SVM and ANN: A comparative evaluation
- Resource Type
- Conference
- Authors
- Sahay, Tanvi; Aggarwal, Arpit; Bansal, Annu; Chandra, Mahesh
- Source
- 2015 1st International Conference on Next Generation Computing Technologies (NGCT) Next Generation Computing Technologies (NGCT), 2015 1st International Conference on. :960-964 Sep, 2015
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
General Topics for Engineers
Robotics and Control Systems
Signal Processing and Analysis
Kernel
Support vector machines
Feature extraction
Biological neural networks
Neurons
Speech recognition
Mel frequency cepstral coefficient
support vector machine (SVM)
kernels
artificial neural network (ANN)
C-SVC
speech recognition
classifier
- Language
Support vector machines (SVMs) are among the most robust classifiers for the purpose of speech recognition. This paper compares one of the more contemporary methods of classification, artificial neural network (ANN) with support vector machines and draws conclusions based on a comparison of accuracy. The neural network is a pattern network for variable hidden neurons and transfer functions. C- Support vector classifier is used with three different kernels and kernel parameters. MFCC has been used as the feature extraction technique for a noiseless database of 50 independent speakers. The results were found to be best for SVM with RBF kernel in comparison to bi-quadratic polynomial and sigmoid kernels and pattern network.