Abstract
It has been stated over and over again, and it remains true at the time of this writing: speech recognition by machines is by far not as robust as recognition by humans. While human listeners apparently face little difficulty ignoring reverberation and background noise, and while healthy-of-hearing listeners can even recognize a speaker in babble noise at 0 dB signal-to-noise power ratio, machine performance degrades quite rapidly if the speech signal is degraded by acoustic environmental noise, reverberation, competing speakers or any other kind of distortion.
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
Baker, J., Deng, L., Glass, J., Khudanpur, S., Lee, C.H., Morgan, N., O’Shaughnessy, D.: Developments and directions in speech recognition and understanding, part 1. Signal Processing Magazine, IEEE 26(3), 75–80 (2009)
Baker, J., Deng, L., Glass, J., Khudanpur, S., Lee, C.H., Morgan, N., O’Shaughnessy, D.: Developments and directions in speech recognition and understanding, part 2. Signal Processing Magazine, IEEE 26(4), 78–85 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Haeb-Umbach, R., Kolossa, D. (2011). Introduction. In: Kolossa, D., Häb-Umbach, R. (eds) Robust Speech Recognition of Uncertain or Missing Data. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21317-5_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-21317-5_1
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21316-8
Online ISBN: 978-3-642-21317-5
eBook Packages: EngineeringEngineering (R0)