Comparison between k-nn and svm method for speech emotion recognition
Journal Title: International Journal on Computer Science and Engineering - Year 2011, Vol 3, Issue 2
Abstract
Human - Computer intelligent interaction (HCII) is an emerging field of science aimed at providing natural ways for humans to use computer as aids. Machine intelligence needs to include emotional intelligence it is argued that for the computer to be able to interact with humans, it needs to have the communication skills of human. One of these skills is the ability to understand the emotional state of the person. Two recognition methods namely K-Nearest Neighbor (K-NN) and Support vector machine (SVM) classifier have been experimented and compared. The paper explores the simplicity and effectiveness of SVM classifier for designing the real-time emotion recognition system.
Authors and Affiliations
Muzaffar Khan , Tirupati Goskula , Mohmmed Nasiruddin , Ruhina Quazi
Keywords
Related Articles
- EP ID EP124267
- DOI -
- Views 118
- Downloads 0
Realisation of Resourceful Data Mining Services Using Cloud Computing
Data security and access control are the most challenging research work going on, at present, in cloud computing. This is because of the users sending their sensitive data to the cloud providers for acquiring their servi...
AN EFFECTIVE RETRIVAL SCHEME FOR SOFTWARE COMPONENT REUSE
Software component reuse has become of much interest in the software community due to its potential benefits, cost benefit, time saving, etc. which include increased product quality and decreased product development cost...
An Extensive Evaluation of Anaphora Resolution Based Abstract Generation System
This paper presents an extensive evaluation of anaphora resolution (AR) algorithm proposed for Abstract Generation System (AGS) and discusses the metrics used to measure its performance. The evaluation exercise is conduc...
DMSA TECHNIQUE FOR FINDING SIGNIFICANT PATTERNS IN LARGE DATABASE
Frequent pattern mining in databases plays a vital role in many data mining tasks like classification, sequential patters, clustering, association rules analysis etc. There are numerous mining algorithms for finding asso...
Effect Of Grouping Cluster Based on Overlapping FOV In Wireless Multimedia Sensor Network
Wireless multimedia sensor network (WMSN) uses multimedia nodes to sense the area that are un-correlated to the areas sensed by the neighboring sensors. Because of huge amount of data produced in wireless multimedia sens...