@article {pub3293,
	title = {Feature Space SVM Adaptation for Speaker Adapted Word Prominence Detection
},
	author = {Andrea Schnall AND Martin Ernst Heckmann},
	year = {2018},
	month = {June},
	abstract = {Prosodic cues like the word prominence play a
fundamental role in human communication, e.g. to express
important information. Since different speakers use a wide
variety of features to express prominence, there is a large difference in performance between speaker dependently and
speaker independently trained models. To cope with these variations without training a new speaker dependent model, in
speech recognition speaker adaptation techniques like featurespace Maximum Likelihood Linear Regression (fMLLR) turned
out to be very useful. These methods are developed for GMM-HMM based classifiers under the assumption that the data can
be modeled as a mixture of Gaussian distributions. However, in many cases these assumptions are too restrictive. In particular
a discriminative classifier as an SVM often yields far superior results to a GMM. Therefore, we propose a new adaptation
method, which adapts the data to the radial basis function kernel of the SVM. To avoid overfitting we apply two regularization
terms. The first is based on fMLLR and the second is an L1 regularization to enforce a sparse transformation matrix. We
analyze the method in the context of speaker adaptation for word prominence detection, with varying amounts of adaptation
data and different weights of the regularization terms. We show that our novel method clearly outperforms fMLLR-GMM and
fMLLR-SVM based adaptation.
},
	publisher = {Elsevier},
	journal = {Computer Speech and Language}
}