Spectral histogram of oriented gradients (SHOGs) for Tamil language male/female speaker classification |
| |
Authors: | A Muthamizh Selvan R Rajesh |
| |
Affiliation: | (1) Dept. of Computer Applications, School of Computer Science and Engineering, Bharathiar University, Coimbatore, 641 046, India |
| |
Abstract: | Gender (Male/Female) classification plays a primary vital role to develop a robust Automatic Tamil Speech Recognition (ASR)
applications due to the diversity in the vocal tract of speakers. Various features including Formants (F1, F2, F3, F4), Zero
Crossings, and Mel-Frequency Cepstral Coefficients (MFCCs) etc. have appeared in the literature especially for speech/signal
classification/recognition. Recently Dalal et al. have proposed a feature called as Histogram of Oriented Gradients (HOG)
for extracting feature from an image for efficient detection/classification of objects. We extend and apply the HOG for spectrogram
of speech signal and hence called as Spectral Histogram of Oriented Gradients (SHOGs). The results of Tamil language male/female
speaker classification using SHOGs features shows good improvement in the classification rate when compared to other features.
The results of combination of various features with SHOGs are also promissing. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|