We consider the task of discriminating speech and non-speech in noisy environments. Previously, Mesgarani et. al [1] achieved state-of-the-art performance using a cortical representation of sound in conjunction with a feature reduction algorithm and a nonlinear support vector machine classifier. In the present work, we show that we can achieve the same or better accuracy by using a linear regularized least squares classifier directly on the high-dimensional cortical representation; the new system is substantially simpler conceptually and computationally. We select the regularization constant automatically, yielding a parameter-free learning system. Intriguingly, we find that optimal classifiers for noisy data can be trained on clean data using heavy regularization.
Cite as: Rifkin, R., Mesgarani, N. (2006) Discriminating speech and non-speech with regularized least squares. Proc. Interspeech 2006, paper 1779-Wed3A1O.6, doi: 10.21437/Interspeech.2006-541
@inproceedings{rifkin06_interspeech,
author={Ryan Rifkin and Nima Mesgarani},
title={{Discriminating speech and non-speech with regularized least squares}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 1779-Wed3A1O.6},
doi={10.21437/Interspeech.2006-541}
}