The analysis of infant cry has become more prevalent due to advances in areas such as digital signal processing, pattern recognition and soft computing. The analysis of infant cry has changed the diagnostic ability of physicians to correctly diagnose new-born. This work presents an approach to decode baby talk by classifying infant cry signal. We use normal infant cry signal of ages 1day to six months old. In particular there are fixed cry attributes for a healthy infant cry, which can be classified into five groups such as: Neh, Eh, Owh, Eairh and Heh. The infant cry signal is segmented by using Pitch frequency and features are extracted using MFC (mel-frequency cepstrum) coefficients over MATLAB. Statistical properties are calculated for the extracted features of MFCC and KNN classifier is used to classify the cry signal. KNN is the most successful classifiers used for audio data when their temporal structure is not important. This study is based on five different databases such as, Neh, Eh, Owh, Eairh, and Heh databases. Each has 50 samples of data 40 samples used for training and 10 samples used for testing. Percentages of results are Neh 80%, Eh 90%, Owh 80%, Eairh 90%, and Heh 90% respectively. Decoding baby talk supports the mother's built-in intuition about knowing and responding to their baby's needs, and physician to treat infant early.

1. O. Wasz-Hockert, K. Michelsson, and J. Lind, Twenty-Five Years of Scandinavian Cry Research, New York, NY, USA, 1985.
2. J. Benson, Social and Emotional Development in Infancy and Early Childhood, Elsevier, 2009.
3. O. Wasz-Hockert, The Infant Cry: A Spectrographic and Auditory Analysis, Lippincott, Philadelphia, Pa, USA, 1968.
4. A. Divakaran, Multimedia Content Analysis: Theory and Applications (Signals and Communication Technology), Springer, 2009.
5. S. Orlandi, L. Bocchi, C. Manfredi, M. Puopolo, A. Guzzetta S. Vicari and M. L. Scattoni, "Study of cry patterns in infants at high risk for AUTISM" at Models and analysis of vocal emissions for biomedical applications at 7th international workshop on August 25-27, 2011 firenze, Italy.
6. J. O. Garcia and C. A. Reyes Garcia. Mel-frequency cepstrum coefficients extraction from infant cry for classification of normal and pathological cry with feed-forward neural networks. In Proceedings of the Interna- tional Joint Conference on Neural Networks, volume 4, pages 3140– 3145, July 2003.
7. G. Varallyay. The melody of crying. International Journal of Pediatric Otorhinolaryngology, 71(11):1699 – 1708, 2007.
8. P. Ruvolo and J. Movellan. Automatic cry detection in early childhood education settings. In 7th IEEE International Conference on Develop- ment and Learning (ICDL), pages 204–208, Aug. 2008.
9. A. Messaoud and C. Tadj. A cry-based babies identification system. In Proceedings of the 4th international conference on Image and signal processing, ICISP'10, pages 192–199, 2010.
10. G. Varallyay. Crysamples, http://sirkan. iit. bme. hu/ var- allyay/crysamples. htm, 2009.
11. A. M. Noll. Cepstrum pitch determination. The Journal of the Acoustical Society of America, 41(2):293–309, 1967.
12. D. Gerhard. Pitch extraction and fundamental frequency: History and current techniques. Technical report, University of Regina, Canada, 2003.
13. A. Klautau. The MFCC. Technical report, Signal Processing Lab, UFPA, Brasil, 2005.
14. T. van Waterschoot and M. Moonen. Fifty years of acoustic feedback control: State of the art and future challenges. Proceedings of the IEEE, 99(2):288 –327, Feb. 2011.
15. Dunstan Baby Ears Web Site Baby Ears by DBL Support http://www. dunstandbabay. com 2007.

Infant Cry Pitch Frequency Knn Mfcc