Infants Cry Classification of Physiological State Using Cepstral and Prosodic Acoustic Features


  • Ramon L. Rodriguez College of Computer Studies, National University, Philippines
  • Susan S. Caluya College of Computer Studies, National University, Philippines


Audio Features, Audio Signal, Infants Cry, Infants State, Machine Learning Algorithms,


Infants cry to express their emotional, psychological and physiological states. The research paper investigates if cepstral and prosodic audio features are enough to classify the infants’ physiological states such as hunger, pain and discomfort. Dataset from our previous paper was used to train the classification algorithm. The results showed that the audio features could classify an infant’s physiological state. We used three classification algorithms, Decision Tree (J48), Neural Network and Support Vector Machine in developing the infant physiological model. To evaluate the performance of the infant physiological state model, Precision, Recall and F-measure were used as performance metrics. Comparison of the cepstral and prosodic audio feature is presented in the paper. Our findings revealed that Decision Tree and Multilayer Perceptron performed better both for cepstral and prosodic feature. It is noted the cepstral feature yielded better result compare with prosodic feature for the given dataset with correctly classified instances ranging from 87.64% to 90.80 with an overall kappa statistic ranging from 0.47 – 0.64 using cepstral feature.


J. Zeman, “Emotional Development – Early Infancy, Later Infancy Months,” Retrieved from Emotional-Development.html.

T. Fuhr, H. Reetz, and C. Wegener, “Comparison of Supervisedlearning Models for Infant Cry Classification,” Int. J. Health Professionals, vol. 2, no. 1, pp 4–15, 2015, doi: 10.1515/ijhp-2015- 0005.

M. Petroni, A.S. Malowany, C.C. Johnston, and B.J. Stevens, “A Comparison of Neural Network Architectures for the Classification of Three Types of Infant Cry Vocalizations,” in Proc. 17th Annu. Conf. of IEEE Eng. in Medicine and Biology Soc., Montreal (Quebec, Canada), Sep. 1995, vol. 2, pp. 975–976, doi: 10.1109/IEMBS.1995.575380.

S. Barajas-Montiel and C. Reyes-Garcia, “Identifying Pain and Hunger in Infant Cry with Classifiers Ensembles,” in Proc. Int. Conf. on Comput. Intell. for Modelling, Control and Autom. and Int. Conf. on Intell. Agents, Web Technol. and Internet Commerce (CIMCAIAWTIC), Vienna (Austria), Nov. 2005, vol. 2, pp. 770–775, doi: 10.1109/CIMCA.2005.1631561.

J. Orozco and C.A. Reyes-Garcia, “Implementation and Analysis of Training Algorithms for the Classification of Infant Cry with FeedForward Neural Networks,” in Proc. IEEE Int. Symp. on Intell. Signal Process., Budapest (Hungary), Sep. 2003, pp. 271–276. doi: 10.1109/ ISP.2003.1275851

R. Cohen and Y. Lavner, “Infant Cry Analysis and Detection,” in Proc. IEEE 27th Conv. of Elect. and Electron. Engineers in Israel (IEEEI), Eilat (Israel), Nov. 2012, doi: 10.1109/EEEI.2012.6376996.

J. Saraswathy, M. Hariharan, S. Yaacob, and W. Khairunizam, “Automatic Classification of Infant Cry: A Review,” in Proc. Int. Conf. on Biomed. Eng. (ICoBE), Penang (Malaysia), Feb. 2012, pp. 543–548, doi: 10.1109/ICoBE.2012.6179077.

Y. Abdulaziz and S.M.S. Ahmad, “Infant Cry Recognition System: A Comparison of System Performance Based on Mel Frequency and Linear Prediction Cepstral Coefficients,” in Proc. Int. Conf. on Inform. Retrieval and Knowl. Manag., Shah Alam (Selangor, Malaysia), Mar. 2010, pp. 260–263, doi: 10.1109/INFRKM.2010.5466907.

S.S. Jagtap, P.K. Kadbe, and P.N. Arotale, “System Propose for Be Acquainted with Newborn Cry Emotion Using Linear Frequency Cepstral Coefficient,” in. Proc. Int. Conf. on Elect., Electron., and Optimization Techn. (ICEEOT), Chennai (India), Mar. 2016, pp. 238– 242, doi: 10.1109/ICEEOT.2016.7755094.

A.K. Singh, J. Mukhopadhyay, and K.S. Rao, “Classification of Infant Cries Using Epoch and Spectral Features,” in Proc. Nat. Conf. on Commun. (NCC), New Delhi (India), Feb. 2013, doi: 10.1109/NCC. 2013.6487999.

M.J. Kim, Y. Kim, S. Hong, and H. Kim, “ROBUST Detection of Infant Crying in Adverse Environments Using Weighted Segmental Two-dimensional Linear Frequency Cepstral Coefficients,” in Proc. IEEE Int. Conf. on Multimedia and Expo Workshops (ICMEW), San Jose, (CA, USA), Jul. 2013, doi: 10.1109/ICMEW.2013.6618321.

S. Yamamoto, Y. Yoshitomi, M. Tabuse, K. Kushida, and T. Asada, “Recognition of a Baby’s Emotional Cry Towards Robotics Baby Caregiver,” Int. J. Advanced Robot. Syst., vol. 10, no. 2, Feb. 2013, doi: 10.5772/55406.

A.M. Prathibha, P. Raju, S. Halvi, and S.B. Satish, “An Eclectic Approach for Detection of Infant Cry and Wireless Monitoring of Swinging Device as an Alternative Warning System for Physically Impaired and Better Neonatal Growth,” World J. Sci. and Technol., vol. 2, no. 5, pp. 62–65, May 2012.

P. Ruvolo and J. Movellan, “Automatic Cry Detection in Early Childhood Education Settings,” in Proc. 7th IEEE Int. Conf. on Develop. and Learn. (ICDL), Monterey (CA, USA), Aug. 2008, pp. 204–208, doi: 10.1109/DEVLRN.2008.4640830.

L. Abou-Abbas, C. Tadj, C. Gargour, and L. Montazeri, “Expiratory and Inspiratory Cries Detection Using Different Signals’ Decomposition Techniques,” J. Voice, vol. 31, no. 2, pp. 259.e13– 259.e28, Mar. 2017, doi: 10.1016/j.jvoice.2016.05.015.

H.F. Alaie, L. Abou-Abbas, and C. Tadj, “Cry-based Infant Pathology Classification Using GMMs,” Speech Commun., vol. 77, pp. 28–52, Mar. 2016, doi: 10.1016/j.specom.2015.12.001.

R. Rodriguez and S. Caluya, “Waah: Infants Cry Classification of Physiological State Based on Audio Features,” in Proc. 5th Int. Conf. on Soft Comput., Intell. Syst. and Inf. Technol. (ICSIIT), Kuta (Bali, Indonesia), Sep. 2017, pp. 7–10, doi: 10.1109/ICSIIT.2017.24.




How to Cite

Rodriguez, R. L., & Caluya, S. S. (2018). Infants Cry Classification of Physiological State Using Cepstral and Prosodic Acoustic Features. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 10(2-3), 193–196. Retrieved from