Classification of cries of infants with cleft-palate using parallel hidden Markov models

Dror Lederman; Ehud Zmora; Stephanie Hauschildt; Angelika Stellzig-Eisenhauer; Kathleen Wermke

doi:10.1007/s11517-008-0334-y

Classification of cries of infants with cleft-palate using parallel hidden Markov models

Dror Lederman, Ehud Zmora, Stephanie Hauschildt, Angelika Stellzig-Eisenhauer, Kathleen Wermke

Research output: Contribution to journal › Article › peer-review

32 Scopus citations

Abstract

This paper addresses the problem of classification of infants with cleft palate. A hidden Markov model (HMM)-based cry classification algorithm is presented. A parallel HMM (PHMM) for coping with age masking, based on a maximum-likelihood decision rule, is introduced. The performance of the proposed algorithm under different model parameters and different feature sets is studied using a database of cries of infants with cleft palate (CLP). The proposed algorithm yields an average of 91% correct classification rate in a subject- and age-dependent experiment. In addition, it is shown that the PHMM significantly outperforms the HMM performance in classification of cries of CLP infants of different ages.

Original language	English
Pages (from-to)	965-975
Number of pages	11
Journal	Medical and Biological Engineering and Computing
Volume	46
Issue number	10
DOIs	https://doi.org/10.1007/s11517-008-0334-y
State	Published - 27 Mar 2008

Keywords

Classification
Cleftlip and palate
Infantcry
Maximum likelihood
Parallel hidden Markov model

ASJC Scopus subject areas

Biomedical Engineering
Computer Science Applications

Access to Document

10.1007/s11517-008-0334-y

Cite this

@article{4baf46599b9d4a8d856dafb2a383bda9,

title = "Classification of cries of infants with cleft-palate using parallel hidden Markov models",

abstract = "This paper addresses the problem of classification of infants with cleft palate. A hidden Markov model (HMM)-based cry classification algorithm is presented. A parallel HMM (PHMM) for coping with age masking, based on a maximum-likelihood decision rule, is introduced. The performance of the proposed algorithm under different model parameters and different feature sets is studied using a database of cries of infants with cleft palate (CLP). The proposed algorithm yields an average of 91% correct classification rate in a subject- and age-dependent experiment. In addition, it is shown that the PHMM significantly outperforms the HMM performance in classification of cries of CLP infants of different ages.",

keywords = "Classification, Cleftlip and palate, Infantcry, Maximum likelihood, Parallel hidden Markov model",

author = "Dror Lederman and Ehud Zmora and Stephanie Hauschildt and Angelika Stellzig-Eisenhauer and Kathleen Wermke",

year = "2008",

month = mar,

day = "27",

doi = "10.1007/s11517-008-0334-y",

language = "English",

volume = "46",

pages = "965--975",

journal = "Medical and Biological Engineering and Computing",

issn = "0140-0118",

publisher = "Springer Verlag",

number = "10",

}

TY - JOUR

T1 - Classification of cries of infants with cleft-palate using parallel hidden Markov models

AU - Lederman, Dror

AU - Zmora, Ehud

AU - Hauschildt, Stephanie

AU - Stellzig-Eisenhauer, Angelika

AU - Wermke, Kathleen

PY - 2008/3/27

Y1 - 2008/3/27

N2 - This paper addresses the problem of classification of infants with cleft palate. A hidden Markov model (HMM)-based cry classification algorithm is presented. A parallel HMM (PHMM) for coping with age masking, based on a maximum-likelihood decision rule, is introduced. The performance of the proposed algorithm under different model parameters and different feature sets is studied using a database of cries of infants with cleft palate (CLP). The proposed algorithm yields an average of 91% correct classification rate in a subject- and age-dependent experiment. In addition, it is shown that the PHMM significantly outperforms the HMM performance in classification of cries of CLP infants of different ages.

AB - This paper addresses the problem of classification of infants with cleft palate. A hidden Markov model (HMM)-based cry classification algorithm is presented. A parallel HMM (PHMM) for coping with age masking, based on a maximum-likelihood decision rule, is introduced. The performance of the proposed algorithm under different model parameters and different feature sets is studied using a database of cries of infants with cleft palate (CLP). The proposed algorithm yields an average of 91% correct classification rate in a subject- and age-dependent experiment. In addition, it is shown that the PHMM significantly outperforms the HMM performance in classification of cries of CLP infants of different ages.

KW - Classification

KW - Cleftlip and palate

KW - Infantcry

KW - Maximum likelihood

KW - Parallel hidden Markov model

UR - http://www.scopus.com/inward/record.url?scp=53149093267&partnerID=8YFLogxK

U2 - 10.1007/s11517-008-0334-y

DO - 10.1007/s11517-008-0334-y

M3 - Article

C2 - 18368431

AN - SCOPUS:53149093267

VL - 46

SP - 965

EP - 975

JO - Medical and Biological Engineering and Computing

JF - Medical and Biological Engineering and Computing

SN - 0140-0118

IS - 10

ER -

Classification of cries of infants with cleft-palate using parallel hidden Markov models

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this