A novel approach to a voice activity detector (VAD) in noisy environments is presented. The generalised Gaussian distribution (GGD) is employed as a parametric model for noisy speech, which enables tuning to the actual data. According to the experimental results, it was discovered that the proposed GGD model is more effective for the VAD algorithm compared to the conventional Laplacian model.
No takes yet. Share an insight, caveat, or question.
Chang et al. (2004) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: