Classification of normal and pathological infant cries using bispectrum features

In this paper, bispectrum-based feature extraction method is proposed for classification of normal vs. pathological infant cries. Bispectrum is computed for all segments of normal as well as pathological cries. Bispectrum is a two-dimensional (2-D) feature. A tensor is formed using these bispectrum features and then for feature reduction, higher order singular value decomposition theorem (HOSVD) is applied. Our experimental results show 70.56 % average accuracy of classification with support vector machine (SVM) classifier, whereas baseline features, viz., MFCC, LPC and PLP gave classification accuracy of 52.41 %, 61.27 % and 57.41 %, respectively. For showing the effectiveness of the proposed feature extraction method, a comparison with other feature extraction methods which uses diagonal slice and peaks and their locations as feature vectors is given as well.

[1]  A. S. Malowany,et al.  A crosscorrelation-based method for improved visualization of infant cry vocalizations , 1994, 1994 Proceedings of Canadian Conference on Electrical and Computer Engineering.

[2]  Carlos Dias Maciel,et al.  Analysis of Voice Pathology Evolution Using Entropy Rate , 2008, 2008 Tenth IEEE International Symposium on Multimedia.

[3]  Sergio Daniel Cano-Ortiz,et al.  Validation of the Cry Unit as Primary Element for Cry Analysis Using an Evolutionary-Neural Approach , 2008, 2008 Mexican International Conference on Computer Science.

[4]  A. S. Malowany,et al.  A comparison of neural network architectures for the classification of three types of infant cry vocalizations , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[5]  Amy Neustein.  Advances in Speech Recognition: Mobile Environments, Call Centers and Clinics , 2010 .

[6]  A. Cohen,et al.  On the use of hidden Markov models in infants' cry classification , 2002, The 22nd Convention on Electrical and Electronics Engineers in Israel, 2002..

[7]  Joos Vandewalle,et al.  A Multilinear Singular Value Decomposition , 2000, SIAM J. Matrix Anal. Appl..

[8]  Ieee Staff.  2017 25th European Signal Processing Conference (EUSIPCO) , 2017 .

[9]  He Wei,et al.  Bispectrum-based radar target classification , 1998, ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344).

[10]  C. L. Nikias,et al.  Signal processing with higher-order spectra , 1993, IEEE Signal Processing Magazine.

[11]  H. A. Patil,et al.  “Cry Baby”: Using Spectrographic Analysis to Assess Neonatal Health Status from an Infant’s Cry , 2010 .

[12]  Wei Liu,et al.  Feature Extraction and Classification Based on Bispectrum for Underwater Targets , 2010, 2010 International Conference on Intelligent System Design and Engineering Application.

[13]  M.R. Raghuveer,et al.  Bispectrum estimation: A digital signal processing framework , 1987, Proceedings of the IEEE.

[14]  Yi Liu,et al.  Feature Extraction of Lung Sounds Based on Bispectrum Analysis , 2010, 2010 Third International Symposium on Information Processing.

[15]  Alfred S. Malowany,et al.  A new, robust vocal fundamental frequency (F/sub 0/) determination method for the analysis of infant cries , 1994, Proceedings of IEEE Symposium on Computer-Based Medical Systems (CBMS).

[16]  Alfred S. Malowany,et al.  Classification of infant cry vocalizations using artificial neural networks (ANNs) , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[17]  Sergio Daniel Cano-Ortiz,et al.  Evolutionary-Neural System to Classify Infant Cry Units for Pathologies Identification in Recently Born Babies , 2008, 2008 Seventh Mexican International Conference on Artificial Intelligence.

[18]  A. S. Malowany,et al.  A robust and accurate cross-correlation-based fundamental frequency (F/sub 0/) determination method for the improved analysis of infant cries , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[19]  Hemant A. Patil,et al.  Data collection and corpus design for analysis of nonnal and pathological infant cry , 2013, 2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE).

[20]  J.O. Garcia,et al.  Mel-frequency cepstrum coefficients extraction from infant cry for classification of normal and pathological cry with feed-forward neural networks , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[21]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.