Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.supervisorSingh, Ashima-
dc.contributor.authorKumar, Manish-
dc.descriptionM.E. (Software Engineering)en
dc.description.abstractThe feature extraction is one of the most important issues in the field of speech recognition. There are two important measurements of speech signal. One is the parametric modeling approach, which is developed by human vocal tract that produces the corresponding speech sound. Generally it is derived from Linear Predictive analysis, such as Linear Prediction Cepstral (LPC) based cepstrum (LPCC). Another approach is non-parametric the modeling method that is based on the human auditory perception system. Mel-frequency cepstral coefficients (MFCCs) are utilized for this purpose. LPC is a technique used in the most of the speech recognition system to estimate the speech parameters like pitch and spectral envelope of the speech signals, which are used in linear predictive (LP) model. A brief survey of LPC and MFCC is initiate with modern phonetics and continuing through the current state of Large-Vocabulary Continuous Speech Recognition (LVCSR) .Experiments has been happening by help of Mat Lab and matlab tools for isolated word speech recognition in different environment. In the experiment we used different recognition algorithm and convert test data to trained data for better speech recognisation .Testing the data from two different vocabularies. Data is collected and recorded with different female and male voices. We have implemented LPC and MFCC algorithms applied on different type of wave (noise or without noise) and Analysis pulse positions, gain and error signal. We are trying to minimise the error and identified batter algorithms. LPC coefficients (LPCC) also estimated by applying some procedures on the speech signal. These procedures started with applying autocorrelation on the windowed frames and windowed frame is auto correlated by p`th order using by MATLAB.en
dc.description.sponsorshipComputer Science, Thapar University, Patialaen
dc.format.extent1679086 bytes-
dc.subjectsoftware engineeringen
dc.subjectcomputer scienceen
dc.titlePerformance Analysis of LPC and MFCC Techniques in Automatic Speech Recognitionen
Appears in Collections:Masters Theses@CSED

Files in This Item:
File Description SizeFormat 
3756.pdf1.64 MBAdobe PDFThumbnail

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