Abstract
The goal of this book was to develop an unsupervised speech controlled system which automatically adapts to several recurring users. They are allowed to operate the system without the requirement to attend a training. Instead, each user can directly use the speech controlled system without any constraints concerning vocabulary or the need to identify himself. Each utterance contains additional information about a particular speaker. The system can be incrementally personalized. Enrolled speakers have to be reliably identified to allow optimal speech decoding and continuous adjustment of the corresponding statistical models. New speaker profiles are initialized when unknown speakers are detected.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
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). Summary and Conclusion. In: Self-Learning Speaker Identification. Signals and Communication Technology. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19899-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-19899-1_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19898-4
Online ISBN: 978-3-642-19899-1
eBook Packages: EngineeringEngineering (R0)