WJERT SEPTEMBER ISSUE PUBLISHED

    SEPTEMBER 2018 Issue has been successfully launched on 1 September 2018

  • New Issue Published

    Its Our pleasure to inform you that, WJERT 1 September 2018 Issue has been Published, Kindly check it on http://wjert.org/home/current_issues

Indexing

Abstract

EMOTION RECOGNITION FROM SPEECH WITH GAUSSIAN MIXTURE MODELS AND VIA BOOSTED GMM

B. Meenapreethi, Deepika G. Krishnan* and Sivaranjani G.

ABSTRACT

Speech has several endowment features such as naturalness and efficient, which makes it as winsome interface medium. It is possible to express emotions and attitudes via speech. In human machine interface application emotion recognition from the speech signal has been prevailing topic of research. Speech emotion recognition is an important issue which affects the human machine intercommunication. Automatic recognition of human emotion in speech angles at recognizing the primitive emotional state of a speaker from the speech signal. Gaussian mixture models (GMMs) and the scintilla error rate classifier (i.e. Bayesian optimal classifier) is embraced and effective tools for speech emotion recognition. Typically, GMMs are used to model the class-conditional distributions of acoustic visage and their parameters are outlined by the expectation maximization (EM) algorithm based on a training data set. Then, classification is performed to minimize the classification error w.r.t. the judged class conditional distributions. This method is called the EM-GMM algorithm. In this paper, we discuss about boosting algorithm for reliably and accurately estimating the classconditional GMMs. The resulting algorithm is named the Boosted-GMM algorithm. This speech recognition experiment shows better results than the prior algorithms available update. This is due to the fact that the boosting algorithm can lead to more scrupulous estimates of the class-conditional GMMs, namely the class-conditional dispersions of acoustic features.

[Full Text Article]