Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/17879
Title: | Discrete wavelet transforms with multiclass SVM for phoneme recognition |
Authors: | Cutajar, Michelle Gatt, Edward Grech, Ivan Casha, Owen Micallef, Joseph |
Keywords: | Support vector machines Speech processing systems Radial basis functions Wavelets (Mathematics) Kernel functions |
Issue Date: | 2013 |
Publisher: | Institute of Electrical and Electronics Engineers Inc. |
Citation: | Cutajar, M., Gatt, E., Grech, I., Casha, O., & Micallef, J. (2013). Discrete wavelet transforms with multiclass SVM for phoneme recognition. EuroCon 2013, Zagreb. 1695-1700. |
Abstract: | A phoneme recognition system based on Discrete Wavelet Transforms (DWT) and Support Vector Machines (SVMs), is designed for multi-speaker continuous speech environments. Phonemes are divided into frames, and the DWTs are adopted, to obtain fixed dimensional feature vectors. For the multiclass SVM, the One-against-one method with the RBF kernel was implemented. To further improve the accuracies obtained, a priority scheme was added, to forecast the three most likely phonemes. After classification, all frames were again re-grouped, in order to evaluate the accuracy of the system according to the substitution, deletion and insertion errors. The percentage correct and accuracy, obtained from the designed phoneme recognition system, were 63.08% and 53.27% respectively. All tests were carried out on the TIMIT database. This phoneme recognition system is intended to be implemented on a dedicated chip, to improve the speed of the software implementation by approximately 100 times. |
URI: | https://www.um.edu.mt/library/oar//handle/123456789/17879 |
Appears in Collections: | Scholarly Works - FacICTMN |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Discrete Wavelet Transforms with Multiclass SVM for Phoneme Recognition.pdf Restricted Access | Discrete wavelet transforms with multiclass SVM for phoneme recognition | 471.42 kB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.