Bangla speech isolation from noisy auditory environment using convolutional neural network

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023.

Opis bibliograficzny
Główni autorzy:	Zaman, K M Tahzeem, Hasan, Zahid, Hossain, Mohd. Ibrahim
Kolejni autorzy:	Alam, Md. Ashraful
Format:	Praca dyplomowa
Język:	English
Wydane:	Brac University 2023
Hasła przedmiotowe:	Short-time Fourier Transform (STFT) U-Net Singal to Distortion Ratio (SDR) Speech separation Neural networks (Computer science)
Dostęp online:	http://hdl.handle.net/10361/19385

id	10361-19385
record_format	dspace
spelling	10361-193852023-08-13T21:02:06Z Bangla speech isolation from noisy auditory environment using convolutional neural network Zaman, K M Tahzeem Hasan, Zahid Hossain, Mohd. Ibrahim Alam, Md. Ashraful Department of Computer Science and Engineering, Brac University Short-time Fourier Transform (STFT) U-Net Singal to Distortion Ratio (SDR) Speech separation Neural networks (Computer science) This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023. Cataloged from PDF version of thesis. Includes bibliographical references (pages 24-25). In recent years, the primary solution to sound enhancement has gained popularity. There is a rich research contribution from academia and industry to remove noise and enhance sound quality. With the advance in machine learning and deep learn ing algorithms, well-performing audio enhancement models now exist. But such a sophisticated and well-researched model has not existed utilizing the language of Bangla. Although there have been models trained and tested to comprehend the language, no such model exists that can process real-time Bangla speech. Also, no such dataset exists that contains a substantial amount of speeches conducted in the Bangla language spanning over multiple hours. In this research, we stud ied the existing models that are working to separate noise in composite auditory environments, and on the basis of that study, we designed and implemented a U Net architecture model that has been trained in the Bangla language and is able to isolate and separate external noise from Bangla language speeches providing a clean feed to the listeners. Implementation of convolution neural networks in digital signal processing is a different approach and we achieved our desired results through it. K M Tahzeem Zaman Zahid Hasan Mohd. Ibrahim Hossain B. Computer Science 2023-08-13T06:47:47Z 2023-08-13T06:47:47Z 2023 2023-01 Thesis ID: 17101212 ID: 17101466 ID: 17201021 http://hdl.handle.net/10361/19385 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. 25 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Short-time Fourier Transform (STFT) U-Net Singal to Distortion Ratio (SDR) Speech separation Neural networks (Computer science)
spellingShingle	Short-time Fourier Transform (STFT) U-Net Singal to Distortion Ratio (SDR) Speech separation Neural networks (Computer science) Zaman, K M Tahzeem Hasan, Zahid Hossain, Mohd. Ibrahim Bangla speech isolation from noisy auditory environment using convolutional neural network
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2023.
author2	Alam, Md. Ashraful
author_facet	Alam, Md. Ashraful Zaman, K M Tahzeem Hasan, Zahid Hossain, Mohd. Ibrahim
format	Thesis
author	Zaman, K M Tahzeem Hasan, Zahid Hossain, Mohd. Ibrahim
author_sort	Zaman, K M Tahzeem
title	Bangla speech isolation from noisy auditory environment using convolutional neural network
title_short	Bangla speech isolation from noisy auditory environment using convolutional neural network
title_full	Bangla speech isolation from noisy auditory environment using convolutional neural network
title_fullStr	Bangla speech isolation from noisy auditory environment using convolutional neural network
title_full_unstemmed	Bangla speech isolation from noisy auditory environment using convolutional neural network
title_sort	bangla speech isolation from noisy auditory environment using convolutional neural network
publisher	Brac University
publishDate	2023
url	http://hdl.handle.net/10361/19385
work_keys_str_mv	AT zamankmtahzeem banglaspeechisolationfromnoisyauditoryenvironmentusingconvolutionalneuralnetwork AT hasanzahid banglaspeechisolationfromnoisyauditoryenvironmentusingconvolutionalneuralnetwork AT hossainmohdibrahim banglaspeechisolationfromnoisyauditoryenvironmentusingconvolutionalneuralnetwork
_version_	1814309062556254208

Bangla speech isolation from noisy auditory environment using convolutional neural network

Podobne zapisy