Robust I-Vector Extraction for Neural Network Adaptation in Noisy Environment

Simple item page
dc.contributor.VIAF19968651 (Hansen, JHL)en_US
dc.contributor.authorYu, Chengzhuen_US
dc.contributor.authorOgawa, A.en_US
dc.contributor.authorDelcroix, M.en_US
dc.contributor.authorYoshioka, T.en_US
dc.contributor.authorNakatani, T.en_US
dc.contributor.authorHansen, John H. L.en_US
dc.contributor.utdAuthorYu, Chengzhu
dc.contributor.utdAuthorHansen, John H. L.
dc.date.accessioned2016-10-27T18:17:42Z
dc.date.available2016-10-27T18:17:42Z
dc.date.created2015-09-06en_US
dc.description.abstractIn this study, we explore an i-vector based adaptation of deep neural network (DNN) in noisy environment. We first demonstrate the importance of encapsulating environment and channel variability into i-vectors for DNN adaptation in noisy conditions. To be able to obtain robust i-vector without losing noise and channel variability information, we investigate the use of parallel feature based i-vector extraction for DNN adaptation. Specifically, different types of features are used separately during two different stages of i-vector extraction namely universal background model (UBM) state alignment and i-vector computation. To capture noise and channel-specific feature variation, the conventional MFCC features are still used for i-vector computation. However, much more robust features such as Vector Taylor Series (VTS) enhanced as well as bottleneck features are exploited for UBM state alignment. Experimental results on Aurora-4 show that the parallel feature-based i-vectors yield performance gains of up to 9.2% relative compared to a baseline DNN-HMM system and 3.3% compared to a system using conventional MFCC-based i-vectors.en_US
dc.identifier.bibliographicCitationYu, C., A. Ogawa, M. Delcroix, T. Yoshioka, et al. 2015. "Robust i-vector extraction for neural network adaptation in noisy environment." INTERSPEECH 2015 (16th Annual Conference Of The International Speech Communication Association), p. 2854-2857.en_US
dc.identifier.issn2308-457Xen_US
dc.identifier.urihttp://hdl.handle.net/10735.1/5109
dc.identifier.volume2015en_US
dc.language.isoenen_US
dc.publisherInternational Speech and Communication Associationen_US
dc.rights©2015 ISCAen_US
dc.source.journalINTERSPEECH 2015en_US
dc.subjectAcoustic modelsen_US
dc.subjectAutomatic speech recognitionen_US
dc.subjectNeural networks (Computer science)en_US
dc.subjectVector analysisen_US
dc.subjectNoiseen_US
dc.subjectSpeech processingen_US
dc.titleRobust I-Vector Extraction for Neural Network Adaptation in Noisy Environmenten_US
dc.type.genrearticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
JECS-3626-4714.65.pdf
Size:
210.5 KB
Format:
Adobe Portable Document Format
Description:
Article
Download

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
International Speech Communication Association.pdf
Size:
94.27 KB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Hansen, John H. L.