DocumentCode :
1882673
Title :
An accurate infant cry classification system based on continuos Hidden Markov Model
Author :
Abdulaziz, Yousra ; Ahmad, Sharifah Mumtazah Syed
Author_Institution :
Coll. of IT, Univ. Tenaga Nasional (UNITEN), Kajang, Malaysia
Volume :
3
fYear :
2010
fDate :
15-17 June 2010
Firstpage :
1648
Lastpage :
1652
Abstract :
This paper describes the feasibility study of applying a novel continuous Hidden Markov Model algorithm as a classifier to an automatic infant cry classification system which main task is to classify and differentiate between pain and non-pain cries belonging to infants. The classification system is trained based on Baum - Welch algorithm on a pair of local feature vectors. In this study, 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 classification module. The system accuracy reported in this study varies from 71.8% up to 92.3% under different parameter settings, whereby in general the system that are bases on MFCC features performs better than the one that utilizes LPCC features. The encouraging results demonstrate that indeed Hidden Markov Model provides for a robust and accurate infant cry classification system.
Keywords :
hidden Markov models; pattern classification; speech recognition; Baum-Welch algorithm; Mel frequency cepstral coefficient; audio sample; continuos hidden Markov model; infant cry classification system; linear prediction cepstral coefficients; local feature vector; nonpain cry; Artificial neural networks; Classification algorithms; Feature extraction; Hidden Markov models; Mel frequency cepstral coefficient; Pain; Pediatrics; Infant Pain Cry Classification; Linear Prediction Cepstral Coefficints; Mel Frequency Cepstral Coefficient; continuos Hidden Markov Model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Technology (ITSim), 2010 International Symposium in
Conference_Location :
Kuala Lumpur
ISSN :
2155-897
Print_ISBN :
978-1-4244-6715-0
Type :
conf
DOI :
10.1109/ITSIM.2010.5561472
Filename :
5561472
Link To Document :
بازگشت