Skip to main content

Evaluating New Set of Acoustical Features for Cry Signal Classification

  • 85 Accesses

Part of the Lecture Notes in Computer Science book series (LNCS,volume 13264)


Searching for new features that contribute to the improvement of the performance of classification algorithms within the scientific area of infant crying classification for diagnostic purposes is a priority. Although several studies have suggested that some acoustic features present in the spectrogram of the signal of infant crying: stridor, melody, and shifts, could be interesting to reflect the pathological status of the newborn independently, a deeper study is still missing. This paper aims to demonstrate the potential of those attributes not sufficiently addressed in the state of the art of cry analysis when they’re properly combined. For this purpose, the Random Forest and k-Nearest Neighbor classification algorithms are used. The set of input vectors to the classifier also incorporates other well-known cry features that have proven to be effective in cry classification such as the Mel Frequency Cepstral Coefficients (MFCCs), fundamental frequency (F0), and the energy (E). The 10-fold cross-validation method was also used to evaluate the classifier performance as well as some standard metrics were used to evaluate the classifier results. Finally, a binary classifier for Central Nervous System (CNS) disorders with a Hypoxia background is proposed. The used experimental corpus comprises 616 samples of 1-s duration (253 pathological and 363 normal), corresponding to 54 children in age ranging from 0 to 3 months. The experimental results support the validity of the proposed feature set (stridor, melody, and shifts) for a child crying classification task as diagnostic method.


  • Cry classification
  • MFCC
  • Qualitative crying features

This is a preview of subscription content, access via your institution.

Buying options

USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-031-07750-0_14
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
USD   59.99
Price excludes VAT (USA)
  • ISBN: 978-3-031-07750-0
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   79.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.


  1. 1.

    Two classes derived from six clinical control groups just for medical purpose.


  1. Varallyay, G., Benyo, Z., Illenyi, A., Farkas, Z., Kovacs, L.: Acoustic analysis of the infant cry: classical and new methods. In: 26th Annual International Conference of the IEEE EM BS, pp. 313–316. San Francisco, CA, USA (2004)

    Google Scholar 

  2. Varallyay, G.: Future prospects of the infant cry in the medicine. Periodica Polytechnica Ser. El. Eng. 50(1–2), 47–62 (2006)

    Google Scholar 

  3. Lederman, D.: Estimation of infant’s cry fundamental frequency using a modified SIFT algorithm. arXiv:1009.2796v1 [cs. SD] 14 Sep, pp. 1–5 (2010)

  4. Osmani, A., Hamidi, M., Chibani, A.: Machine learning approach for infant cry interpretation. In: Proceedings – International Conference on Tools with Artificial Intelligence, ICTAI. (2018).

  5. Huckvale, M.: Neural network architecture that combines temporal and summative features for infant cry classification. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH in the Interspeech 2018 Computational Paralinguistic Challenge, pp. 137–141 (2018).

  6. Chittora, A., Patil, H.A.: Significance of unvoiced segments and fundamental frequency in infant cry analysis. In: Král, P., Matoušek, V. (eds.) TSD 2015. LNCS (LNAI), vol. 9302, pp. 273–281. Springer, Cham (2015).

    CrossRef  Google Scholar 

  7. Orlandi, S., Reyes Garcia, C.A., Bandini, A., Donzelli, G., Manfredi, C.: Application of pattern recognition techniques to the classification of full-term and preterm infant cry. J. Voice. 30(6), 656–663 (2016).

    CrossRef  Google Scholar 

  8. Zabidi, A., Khuan, L. Y., Mansor, W., Yassin, I. M., Sahak, R.: Detection of infant hypothyroidism with mel frequency cepstrum analysis and multi-layer perceptron classification. In: Proceedings -CSPA 2010: 2010 6th International Colloquium on Signal Processing and Its Applications, pp. 140–144 (2010).

  9. Gu, G., Shen, X., Xu, P.: A set of DSP system to detect baby crying. In: Proceedings of 2018 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2018, pp. 411–415 (2018).

  10. Galaviz, O.F.R., García, C.A.R.: Infant cry classification to identify hypo acoustics and asphyxia comparing an evolutionary-neural system with a neural network system. In: Gelbukh, A., de Albornoz, Á., Terashima-Marín, H. (eds.) MICAI 2005. LNCS (LNAI), vol. 3789, pp. 949–958. Springer, Heidelberg (2005).

    CrossRef  Google Scholar 

  11. Liu, L., Li, W., Wu, X., Zhou, B.X.: Infant cry language analysis and recognition: an experimental approach. IEEE/CAA J. Autom. Sin. 6(3), 778–788 (2019).

    CrossRef  Google Scholar 

  12. Franti, E., Ispas, I., Dascalu, M.: Testing the Universal Baby Language hypothesis - automatic infant speech recognition with CNNs. In: 2018 41st International Conference on Telecommunications and Signal Processing, TSP 2018, pp. 1–4 (2018).

  13. Le, L., Kabir, A.N.M.H., Ji, C., Basodi, S., Pan, Y.: Using transfer learning, SVM, and ensemble classification to classify baby cries based on their spectrogram images. In: Proceedings - 2019 IEEE 16th International Conference on Mobile Ad Hoc and Smart Systems Workshops, MASSW 2019. (2019).

  14. Chang, C.-Y., Tsai, L.-Y.: A CNN-based method for infant cry detection and recognition. In: Barolli, L., Takizawa, M., Xhafa, F., Enokido, T. (eds.) WAINA 2019. AISC, vol. 927, pp. 786–792. Springer, Cham (2019).

    CrossRef  Google Scholar 

  15. Felipe, G.Z., et al.: Identification of infants’ cry motivation using spectrograms. In: 2019 International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 181–186 (2019).

  16. Michelsson, K.: Cry characteristics in sound spectrographic cry analysis. In: Murry, T., Murry, J. (eds.) Infant Communication: Cry and Early Speech, pp. 85–105. College-Hill Press, Houston (1980)

    Google Scholar 

  17. Cano, S., Suaste, I., Escobedo, D., Reyes-García, C.A., Ekkel, T.: A combined classifier of cry units with new acoustic attributes. In: Martínez-Trinidad, J Francisco, Carrasco Ochoa, J.A., Kittler, J. (eds.) CIARP 2006. LNCS, vol. 4225, pp. 416–425. Springer, Heidelberg (2006).

    CrossRef  Google Scholar 

  18. Reyes-García, C.A., Torres-García, A.A., RuizDiaz, M.A.: Extracción de Características Cualitativas del Llanto de Bebé y su Clasificación para la Identificación de Patologías Utilizando Modelos Neuro-Difusos. In: Memorias del Congreso Nacional de Ingeniería Biomédica, vol. 5, no. 1, pp. 106–109 (2018)

    Google Scholar 

  19. Wasz-Höckert, O., Koivisto, M., Vuorenkoski, V., Partanen, T., Lind, J.: Spectrographic analysis of pain cry in hyperbilirubinemia. Biol. Neonate. 17, 260–271 (1971)

    CrossRef  Google Scholar 

  20. Michelsson, K., Sirviö, P., Wasz-Höckert, O.: Pain cry in full-term asphyxiated newborninfants correlated with late findings. Acta Paediatr. Scand. 66(5), 611–616 (1977)

    CrossRef  Google Scholar 

  21. Michelsson, K., Sirviö, P., Wasz- Höckert, O.: Sound spectrographic cry analysis of infants with bacterial meningitis. Dev Med Child Neurol. 19(3), 309–315 (1977). PMID: 18378

    CrossRef  Google Scholar 

  22. Hariharan, M., Yaacob, S., Awang, S.A.: Pathological infant cry analysis using wavelet packet transform and probabilistic neural network. Expert Syst. Appl. 38(12), 15377–15382 (2011).

    CrossRef  Google Scholar 

  23. Escobedo, D., Cano, S., Coello, E., Regueiferos, L., Capdevila, L.: Rising shift of pitch frequency in the infant cry of some pathologic cases. In: 2nd International Conference, MAVEBA 2001, Firenze, Italy (2001)

    Google Scholar 

Download references


This work has been fully supported by the Belgian Development Cooperation through VLIR-UOS (Flemish Interuniversity Council-University Cooperation for Development) in the context of the Institutional University Cooperation programme with Universidad de Oriente.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Sergio Daniel Cano-Ortiz .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Cano-Ortiz, S.D., Martinez-Canete, Y., Veranes-Vicet, L. (2022). Evaluating New Set of Acoustical Features for Cry Signal Classification. In: Vergara-Villegas, O.O., Cruz-Sánchez, V.G., Sossa-Azuela, J.H., Carrasco-Ochoa, J.A., Martínez-Trinidad, J.F., Olvera-López, J.A. (eds) Pattern Recognition. MCPR 2022. Lecture Notes in Computer Science, vol 13264. Springer, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-07749-4

  • Online ISBN: 978-3-031-07750-0

  • eBook Packages: Computer ScienceComputer Science (R0)