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{174482,
        author = {Ch. Sowmya and K.V. Satyanarayana and B. Yaamini Reddy and K. Gowtham Santhosh Kumar and D. Nikhil Kumar},
        title = {Voice Activity Detection Using Gaussian Mixture Models},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {4261-4266},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174482},
        abstract = {The rise of voice-driven human-machine interfaces has spurred advancements in both academic research and industry, with a focus on creating voice assistants that reliably process commands despite ambient noise. A foundational requirement for such systems is the accurate isolation of speech segments from background interference within audio streams. This study presents an innovative approach to voice activity detection (VAD) using Gaussian Mixture Models (GMMs) to differentiate speech from noise. The proposed method extracts a quartet of audio features— Mel-Frequency Cepstral Coefficients (MFCCs), Spectral Roll-Off, Spectral Centroid, and Zero-Crossing Rate—from 0.125-second audio intervals. These features are subsequently analyzed using a GMM, which models the data as two distinct probabilistic clusters representing speech and non-speech activity also male and female parts. This technique delivers a streamlined, noise-robust solution, achieving precise segmentation with minimal computational overhead. Experimental outcomes highlight its effectiveness in real-time applications, positioning it as a promising tool for enhancing voice interaction technologies in diverse, noisy environments.},
        keywords = {Voice Activity Detection, Gaussian Mixture Models, Speech Segmentation, Noise Robustness, Mel-Frequency Cepstral Coefficients, Audio Feature Extraction, Real-Time Processing.},
        month = {March},
        }