Radon transform of auditory neurograms: a robust feature set for phoneme classification

Alam, Md Shariful and Jassim, Wissam A. and Zilany, Muhammad Shamsul Arefeen (2018) Radon transform of auditory neurograms: a robust feature set for phoneme classification. IET Signal Processing, 12 (3). pp. 260-268. ISSN 1751-9675, DOI https://doi.org/10.1049/iet-spr.2017.0170.

Full text not available from this repository.
Official URL: https://doi.org/10.1049/iet-spr.2017.0170


Classification of speech phonemes is challenging, especially under noisy environments, and hence traditional speech recognition systems do not perform well in the presence of noise. Unlike traditional methods in which features are mostly extracted from the properties of the acoustic signal, this study proposes a new feature for phoneme classification using neural responses from a physiologically based computational model of the auditory periphery. The two-dimensional neurogram was constructed from the simulated responses of auditory-nerve fibres to speech phonemes. Features of neurogram images were extracted using the Discrete Radon Transform, and the dimensionality of features was reduced using an efficient feature selection technique. A standard classifier, Support Vector Machine, was employed to model and test the phoneme classes. Classification performance was evaluated in quiet and under noisy conditions in which test data were corrupted with various environmental distortions such as additive noise, room reverberation, and telephone-channel noise. Performances were also compared with the results from existing methods such as the Mel-frequency cepstral coefficient, Gammatone frequency cepstral coefficient, and frequency-domain linear prediction-based phoneme classification methods. In general, the proposed neural feature exhibited a better classification accuracy in quiet and under noisy conditions compared with the performance of most existing acoustic-signal-based methods.

Item Type: Article
Uncontrolled Keywords: Classification accuracy; Classification of speech; Classification performance; Discrete radon transform; Efficient feature selections; Mel frequency cepstral co-efficient; Phoneme classification; Speech recognition systems
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Engineering
Depositing User: Ms. Juhaida Abd Rahim
Date Deposited: 27 Sep 2019 01:26
Last Modified: 27 Sep 2019 01:26
URI: http://eprints.um.edu.my/id/eprint/22595

Actions (login required)

View Item View Item