Voice and Noise Detection with AdaBoost
Tetsuya Takiguchi, N. Miyake, Hiroyoshi Matsuda, Yasuo Ariki · 2007
We proposed the sudden-noise detection and classification with Boosting. Experimental results show that the performance using AdaBoost is better than that of the conventional GMM-based method, especially at a high SNR (meaning, under low-power noise conditions). The reason is that Boosting could make a complex non-linear boundary fitting training data, while the GMM approach could not express the complex boundary because the GMM-based method calculates the mean and covariance of the training data only. Future research will include combining the noise detection and classification with noise reduction.