Survey on approaches to speech recognition in reverberant environments
Yoshioka T, Sehr A, Delcroix M, Kinoshita K, Maas R, Nakatani T, Kellermann W (2012)
Publication Language: English
Publication Status: Published
Publication Type: Conference contribution, Conference Contribution
Publication year: 2012
Pages Range: 1-4
Article Number: 6411845
Event location: Los Angeles
ISBN: 9780615700502
URI: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84874408684∨igin=inward
Abstract
This paper overviews the state of the art in reverberant speech processing from the speech recognition viewpoint. First, it points out that the key to successful reverberant speech recognition is to account for long-term dependencies between reverberant observations obtained from consecutive time frames. Then, a diversity of approaches that exploit the long-term dependencies in various ways is described, ranging from signal and feature dereverberation to acoustic model compensation tailored to reverberation. A framework for classifying those approaches is presented to highlight similarities and differences between them. © 2012 APSIPA.
Authors with CRIS profile
Armin Sehr
Professur für Signalverarbeitung
Roland Maas
Professur für Signalverarbeitung
Walter Kellermann
Professur für Signalverarbeitung
Involved external institutions
Japan (JP)How to cite
APA:
Yoshioka, T., Sehr, A., Delcroix, M., Kinoshita, K., Maas, R., Nakatani, T., & Kellermann, W. (2012). Survey on approaches to speech recognition in reverberant environments. In Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (pp. 1-4). Los Angeles, US.
MLA:
Yoshioka, Takuya, et al. "Survey on approaches to speech recognition in reverberant environments." Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Los Angeles 2012. 1-4.
BibTeX: Download