Abstract
The very first cry or the birth cry of an infant carries significant information about the health of an infant and hence, it is considered as the vital parameter in deciding the Apgar count. As an infant grows, the cry acoustics changes with the integration of vocal tract system. Infants are found to produce many sounds apart from crying, which reflect the learning mechanism of the infants of the language spoken in his or her surroundings or the environment. Along with this, infants who have distinct cry sounds or who require large amount of stimulation to produce a cry, are found to be at risk of sudden infant death syndrome (SIDS) or possible neurological disorders. In this paper, newborn infant cries are analyzed using features derived from fundamental frequency (F 0) contour or pitch contour, energy of the cry signal in different frequency sub-bands and unvoicing present in the infant’s cry. For the extraction of fundamental frequency, modified autocorrelation method is used and shown to perform better than traditional autocorrelation-based method. To identify the significance of these features in identifying the reason of crying, ANOVA analysis is applied on these features. It is observed that the F 0 features are not of significance in the newborn cry analysis and presence of unvoicing in the infant’s cry varies with the maturity of central nervous system (CNS) and is a discriminative feature of prime importance in newborn’s cry analysis. In birth cries, the mean percentage of unvoicing is 84.4 % which drops to 67.7 % in normal infants (20 days–3 months). Birth cry analysis shows that there is very less voicing and hence, less vibration of the vocal folds.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ali, M. Z. M., Mansor, W., Lee, Y. K., & Zabidi, A. (2012). Asphyxiated infant cry classification using simulink model Conference. In IEEE 8th International Colloquium on Signal Processing and its Applications, Malacca, Malaysia, 491–494.
Baeck, H. E., & Souza, M. N. (2001). Study of acoustic features of newborn cries that correlate with the context. In Proceedings of 23rd IEEE Annual International Conference of EMBS, Istanbul, 2174–2177.
Barajas-Montiel, S. E., & Reyes-Garcia, C. A. (2005). Identifying pain and hunger in infant cry with classifiers ensembles. International Conference on Intelligent Agents, Web Technologies and Internet Commerce, Vienna, 2, 770–775.
Bauer, H. R., & Zimmerman, L. (1994). Newborn human cries: Prenatal cocaine exposed and nonexposed. The Journal of the Acoustical Society of America, 95(5), 3013.
Buddha, N., & Patil, H. A. (2007). Corpora for analysis of infant cry. In International Conference on Speech Databases and Assessments, Oriental COCOSDA, Hanoi, Vietnam, 43-48
Chittora, A., & Patil, H. A. (2014). Use of glottal inverse filtering for asthma and HIE infant cries classification. In International Conference on Asian Language Processing (IALP) (pp. 158–161). Kuching, Sarawak.
Chittora, A., & Patil, H. A. (2015a). Significance of unvoiced segments and fundamental frequency for infant cry analysis. In P. Kral & V. Matousek (Eds.), Text, Speech and Dialogue (TSD), New York: Springer. LNAI 9302, pp. 273–281
Chittora, A., & Patil, H. A. (2015b). Classification of normal and pathological infant cries using bispectrum features. In 23rd European Signal Processing Conference (EUSIPCO)(pp. 639–643). Nice, France.
Chittora, A., & Patil, H. A. (2015c). Modified group delay-based features for Asthma and HIE infant cries classification. In P. Kral & V. Matousek (Eds.), 18th International Conference on Text, Speech and Dialogue (TSD) (pp. 595–602)., Lecture Notes in Artificial Intelligence (LNAI) New York: Springer.
Corwin, M. J., et al. (1995). Newborn acoustic cry characteristics of infants subsequently dying of sudden infant death syndrome. Pediatrics, 96(1), 73–77.
Garcia, J. O., & Garcia, C. A. R. (2003). Mel-frequency cepstrum coefficients extraction from infant cry for classification of normal and pathological cry with feedforward neural networks. In Proceedings of the International Joint Conference on Neural Networks (pp. 3140-3145). Portland.
Hariharan, M., Sindhu, R., & Yaacob, S. (2012). Normal and hypoacoustic infant cry signal classification using time-frequency analysis and general regression neural networks. Journal of Computer Methods and Programs in Biomedicine, Amsterdam: Elsevier, 108(2), 559–569.
Lederman, D. (2002). Automatic classification of infants’ cry. Masters Thesis, Ben- Gurion University of the Negev.
Lester, B. M. (1985). Introduction- There’s more to crying than meets the ear. In B. M. Lester & Z. C. F. Boukydis (Eds.), Infant crying- Theoritical and Research Perspective. New York: Plenum Press.
Manfredi, C., Tocchioni, V., & Bocchi, L. (2006). A robust tool for newborn infant cry analysis. In 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS) (pp. 509–512). New York.
Michelson, K., & Michelson, O. (1999). Phonation in newborn. International Journal of Pediatric Otorhinolaryngology, 49(1), S297–S301.
Nicollas, R., Giordano, J., & Ouaknine, M. (2012). The very first cry: A multidisciplinary approach toward a model. In Annals of Otology, Rhinology and Laryngology, Annals Pub. Co., 121(12), 821-826.
Petroni, M., Malowany, M. E., Johnston, C. C., & Stevens, B. J. (1994). A Crosscorrelation based method for improved visualization of infant cry vocalizations. In Canadian Conference on Electrical and Computer Engineering (pp. 25–28).
Petroni, M., Malowany, M. E., Johnston, C. C., & Stevens, B. J. (1995). A comparison of neural network architectures for the classification of three types of infant cry vocalizations. In IEEE 17th Annual Conference Engineering in Medicine and Biology Society (pp. 821–822). Canada.
Petroni, M., Malowany, A. S., Johnston, C. C., & Stevens, B. J. (2009). Classification of infant cry vocalizations using artificial neural networks, In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Georgia, USA, Vol. 5, 3475–3478.
Rabiner, L. R. (1977). On the use of autocorrelation analysis for pitch detection. IEEE Transactions on Acoustics, Speech and Signal Processing, 25(1), 24–33.
Reyes Galaviz O. F., Cano-Ortiz S. D., & Rayes-Garcia C. A. (2008). Evolutionary-neural system to classify infant cry units for pathologies identification in recently born babies. In 7th Mexican International Conference on Artificial Intelligence (pp. 330–335).
Saraswathy, J., Hariharan, M., Vijean, V., Yaacob, S., & Khairunizam, W. (2012). Performance comparison of Daubechies wavelet family in infant cry classification. In 8th International Colloquium on Signal Processing and its Applications (pp. 451–455).
Seshadri, G., & Yegnanarayana, B. (2009). Perceived loudness of speech based on the characteristics of glottal excitation source. The Journal of the Acoustical Society of America, 126(4), 2061–2071.
Singh, A. K., Mukhopadhyay, J., Kumar, S. S., & Rao, K. S. (2013). Infant cry recognition using excitation source features. In IEEE India conference (INDICON) (pp. 1–5).Mumbai, India.
Zabidi, A., Mansor, W., Khuan, L. Y., Sahak, R., & Rahman, F. Y. (2009). Mel-frequency cepstrum coefficient analysis of infant cry with hypothyroidism. In 5th International Colloquium on Signal Processing & Its Applications (CSPA) (pp. 204–208).
Acknowledgments
Authors would like to thank DA-IICT, Gandhinagar, India, for providing necessary resources for this study. We also like to thank Department of Electronics and Information Technology (DeitY) and Department of Science and Technology (DST), Government of India, New Delhi, India for partial support in providing resources for carrying out this research work. We acknowledge the help given by the members of Speech Research Lab, DA-IICT, Gandhinagar.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chittora, A., Patil, H.A. Newborn infant’s cry analysis. Int J Speech Technol 19, 919–928 (2016). https://doi.org/10.1007/s10772-016-9379-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10772-016-9379-8