Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods

One of the main challenges in the Automatic Speech Recognition (ASR) is the noise. The performance of the ASR system reduces significantly if the speech is corrupted by noise. In spectrogram representation of a speech signal, after deleting low Signal to Noise Ratio (SNR) elements, the incomplete sp...

Full description

Bibliographic Details
Main Authors:	Rassem, Taha H., Makbol, Nasrin M., Hassan, Ali Muttaleb, Siti Syazni, Mohd Zaki, Girija, P. N.
Format:	Conference or Workshop Item
Language:	English
Published:	American Institute of Physics 2017
Subjects:	QA76 Computer software
Online Access:	http://umpir.ump.edu.my/id/eprint/18743/ http://umpir.ump.edu.my/id/eprint/18743/ http://umpir.ump.edu.my/id/eprint/18743/ http://umpir.ump.edu.my/id/eprint/18743/1/ICAST2017_AIP.pdf

id	ump-18743
recordtype	eprints
spelling	ump-187432018-03-20T04:20:00Z http://umpir.ump.edu.my/id/eprint/18743/ Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods Rassem, Taha H. Makbol, Nasrin M. Hassan, Ali Muttaleb Siti Syazni, Mohd Zaki Girija, P. N. QA76 Computer software One of the main challenges in the Automatic Speech Recognition (ASR) is the noise. The performance of the ASR system reduces significantly if the speech is corrupted by noise. In spectrogram representation of a speech signal, after deleting low Signal to Noise Ratio (SNR) elements, the incomplete spectrogram is obtained. In this case, the speech recognizer should make modifications to the spectrogram in order to restore the missing elements, which is one direction. In another direction, speech recognizer should be able to restore the missing elements due to deleting low SNR elements before performing the recognition. This is can be done using different spectrogram reconstruction methods. In this paper, the geometrical spectrogram reconstruction methods suggested by some researchers are implemented as a toolbox. In these geometrical reconstruction methods, the linear interpolation along time or frequency methods are used to predict the missing elements between adjacent observed elements in the spectrogram. Moreover, a new linear interpolation method using time and frequency together is presented. The CMU Sphinx III software is used in the experiments to test the performance of the linear interpolation reconstruction method. The experiments are done under different conditions such as different lengths of the window and different lengths of utterances. Speech corpus consists of 20 males and 20 females; each one has two different utterances are used in the experiments. As a result, 80% recognition accuracy is achieved with 25% SNR ratio. American Institute of Physics 2017 Conference or Workshop Item PeerReviewed application/pdf en http://umpir.ump.edu.my/id/eprint/18743/1/ICAST2017_AIP.pdf Rassem, Taha H. and Makbol, Nasrin M. and Hassan, Ali Muttaleb and Siti Syazni, Mohd Zaki and Girija, P. N. (2017) Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods. In: The 2nd International Conference on Applied Science and Technology, 3–5 April 2017 , Kedah, Malaysia. pp. 1-6., 1891 (020119). ISBN 978-0-7354-1573-7 http://dx.doi.org/10.1063/1.5005452 http://dx.doi.org/10.1063/1.5005452
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Malaysia Pahang
building	UMP Institutional Repository
collection	Online Access
language	English
topic	QA76 Computer software
spellingShingle	QA76 Computer software Rassem, Taha H. Makbol, Nasrin M. Hassan, Ali Muttaleb Siti Syazni, Mohd Zaki Girija, P. N. Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods
description	One of the main challenges in the Automatic Speech Recognition (ASR) is the noise. The performance of the ASR system reduces significantly if the speech is corrupted by noise. In spectrogram representation of a speech signal, after deleting low Signal to Noise Ratio (SNR) elements, the incomplete spectrogram is obtained. In this case, the speech recognizer should make modifications to the spectrogram in order to restore the missing elements, which is one direction. In another direction, speech recognizer should be able to restore the missing elements due to deleting low SNR elements before performing the recognition. This is can be done using different spectrogram reconstruction methods. In this paper, the geometrical spectrogram reconstruction methods suggested by some researchers are implemented as a toolbox. In these geometrical reconstruction methods, the linear interpolation along time or frequency methods are used to predict the missing elements between adjacent observed elements in the spectrogram. Moreover, a new linear interpolation method using time and frequency together is presented. The CMU Sphinx III software is used in the experiments to test the performance of the linear interpolation reconstruction method. The experiments are done under different conditions such as different lengths of the window and different lengths of utterances. Speech corpus consists of 20 males and 20 females; each one has two different utterances are used in the experiments. As a result, 80% recognition accuracy is achieved with 25% SNR ratio.
format	Conference or Workshop Item
author	Rassem, Taha H. Makbol, Nasrin M. Hassan, Ali Muttaleb Siti Syazni, Mohd Zaki Girija, P. N.
author_facet	Rassem, Taha H. Makbol, Nasrin M. Hassan, Ali Muttaleb Siti Syazni, Mohd Zaki Girija, P. N.
author_sort	Rassem, Taha H.
title	Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods
title_short	Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods
title_full	Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods
title_fullStr	Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods
title_full_unstemmed	Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods
title_sort	restoring the missing features of the corrupted speech using linear interpolation methods
publisher	American Institute of Physics
publishDate	2017
url	http://umpir.ump.edu.my/id/eprint/18743/ http://umpir.ump.edu.my/id/eprint/18743/ http://umpir.ump.edu.my/id/eprint/18743/ http://umpir.ump.edu.my/id/eprint/18743/1/ICAST2017_AIP.pdf
first_indexed	2023-09-18T22:26:43Z
last_indexed	2023-09-18T22:26:43Z
_version_	1777416015419801600

Restoring The Missing Features of the Corrupted Speech using Linear Interpolation Methods

Similar Items