Personal information from Bangla speech signal using MFCC and GMM

Personal information from Bangla speech signal using MFCC and GMM

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2019.

Manylion Llyfryddiaeth
Prif Awduron: Hridy, Maisha Munawara, Hasan, Md. Hasib, Emon, Mahfuz Al
Awduron Eraill: Uddin, Jia
Fformat: Traethawd Ymchwil
Iaith:English
Cyhoeddwyd: Brac University 2021
Pynciau:
Mel Frequency Cepstral Coe cient
Gaussian Mixture Model
Natural language processing
Python
Bangla
Machine learning.
Mynediad Ar-lein:http://hdl.handle.net/10361/14744
id 10361-14744
record_format dspace
spelling 10361-147442022-01-26T10:20:08Z Personal information from Bangla speech signal using MFCC and GMM Hridy, Maisha Munawara Hasan, Md. Hasib Emon, Mahfuz Al Uddin, Jia Department of Computer Science and Engineering, Brac University Mel Frequency Cepstral Coe cient Gaussian Mixture Model Natural language processing Python Bangla Machine learning. This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2019. Cataloged from PDF version of thesis. Includes bibliographical references (pages 18-20). Our system extracts personal information from bangla speech. Dataset that was used consists real-life voice inputs from di erent age and gender groups. A set of Bengali speech samples from YouTube were used as input dataset. This system is based on basic machine learning algorithms. Mel frequency cepstral coe cient was used to train and construct this system. While calculating gender and age detection part, we will be using GMM to calculate the nal scores on the samples having the MFCCs of the extracted speech samples. GMM model basically congregates some subsets among the whole set based on probability. Along with the gender determination process, age detection process will also be simulated using fundamental frequency of speech. Python is the programming language used to write the coding. Our system was successful in giving 88% accuracy for gender recognition and 75% accuracy for age detection. Maisha Munawara Hridy Md. Hasib Hasan Mahfuz Al Emon B. Computer Science 2021-07-06T15:50:53Z 2021-07-06T15:50:53Z 2019 2019-08 Thesis ID 14101037 ID 14101033 ID 14101007 http://hdl.handle.net/10361/14744 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 21 pages application/pdf Brac University
institution Brac University
collection Institutional Repository
language English
topic Mel Frequency Cepstral Coe cient
Gaussian Mixture Model
Natural language processing
Python
Bangla
Machine learning.
spellingShingle Mel Frequency Cepstral Coe cient
Gaussian Mixture Model
Natural language processing
Python
Bangla
Machine learning.
Hridy, Maisha Munawara
Hasan, Md. Hasib
Emon, Mahfuz Al
Personal information from Bangla speech signal using MFCC and GMM
description This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2019.
author2 Uddin, Jia
author_facet Uddin, Jia
Hridy, Maisha Munawara
Hasan, Md. Hasib
Emon, Mahfuz Al
format Thesis
author Hridy, Maisha Munawara
Hasan, Md. Hasib
Emon, Mahfuz Al
author_sort Hridy, Maisha Munawara
title Personal information from Bangla speech signal using MFCC and GMM
title_short Personal information from Bangla speech signal using MFCC and GMM
title_full Personal information from Bangla speech signal using MFCC and GMM
title_fullStr Personal information from Bangla speech signal using MFCC and GMM
title_full_unstemmed Personal information from Bangla speech signal using MFCC and GMM
title_sort personal information from bangla speech signal using mfcc and gmm
publisher Brac University
publishDate 2021
url http://hdl.handle.net/10361/14744
work_keys_str_mv AT hridymaishamunawara personalinformationfrombanglaspeechsignalusingmfccandgmm
AT hasanmdhasib personalinformationfrombanglaspeechsignalusingmfccandgmm
AT emonmahfuzal personalinformationfrombanglaspeechsignalusingmfccandgmm
_version_ 1814309284386701312

Eitemau Tebyg