Name
Abstract | ||
|---|---|---|
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 (G@CD) 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 G@CD 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 knowledge obtained from the speech database, which can enhance the performance of the VAD. Firstly, we present a discriminative weight training method based on the MCE criterion. In this approach, the VAD decision rule becomes the geometric mean of optimally weighted likelihood ratios. Secondly, the SVM-based approach is introduced to assist the VAD based on statistical models. In this algorithm, the SVM efficiently classifies the input signal into two classes which are voice active and voice inactive regions with nonlinear boundary. Experimental results show that these training-based approaches can effectively enhance the performance of the VAD. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1016/j.csl.2009.02.003 | Computer Speech & Language |
Keywords | Field | DocType |
a priori snr,support vector machine,vad algorithm,predicted snr,precise statistical model,prior knowledge,a posteriori snr,maximum likelihood principle,statistical modeling,likelihood ratio test,optimally weighted likelihood ratio,minimum classification error,vad decision rule,generalized gamma,statistical model,machine learning,voice activity detection,flexible statistical model,gamma distribution,decision rule,parameter estimation,geometric mean,weight training,likelihood ratio | Speech processing,Likelihood-ratio test,Computer science,Artificial intelligence,Discriminative model,Pattern recognition,Voice activity detection,Support vector machine,Speech recognition,Statistical model,Gamma distribution,Generalized gamma distribution,Machine learning | Journal |
Volume | Issue | ISSN |
24 | 3 | Computer Speech & Language |
Citations | PageRank | References |
33 | 1.47 | 18 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jong Won Shin | 1 | 215 | 21.85 |
| Joon-Hyuk Chang | 2 | 263 | 21.87 |
| Nam Soo Kim | 3 | 275 | 29.16 |