Machine Learning Analysis of Speech Detects Anxiety and Depression in Early Childhood
DOI:
https://doi.org/10.15662/IJEETR.2026.0802200Keywords:
Speech Emotion Recognition, CNN, MFCC, Deep Learning, Anxiety Detection, Depression AnalysisAbstract
Speech Emotion Recognition (SER) has emerged as a significant research area in machine learning and artificial intelligence, focusing on identifying human emotional states such as anxiety and depression from speech signals. This project presents a deep learning-based approach using hybrid 1D and 2D Convolutional Neural Networks (CNN) to improve the accuracy and robustness of emotion classification systems.
The model is trained and evaluated using benchmark datasets such as RAVDESS and TESS, incorporating feature extraction techniques including Mel-Frequency Cepstral Coefficients (MFCC), chroma features, and Mel-spectrograms. These features enable effective representation of both temporal and spectral characteristics of speech signals.
The integration of both temporal and spatial feature extraction through hybrid CNN architectures enhances the system’s ability to capture subtle emotional variations in speech. The proposed model achieves an accuracy of approximately 86–89%, outperforming traditional methods and demonstrating improved generalization on unseen data.
Furthermore, the system is computationally efficient and suitable for real-time implementation. This work highlights the potential of speech-based emotion recognition as a non-invasive and cost-effective solution for early detection of mental health conditions, contributing to advancements in intelligent healthcare systems and human-computer interaction
References
1. Mustaqueem khan and Soonil Kwon , “TC-Net: A Modest & Lightweight Emotion Recognition System Using Temporal Convolution Network”, vol. 26 , 2023.
2. BubaiMaji ,Monorama Swain and Mustaqeem Khan, “ Advanced Fusion- Based Emotion Recognition System Using a Dual-Attention Mechanism with Conv-Caps and Bi-GRU Features” , Electronics , vol. 11,pp. 1328, 2022.
3. Yan, Y.; Shen, X., “Research on Speech Emotion Recognition Based on AA-CBGRU Network”, Electronics, vol.11, pp.1409,2022
4. Fauzivy Reggiswarashari, Sari Widya Sihw, “Speech emotion recognition using 2Dconvolutional neural network,”vol.12,pp.6594,2022
5. Rakhi Rani Paul, Subrata Kumer Paul, Md. Ekramul Hamid,” A 2D Convolution Neural Network Based Method for Human Emotion Classification from Speech Signal,” IEEE Acess,vol.10,pp.72-77,2022
6. Mohammad Reza Falahzadeh,Edris Zaman Farsa,AliHarimi,Arash Ahmadi , “3D
7. Convolutional Neural Network for Speech Emotion Recognition With Its Realization on Intel CPU and NVIDIA GPU,” IEEE Access,vol.10,pp.112460- 112471,2022
8. E. Lieskovská, M. Jakubec, R. Jarina, and M. Chmulík, “A review on speech emotion recognition using deep learning and attention mechanism,” Electronics, vol.10,pp.1163,2021
9. Mustaqueem khan and SoonilKwon , “1D-CNN:Speech Emotion Recognition System Using a Stacked Network with Dilated CNN Features,”vol.67,pp.4039- 4059,materials & continua 2021.
10. Anbazhagan, K. (2024). Trustworthy and Adaptive AI Systems for Enterprise Analytics Cybersecurity and Decision Optimization Using API-First and Cloud-Native Architectures. International Journal of Technology, Management and Humanities, 10(03), 65-74.
11. Padmapriya, V. M., Thenmozhi, K., Hemalatha, M., Thanikaiselvan, V., Lakshmi, C., Chidambaram, N., & Rengarajan, A. (2025). Secured IIoT against trust deficit-A flexi cryptic approach. Multimedia Tools and Applications, 84(9), 5625-5652.
12. Soundappan, S. J. (2020). Big Data Analytics in Healthcare: Applications for Pandemic Forecastin. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 3(1), 2248-2253.
13. Mathew, A., & Alex, H. (2023, January). Hyper automation and augmented intelligence. In 2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT) (pp. 1230-1234). IEEE.
14. Murugeshwari, B., Sudharson, K., Panimalar, S. P., Shanmugapriya, M., & Abinaya, M. (2020). SAFE–Secure Authentication in Federated Environment using CEG Key code.
15. Anand, L., Tyagi, R., & Mehta, V. (2024, January). Food recognition using deep learning for recipe and restaurant recommendation. In Proceedings of Eighth International Conference on Information System Design and Intelligent Applications (pp. 269-279). Singapore: Springer Nature Singapore.
