Name
Abstract | ||
|---|---|---|
Detecting the presence of speech in a noisy signal is an unsolved problem affecting numerous speech processing applications. This paper shows an effective method employing support vector machines (SVM) for voice activity detection (VAD) in noisy environments. The use of kernels in SVM enables to map the data into some other dot product space (called feature space) via a nonlinear transformation. The feature vector includes the subband signal-to-noise ratios of the input speech and a radial basis function (RBF) kernel is used as SVM model. It is shown the ability of the proposed method to learn how the signal is masked by the acoustic noise and to define an effective non-linear decision rule. The proposed approach shows clear improvements over standardized VADs for discontinuous speech transmission and distributed speech recognition, and other recently reported VADs. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1007/11760023_99 | ISNN (2) |
Keywords | Field | DocType |
noisy environment,speech recognition,effective method,input speech,svm-enabled voice activity detection,discontinuous speech transmission,feature vector,feature space,svm model,numerous speech processing application,effective non-linear decision rule,support vector machine,product space,radial basis function,decision rule,signal to noise ratio,speech processing,acoustic noise,voice activity detection | Noise,Kernel (linear algebra),Speech processing,Feature vector,Pattern recognition,Voice activity detection,Computer science,Support vector machine,Speech recognition,Artificial intelligence,Dot product,Artificial neural network | Conference |
Volume | ISSN | ISBN |
3972 | 0302-9743 | 3-540-34437-3 |
Citations | PageRank | References |
2 | 0.39 | 7 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Javier Ramírez | 1 | 656 | 68.23 |
| Pablo Yélamos | 2 | 2 | 0.39 |
| Juan Manuel Górriz Sáez | 3 | 289 | 35.14 |
| Carlos G. Puntonet | 4 | 163 | 23.59 |
| José C. Segura | 5 | 481 | 38.14 |