Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199446,
        author = {Mrs. Boppena.Vijitha and Ragipani Srinayan Chary and Potharaju Sai varsha and Pothnak Varun and Manda Srihari Goud},
        title = {Women Safety Monitoring System using Speech Emotion Recognition with Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {12603-12611},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199446},
        abstract = {Ensuring women’s safety has become a critical global concern due to increasing incidents of harassment and violence. According to global crime analyses, a significant percentage of women experience unsafe conditions in public or private environments, highlighting the need for intelligent safety systems. Traditional solutions rely on manual activation, which can fail during emergencies. This research proposes an automated women safety monitoring system using speech emotion recognition and deep learning techniques. The system analyses audio signals and extracts Mel Frequency Cepstral Coefficients (MFCC) for feature representation. Multiple machines learning models, including Logistic Regression, Random Forest, Support Vector Machine, and XGBoost, are evaluated. A hybrid deep learning architecture combining Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Units (BiGRU) is proposed to enhance classification performance. Experimental evaluation on benchmark datasets such as TESS and SAVEE shows that the hybrid CNN-BiGRU model achieves an accuracy of 94.8%, outperforming traditional models such as SVM (87.2%) and Random Forest (89.5%). The system demonstrates high precision (93.6%) and recall (92.9%) in detecting distress-related emotions. These results indicate that the proposed approach is effective for real-time safety monitoring and automated alert generation.},
        keywords = {Women Safety, Speech Emotion Recognition, CNN-BiGRU, MFCC, Deep Learning, Distress Detection.},
        month = {April},
        }