COMPARISON OF VOWEL RECOGNITION SYSTEMS BASED ON DIFFERENT EXTRACTED FEATURES

منو

" COMPARISON OF VOWEL RECOGNITION SYSTEMS BASED ON DIFFERENT EXTRACTED FEATURES "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	149034
Doc. No	:	ET20826
Main Entry	:	YASHURAJ RAJAGOPAL
Title Proper	:	COMPARISON OF VOWEL RECOGNITION SYSTEMS BASED ON DIFFERENT EXTRACTED FEATURES
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	The thesis revolves around development and comparison of vowel recognition systems.For automatic speech recognition systems, a preprocessing step called the endpointdetection is required to isolate the speech of interest from the background noise so as tobe able to create a speech pattern or template.Particular features are extracted from the speech templates. The features extractedin this thesis are:1. Energy at different frequency bands attained by Wavelet packet decomposition.2. Formant frequencies of vowel utterances.Approaches like, frequency partitioning and LPC models are developed to extractfeatures. The two features are compared by feeding them into neural network classifiers.The neural networks are developed by adopting the concepts of vector quantization andK-means algorithms. The recognition.
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL43971.pdf
Title and statement of responsibility and	:	COMPARISON OF VOWEL RECOGNITION SYSTEMS BASED ON DIFFERENT EXTRACTED FEATURES [Thesis]