Abstract
In this paper, significance of unvoiced segments and fundamental frequency (\(F_0\)) in infant cry analysis is investigated. To find out the unvoiced segments from the infant cry \(F_0\) contour is used. For extraction of \(F_0\) contour, Teager Energy operator (TEO) based pitch extraction algorithm is used. TEO gives the running estimate of the signal energy in terms of its amplitude and instantaneous frequency. To quantify the importance of proposed features in infant cry analysis of variance (ANOVA) method is applied. It has been found that quantification of unvoiced segments and fundamental frequency in the cry, deliver information about the maturation of cry production system. In infant cry analysis, presence of high unvoicing ratio in a cry cannot be attributed to presence of pathology, like adult vocal fold pathological sounds.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Xie, Q., Ward, R.K., Laszlo, C.A.: Determining normal infants’ level-of-distress from cry sounds. In: Canadian Conference on Electrical and Computer Engineering, pp. 1094–1096 (1993)
Patil, H.A.: Cry Baby: Using spectrographic analysis to assess neonatal health from an infants cry. In: Neustein, A. (ed.) Advances in Speech Recognition, Mobile Environments, Call Centers and Clinics, pp. 323–348. Springer (2010)
Lester, B.M.: Infant Crying: Theoretical and Research Perspective. Plenum Pub. Corp., NY (1985)
Petroni, M., Malowany, M.E., Johnston, C.C., Stevens, B.J.: A comparison of neural network architectures for the classification of three types of infant cry vocalizations. In: IEEE 17th Annual Conference on Engineering in Medicine and Biology Society (EMBS), vol. 1, pp. 821–822 (1995)
Garcia, J.O., Reyes Garcia, C.A.: Mel-frequency cepstrum coefficients extraction from infant cry for classification of normal and pathological cry with feed-forward neural networks. In: Proc. of the Int. Joint Conf. on Neural Networks, vol. 4, pp. 3140–3145 (2003)
Lederman, D., Cohen, A., Zmora, E., Wermke, K., Hauschildt, S., Stellzig-Eisenhauer, A.: On the use of hidden Markov models in infants’ cry classification. In: 22nd Convention of Electrical and Electronics Engineers, pp. 350–352 (2002) (in Israel)
Patil, H.A.: Infant identification from their cry. In: 7th Int. Conf. on Advances in Pattern Recognition, ICAPR 2009, vol. 4, pp. 107–110 (2009)
Patil, H.A., Srikant, V.: Effectiveness of Teager energy operator for epoch detection from speech signals. Inter. J. of Speech Technology 14(4), 321–337 (2011)
Buddha, N., Patil, H.A.: Corpora for analysis of infant cry. In: Int. Conf. on Speech Databases and Assessments, Oriental COCOSDA, Hanoi, Vietnam (2007)
Details of ANOVA. http://www.psychstat.missouristate.edu/introbook/sbk27.html (last Accessed on January 18th, 2014)
Fuamenya, N.A., Robb, M.P., Wermke, K: Noisy but Effective: Crying Across the First 3 Months of Life. J. Voice (2014) (in Press)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chittora, A., Patil, H.A. (2015). Significance of Unvoiced Segments and Fundamental Frequency in Infant Cry Analysis. In: Král, P., Matoušek, V. (eds) Text, Speech, and Dialogue. TSD 2015. Lecture Notes in Computer Science(), vol 9302. Springer, Cham. https://doi.org/10.1007/978-3-319-24033-6_31
Download citation
DOI: https://doi.org/10.1007/978-3-319-24033-6_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24032-9
Online ISBN: 978-3-319-24033-6
eBook Packages: Computer ScienceComputer Science (R0)