On using Parameterized Multi-channel Non-causal Wiener Filter-Adapted Convolutional Neural Networks for Distant Speech Recognition
- Title
- On using Parameterized Multi-channel Non-causal Wiener Filter-Adapted Convolutional Neural Networks for Distant Speech Recognition
- Author
- 장준혁
- Keywords
- beamforming; Convolutional neural networks; distant speech recognition; PMWF
- Issue Date
- 2016-01
- Publisher
- IEEE, IEIE
- Citation
- International Conference on Electronics, Information, and Communications, ICEIC 2016, Article number 7562963, Page. 1-4
- Abstract
- Recently, the convolutional neural network (CNN) with multiple microphones was proposed to use the delay-sum (DS) beamformer for distant speech recognition (DSR) and compared to the direct use of multiple acoustic channels as a parallel input to the CNN [1]. We explore the parameterized multi-channel non-causal Wiener filter (PMWF) as the front-end to train the CNN, which is applied to acoustic modeling for DSR. For this, we first present a concise description of the basic PMWF as well as its advantages and then explain how to organize the PMWF into the CNN with a novel architecture. Experimental results on the TIMIT dataset show that the proposed PMWF-based CNN approach outperforms the cross-channel CNN and the DS beamformer when evaluating the word error rate (WER) in various DSR environments. © 2016 IEEE.
- URI
- http://ieeexplore.ieee.org/document/7562963/http://hdl.handle.net/20.500.11754/30389
- ISSN
- 978-1-4673-8016-4
- DOI
- 10.1109/ELINFOCOM.2016.7562963
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > ELECTRONIC ENGINEERING(융합전자공학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML