Staff View: Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients

Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients

This paper describes the architecture of an automatic infant cry recognition system which main task is to identify and differentiate between pain and non-pain cries belonging to infants. The recognition system is mainly based on feed forward neural network architecture which is trained with the scal...

Full description

Saved in:

Bibliographic Details
Main Authors:	Abdulaziz Y., Ahmad S.M.S.
Other Authors:	57207857499
Format:	Conference paper
Published:	2023
Subjects:	Automatic recognition of infant cry Feed-forward neural network Linear prediction cepstral coefficients Mel-frequency cepstral coefficients Conjugate gradient method Extraction Feedforward neural networks Information retrieval Knowledge management Natural language processing systems Speech recognition Audio samples Automatic recognition Feature sets Infant cry Infant cry recognition Main tasks Parameter setting Performance based Recognition systems Scaled conjugate gradient algorithm System accuracy Forecasting
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uniten.dspace-29647
record_format	dspace
spelling	my.uniten.dspace-296472023-12-28T15:17:52Z Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients Abdulaziz Y. Ahmad S.M.S. 57207857499 24721182400 Automatic recognition of infant cry Feed-forward neural network Linear prediction cepstral coefficients Mel-frequency cepstral coefficients Conjugate gradient method Extraction Feedforward neural networks Information retrieval Knowledge management Natural language processing systems Speech recognition Audio samples Automatic recognition Feature sets Infant cry Infant cry recognition Linear prediction cepstral coefficients Main tasks Mel-frequency cepstral coefficients Parameter setting Performance based Recognition systems Scaled conjugate gradient algorithm System accuracy Forecasting This paper describes the architecture of an automatic infant cry recognition system which main task is to identify and differentiate between pain and non-pain cries belonging to infants. The recognition system is mainly based on feed forward neural network architecture which is trained with the scaled conjugate gradient algorithm. This paper presents an in depth comparison of system performance whereby two different sets of features, namely Mel Frequency Cepstral Coefficient (MFCC) and Linear Prediction Cepstral Coefficients (LPCC) are extracted from the audio samples of infant's cries and are fed into the recognition module. The system accuracy reported in this study varies from 57% up to 76.2% under different parameter settings. The results demonstrated that in general, the infant cry recognition system performs better by using the MPCC feature sets. �2010 IEEE. Final 2023-12-28T07:17:52Z 2023-12-28T07:17:52Z 2010 Conference paper 10.1109/INFRKM.2010.5466907 2-s2.0-77953877115 https://www.scopus.com/inward/record.uri?eid=2-s2.0-77953877115&doi=10.1109%2fINFRKM.2010.5466907&partnerID=40&md5=1b3d38bf4450fcc234b721c0f74d5e0f https://irepository.uniten.edu.my/handle/123456789/29647 5466907 260 263 Scopus
institution	Universiti Tenaga Nasional
building	UNITEN Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Tenaga Nasional
content_source	UNITEN Institutional Repository
url_provider	http://dspace.uniten.edu.my/
topic	Automatic recognition of infant cry Feed-forward neural network Linear prediction cepstral coefficients Mel-frequency cepstral coefficients Conjugate gradient method Extraction Feedforward neural networks Information retrieval Knowledge management Natural language processing systems Speech recognition Audio samples Automatic recognition Feature sets Infant cry Infant cry recognition Linear prediction cepstral coefficients Main tasks Mel-frequency cepstral coefficients Parameter setting Performance based Recognition systems Scaled conjugate gradient algorithm System accuracy Forecasting
spellingShingle	Automatic recognition of infant cry Feed-forward neural network Linear prediction cepstral coefficients Mel-frequency cepstral coefficients Conjugate gradient method Extraction Feedforward neural networks Information retrieval Knowledge management Natural language processing systems Speech recognition Audio samples Automatic recognition Feature sets Infant cry Infant cry recognition Linear prediction cepstral coefficients Main tasks Mel-frequency cepstral coefficients Parameter setting Performance based Recognition systems Scaled conjugate gradient algorithm System accuracy Forecasting Abdulaziz Y. Ahmad S.M.S. Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients
description	This paper describes the architecture of an automatic infant cry recognition system which main task is to identify and differentiate between pain and non-pain cries belonging to infants. The recognition system is mainly based on feed forward neural network architecture which is trained with the scaled conjugate gradient algorithm. This paper presents an in depth comparison of system performance whereby two different sets of features, namely Mel Frequency Cepstral Coefficient (MFCC) and Linear Prediction Cepstral Coefficients (LPCC) are extracted from the audio samples of infant's cries and are fed into the recognition module. The system accuracy reported in this study varies from 57% up to 76.2% under different parameter settings. The results demonstrated that in general, the infant cry recognition system performs better by using the MPCC feature sets. �2010 IEEE.
author2	57207857499
author_facet	57207857499 Abdulaziz Y. Ahmad S.M.S.
format	Conference paper
author	Abdulaziz Y. Ahmad S.M.S.
author_sort	Abdulaziz Y.
title	Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients
title_short	Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients
title_full	Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients
title_fullStr	Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients
title_full_unstemmed	Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients
title_sort	infant cry recognition system: a comparison of system performance based on mel frequency and linear prediction cepstral coefficients
publishDate	2023
_version_	1806423303401766912
score	13.222552

Infant cry recognition system: A comparison of system performance based on Mel frequency and linear prediction cepstral coefficients

Similar Items