Window Size Versus Accuracy Experiments in Voice Activity Detectors
Sound
2026-01-27 v1 Computation and Language
Audio and Speech Processing
Abstract
Voice activity detection (VAD) plays a vital role in enabling applications such as speech recognition. We analyze the impact of window size on the accuracy of three VAD algorithms: Silero, WebRTC, and Root Mean Square (RMS) across a set of diverse real-world digital audio streams. We additionally explore the use of hysteresis on top of each VAD output. Our results offer practical references for optimizing VAD systems. Silero significantly outperforms WebRTC and RMS, and hysteresis provides a benefit for WebRTC.
Cite
@article{arxiv.2601.17270,
title = {Window Size Versus Accuracy Experiments in Voice Activity Detectors},
author = {Max McKinnon and Samir Khaki and Chandan KA Reddy and William Huang},
journal= {arXiv preprint arXiv:2601.17270},
year = {2026}
}