Citation :

Amkar Brahma, Manoj Kumar Deka, Pranchis Narzaree, Bijay Kumar Singh, "Towards Robust Identification of Age-Sensitive Acoustic Features for Developmental Speech Analysis in Low Resource Bodo Language," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 9, pp. 399-407, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I9P127

Abstract

Children’s speech exhibits wide variation because their vocal tract and articulatory system mature progressively with age, and thus, analysis of children's speech faces greater difficulty when compared to adults' speech. When the language is a low-resource language where only scarce child speech corpora are available and the development of speech has not been extensively explored, it becomes extremely difficult to build any sophisticated child speech technologies. This study investigates age-sensitive acoustic characteristics of child’s speech in the low-resource Bodo language using Mel-Frequency Cepstral Coefficients (MFCC) and their dynamic characteristics. The children's speech recordings from various ages groups are analyzed, and the MFCC, mean, MFCC variance, del-MFCC mean, and del-MFCC variance are computed from each of the segments to find age-varying features. Correlation analysis, linear regression and one-way ANOVA were employed to identify the acoustically varying features as per age. From the experiments, it was found that deltamean3, deltamean2, mean3, mean6, and mean13 possess a high association with speech speaker age at all the statistical analyses tests. The developmental profile of selected acoustic features shows that both spectro-temporal characteristics of speech are growing into stability as children progress in their age to demonstrate maturity in the mechanism of speech production. The analysis and research using these age-sensitive acoustic features may provide valuable directions to developmental speech research and help to develop useful child-based speech applications for low-resource languages like Bodo.

Keywords

Child speech, Age-sensitive acoustic features, Low-resource language, Mel-Frequency Cepstral Coefficients (MFCC), Statistical analysis, Speech signal processing.

References

[1] Sungbok Lee, Alexandros Potamianos, and Shrikanth Narayanan, “Acoustics of Children’s Speech: Developmental Changes of Temporal and Spectral Parameters,” The Journal of the Acoustical Society of America, vol. 105, no. 3, pp. 1455-1468, 1999.
[CrossRef] [Google Scholar] [Publisher Link]                                                                                     

[2] A. Potamianos, and S. Narayanan, “Robust Recognition of Children’s Speech,” IEEE Transactions on Speech and Audio Processing, vol. 11, no. 6, pp. 603-616, 2003. 
[CrossRef] [Google Scholar] [Publisher Link] 

[3] Serdar Yildirim et al., “Acoustic Analysis of Preschool Children’s Speech,” Proceedings of the International Congresses of Phonetic Sciences (ICPhS), pp. 949-952, 2003.
[Google Scholar]

[4] Shawn L. Nissen, and Robert Allen Fox, “Acoustic and Spectral Characteristics of Young Children’s Fricative Productions: A Developmental Perspective,” The Journal of the Acoustical Society of America, vol. 118, no. 4, pp. 2570-2578, 2005.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Sumanlata Gautam, and Latika Singh, “Developmental Pattern Analysis and Age Prediction by Extracting Speech Features and Applying Various Classification Techniques,” International Conference on Computing, Communication and Automation, Greater Noida, India, pp. 83-87, 2015.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Gaurav Aggarwal, and Latika Singh, “Age Classification with LPCC Features using SVM and ANN,” Information and Communication Technology for Competitive Strategies: Proceedings of Third International Conference on ICTCS, vol. 40, pp. 399-408, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Alexey Grigorev, Olga Frolova and Elena Lyakso, “Acoustic Features of Speech of Typically Developing Children Aged 5-16 Years,” Artificial Intelligence and Natural Language: 7^th International Conference, AINL 2018, St. Petersburg, Russia, vol. 930, pp. 152-163. 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Elena Lyakso, Olga Frolova, and Aleksandr Nikolaev, “Voice and Speech Features as a Diagnostic Symptom,” Psychological Applications Conference and Trends, vol. 202, pp. 359-363, 2021.
[Google Scholar]

[9] Elena Lyakso et al., “Speech Features of 13-15Year-Old Children with Autism Spectrum Disorders,” Speech and Computer: 22^nd International Conference, SPECOM 2020, St. Petersburg, Russia, vol. 12335, pp. 291-303, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Vishakha Kumari, Abhijit Sinha, and Hemant Kumar Kathania, “Role of Acoustics and Prosodic Features for Children’s Age Classification,” 2024 International Conference on Signal Processing and Communications (SPCOM), Bangalore, India, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[11] JunHwi Moon et al., “CSAF: Child-like Speech Augmentation Framework through Adult Speech Data Modulation,” KSII Transactions on Internet and Information Systems, vol. 19, no. 11, pp. 4119-4137, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Abhijit Sinha, “Effect of Speech Modification on Wav2Vec2 Models for Children Speech Recognition,” 2024 International Conference on Signal Processing and Communications (SPCOM), Bangalore, India, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Sonal Yadav et al., “A Review of Feature Extraction and Classification Techniques in Speech Recognition,” SN Computer Science, vol. 4, no. 6, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Pegah Ghahremani et al., “A Pitch Extraction Algorithm Tuned for Automatic Speech Recognition,” 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, pp. 2494-2498, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Jyoti Guglani, and A.N. Mishra, “Automatic speech Recognition System with Pitch Dependent Features for Punjabi Language on Kaldi Toolkit,” Applied Acoustics, vol. 167, pp. 1-3, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Chang-Sheng Yang, and Hideki Kasuya, “Uniform and non-Uniform Normalization of Vocal Tracts Measured by MRI Across Male, Female and Child Subjects,” IEICE Transactions on Information and Systems, vol. 78, no. 6, pp. 732-737, 1995.
[Google Scholar] [Publisher Link]

[17] Si-Ioi Ng, Cymie Wing-Yee Ng, and Tan Lee, “A Study on using Duration and Formant Features in Automatic Detection of Speech Sound Disorder in Children,” Proceedings Interspeech, pp. 4643-4647, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Samreen Naeem et al., “An Unsupervised Machine Learning Algorithms: Comprehensive Review,” International Journal of Computing and Digital Systems, vol. 13, no. 1, pp. 911-921, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Muhammad Usama et al., “Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges,” IEEE Access, vol. 7, pp. 65579-65615, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Thomas Drugman et al., “Traditional Machine Learning for Pitch Detection,” IEEE Signal Process Letters, vol. 25, no. 11, pp. 1745-1749, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[21] M.K. Benkaddour, “CNN based Features Extraction for Age Estimation and Gender Classification,” Informatica, vol. 45, no. 5, pp. 697-707, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Okko Räsänen, and Daniil Kocharov, “Age-Dependent Analysis and Stochastic Generation of Child-Directed Speech,” arXiv preprint arXiv, vol. 13, pp. 1-7, 2024.
[CrossRef] [Google Scholar] [Publisher Link]