Abstract
At the end of this book an outlook for prospective applications and extensions of the techniques presented here is discussed. The outlook is intended to emphasize the potential for many applications and shall motivate for further research.
Adaptation
One important aspect of the speech controlled system presented in this book is to capture speaker characteristics fast and accurately for robust speaker identification. This task was accomplished by EV adaptation. To obtain optimal performance of EV adaptation, training and test conditions have to be balanced. Especially for applications in varying environments, re-estimating the eigenvoices may be applied to improve on the eigenspace given by the PCA [Nguyen et al., 1999].
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Herbig, T., Gerl, F., Minker, W. (2011). Outlook. In: Self-Learning Speaker Identification. Signals and Communication Technology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19899-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-19899-1_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19898-4
Online ISBN: 978-3-642-19899-1
eBook Packages: EngineeringEngineering (R0)