Voice Activity Detection: Merging Source And Filter-based Information
2019 · Thomas Drugman, Yannis Stylianou, Yusuke Kida, et al.
Abstract
Voice Activity Detection (VAD) refers to the problem of distinguishing speech segments from background noise. Numerous approaches have been proposed for this purpose. Some are based on features derived from the power spectral density, others exploit the periodicity of the signal. The goal of this paper is to investigate the joint use of source and filter-based features. Interestingly, a mutual information-based assessment shows superior discrimination power for the source-related features, especially the proposed ones. The features are further the input of an artificial neural network-based classifier trained on a multi-condition database. Two strategies are proposed to merge source and filter information: feature and decision fusion. Our experiments indicate an absolute reduction of 3% of the equal error rate when using decision fusion. The final proposed system is compared to four state-of-the-art methods on 150 minutes of data recorded in real environments. Thanks to the robustness
Authors
(none)
Tags
Stats
Related papers
- Unsupervised Voice Activity Detection By Modeling Source And System Information Using Zero Frequency Filtering (2022)6.34
- Speech Enhancement Aided End-to-end Multi-task Learning For Voice Activity Detection (2020)11.49
- An Ensemble Svm-based Approach For Voice Activity Detection (2019)5.24
- Rule-embedded Network For Audio-visual Voice Activity Detection In Live Musical Video Streams (2020)4.52
- Self-adaptive Soft Voice Activity Detection Using Deep Neural Networks For Robust Speaker Verification (2019)6.77
- Personal VAD: Speaker-conditioned Voice Activity Detection (2019)13.05
- Rvad: An Unsupervised Segment-based Robust Voice Activity Detection Method (2019)0.00
- Waveform-based Voice Activity Detection Exploiting Fully Convolutional Networks With Multi-branched Encoders (2020)0.00