15 Monaural Speech Separation by Support Vector Machines : Bridging the Divide Between Supervised and Unsupervised Learning Methods

@inproceedings{Hochreiter200715MS,
  title={15 Monaural Speech Separation by Support Vector Machines : Bridging the Divide Between Supervised and Unsupervised Learning Methods},
  author={Sepp Hochreiter and Michael C. Mozer},
  year={2007}
}
We address the problem of identifying multiple independent speech sources from a single signal that is a mixture of the sources. Because the problem is ill-posed, standard independent component analysis (ICA) approaches which try to invert the mixing matrix fail. We show how the unsupervised problem can be transformed into a supervised regression task which is then solved by supportvector regression (SVR). It turns out that the linear SVR approach is equivalent to the sparse-decomposition… CONTINUE READING