Voice activity detection based on statistical models and machine learning approaches

The voice activity detectors (VADs) based on statistical models have shown impressive performances especially when fairly precise statistical models are employed. Moreover, the accuracy of the VAD utilizing statistical models can be significantly improved when machine-learning techniques are adopted to provide prior knowledge for speech characteristics. In the first part of this paper, we introduce a more accurate and flexible statistical model, the generalized gamma distribution (GCD) as a new model in the VAD based on the likelihood ratio test. In practice, parameter estimation algorithm based on maximum likelihood principle is also presented. Experimental results show that the VAD algorithm implemented based on GCD outperform those adopting the conventional Laplacian and Gamma distributions. In the second part of this paper, we introduce machine learning techniques such as a minimum classification error (MCE) and support vector machine (SVM) to exploit automatically prior knowl...

• Type: Journal
• Year: 2010
• Where: CSL
• Authors: Jong Won Shin, Joon-Hyuk Chang, Nam Soo Kim
• Keywords: Automated Reasoning, CSL 2010, Gamma Distributions, Prior Knowledge, Statistical Models