Robust I-Vector Extraction for Neural Network Adaptation in Noisy Environment
dc.contributor.VIAF | 19968651 (Hansen, JHL) | en_US |
dc.contributor.author | Yu, Chengzhu | en_US |
dc.contributor.author | Ogawa, A. | en_US |
dc.contributor.author | Delcroix, M. | en_US |
dc.contributor.author | Yoshioka, T. | en_US |
dc.contributor.author | Nakatani, T. | en_US |
dc.contributor.author | Hansen, John H. L. | en_US |
dc.contributor.utdAuthor | Yu, Chengzhu | |
dc.contributor.utdAuthor | Hansen, John H. L. | |
dc.date.accessioned | 2016-10-27T18:17:42Z | |
dc.date.available | 2016-10-27T18:17:42Z | |
dc.date.created | 2015-09-06 | en_US |
dc.description.abstract | In 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.bibliographicCitation | Yu, 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.issn | 2308-457X | en_US |
dc.identifier.uri | http://hdl.handle.net/10735.1/5109 | |
dc.identifier.volume | 2015 | en_US |
dc.language.iso | en | en_US |
dc.publisher | International Speech and Communication Association | en_US |
dc.rights | ©2015 ISCA | en_US |
dc.source.journal | INTERSPEECH 2015 | en_US |
dc.subject | Acoustic models | en_US |
dc.subject | Automatic speech recognition | en_US |
dc.subject | Neural networks (Computer science) | en_US |
dc.subject | Vector analysis | en_US |
dc.subject | Noise | en_US |
dc.subject | Speech processing | en_US |
dc.title | Robust I-Vector Extraction for Neural Network Adaptation in Noisy Environment | en_US |
dc.type.genre | article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- JECS-3626-4714.65.pdf
- Size:
- 210.5 KB
- Format:
- Adobe Portable Document Format
- Description:
- Article
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- International Speech Communication Association.pdf
- Size:
- 94.27 KB
- Format:
- Adobe Portable Document Format
- Description: