Abstract
In this paper we examine two approaches for the automatic personalization of speech controlled systems. Speech recognition may be significantly improved by continuous speaker adaptation if the speaker can be reliably tracked. We evaluate two approaches for speaker identification suitable to identify 5-10 recurring users even in adverse environments. Only a very limited amount of speaker specific data can be used for training. A standard speaker identification approach is extended by speaker specific speech recognition. Multiple recognitions of speaker identity and spoken text are avoided to reduce latencies and computational complexity. In comparison, the speech recognizer itself is used to decode spoken phrases and to identify the current speaker in a single step. The latter approach is advantageous for applications which have to be performed on embedded devices, e.g. speech controlled navigation in automobiles. Both approaches were evaluated on a subset of the SPEECON database which represents realistic command and control scenarios for in-car applications.
This work has been conducted when Tobias Herbig and Franz Gerl were affiliated with Harman/Becker. Tobias Herbig is now with Nuance Communications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Furui, S.: Selected topics from 40 years of research in speech and speaker recognition. In: INTERSPEECH 2009, pp. 1–8 (2009)
Junqua, J.-C.: Robust Speech Recognition in Embedded Systems and PC Applications. Kluwer Academic Publishers, Dordrecht (2000)
Kuhn, R., Junqua, J.-C., Nguyen, P., Niedzielski, N.: Rapid speaker adaptation in eigenvoice space. IEEE Transactions on Speech and Audio Processing 8(6), 695–707 (2000)
Herbig, T., Gerl, F., Minker, W.: Fast adaptation of speech and speaker characteristics for enhanced speech recognition in adverse intelligent environments. In: The 6th International Conference on Intelligent Environments, IE 2010 (2010) (to appear)
Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted gaussian mixture models. Digital Signal Processing 10(1-3), 19–41 (2000)
Schukat-Talamazzini, E.G.: Automatische Spracherkennung. Vieweg (1995) (in German)
Class, F., Kaltenmeier, A., Regel-Brietzmann, P.: Optimization of an hmm - based continuous speech recognizer. In: EUROSPEECH 1993, pp. 803–806 (1993)
Class, F., Haiber, U., Kaltenmeier, A.: Automatic detection of change in speaker in speaker adaptive speech recognition systems. US 2003/0187645 A1 (2003)
Gauvain, J.-L., Lee, C.-H.: Maximum a posteriori estimation for multivariate gaussian mixture observations of markov chains. IEEE Transactions on Speech and Audio Processing 2(2), 291–298 (1994)
Iskra, D., Grosskopf, B., Marasek, K., van den Heuvel, H., Diehl, F., Kiessling, A.: Speecon - speech databases for consumer devices: Database specification and validation. In: Proceedings of the Third International Conference on Language Resources and Evaluation, LREC 2002, pp. 329–333 (2002)
Herbig, T., Gerl, F., Minker, W.: Detection of unknown speakers in an unsupervised speech controlled system. In: Second International Workshop on Spoken Dialogue Systems Technology, IWSDS 2010 (2010) (to appear)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Herbig, T., Gerl, F., Minker, W. (2010). Evaluation of Two Approaches for Speaker Specific Speech Recognition. In: Lee, G.G., Mariani, J., Minker, W., Nakamura, S. (eds) Spoken Dialogue Systems for Ambient Environments. IWSDS 2010. Lecture Notes in Computer Science(), vol 6392. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16202-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-16202-2_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16201-5
Online ISBN: 978-3-642-16202-2
eBook Packages: Computer ScienceComputer Science (R0)