Please use this identifier to cite or link to this item: http://13.232.72.61:8080/jspui/handle/123456789/985
Full metadata record
DC FieldValueLanguage
dc.contributor.authorRajeswari-
dc.contributor.authorPrasad, N. N. S. S. R. K.-
dc.contributor.authorSathyanarayana, V.-
dc.date.accessioned2019-02-23T04:41:30Z-
dc.date.available2019-02-23T04:41:30Z-
dc.date.issued2013-07-
dc.identifier.citationRajeswariPrasad, N. N. S. S. R. K., & Sathyanarayana, V. (2013, July). A comparision of multiclass SVM and HMM classifier for wavelet front end robust automatic speech recognition. In 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT) (pp. 1-5). Tiruchengode, India: IEEE.en_US
dc.identifier.isbne-9781479939268-
dc.identifier.otherDOI: 10.1109/ICCCNT.2013.6726821-
dc.identifier.urihttp://13.232.72.61:8080/jspui/handle/123456789/985-
dc.description.abstractClassifiers in Automatic Speech Recognition (ASR) aims to improve the generalization ability of the machine learning and improve the recognition accuracy in noisy environments. This paper discusses the classification performance of Hidden Markov Models (HMM) and Support Vector Machines (SVM) applied to a wavelet front end based ASR. The experiments are performed on speaker independent TIMIT database which are trained in a clean environment and later tested in the presence of Additive White Gaussian Noise (AWGN) for various SNR levels using the HTK toolkit and SVM Light software tool. Experiments indicate that for large vocabulary the wavelet front end and the Multiclass SVM classifier with RBF kernel performs better than the conventional HMM classifier.en_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.subjectElectronics Engineeringen_US
dc.subjectCommunicationen_US
dc.subjectHidden markov modelsen_US
dc.subjectSupport vector machinesen_US
dc.titleA Comparision of Multiclass SVM and HMM Classifier for Wavelet Front End Robust Automatic Speech Recognitionen_US
dc.typeOtheren_US
Appears in Collections:Conference Proceedings



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.