Welcome to IJSDR UGC CARE norms ugc approved journal norms IJRTI Research Journal | ISSN : 2455-2631
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.15 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)

Issue: January 2023

Volume 8 | Issue 1

Impact factor: 8.15

Click Here For more Info

Imp Links for Author
Imp Links for Reviewer
Research Area
Subscribe IJSDR
Visitor Counter

Copyright Infringement Claims
Indexing Partner
Published Paper Details
Paper Title: Feature Selection for Speech Recognition using Hidden Markov Model
Authors Name: Ms. Priyanka Shinde , Prof. P. M. Ghate
Unique Id: IJSDR1710026
Published In: Volume 2 Issue 10, October-2017
Abstract: Present system focus on the challenging issue of selection of feature for HMM for speech recognition application. The features which do not contribute in distinguish between two states could be removed without affecting the usefulness of model. In this paper, Feature Saliency is introduced for selection of feature for Hidden Markov model. The feature saliency gives probability of relevance of feature that distinguish between state independent distributions. An expectation maximization algorithm is used for calculation of maximum a posteriori estimates. Exponential and beta priors are used to include cost in the process of selecting feature. The feature extraction process is implemented using MFCC (Mel Frequency cepstral Coefficients).Extracted MFCC features are given to pattern trainer and are trained by HMM to create HMM model for each word. EM algorithm is used to find out maximum likelihood. The speech recognition process depends on frequency analysis. This can be done because each person has some very unique characteristics to their voice that can be isolated in the frequency domain. This paper presents an approach to the recognition of speech signal using frequency spectral information with Mel frequency for the improvement of speech feature representation in a HMM based recognition approach. There are two strong reasons why Hidden Morkov Model is used. Very first reason is the models are very rich in mathematical structure and hence can form the basis for use in a wide range of applications. Second reason is the models, if applied properly, work very well in practice for several important applications.
Keywords: Hidden Markov Model (HMM), Mel Frequency Cepstral Coefficients (MFCC), Expectation Maximization (EM).
Cite Article: "Feature Selection for Speech Recognition using Hidden Markov Model", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.2, Issue 10, page no.118 - 122, October-2017, Available :http://www.ijsdr.org/papers/IJSDR1710026.pdf
Downloads: 000201506
Publication Details: Published Paper ID: IJSDR1710026
Registration ID:170825
Published In: Volume 2 Issue 10, October-2017
DOI (Digital Object Identifier):
Page No: 118 - 122
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631

Click Here to Download This Article

Article Preview

Click here for Article Preview

Major Indexing from www.ijsdr.org
Google Scholar ResearcherID Thomson Reuters Mendeley : reference manager Academia.edu
arXiv.org : cornell university library Research Gate CiteSeerX DOAJ : Directory of Open Access Journals
DRJI Index Copernicus International Scribd DocStoc

Track Paper
Important Links
Conference Proposal
DOI (A digital object identifier)

Providing A digital object identifier by DOI
How to GET DOI and Hard Copy Related
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Creative Commons License
This material is Open Knowledge
This material is Open Data
This material is Open Content
Social Media

Indexing Partner