DNN Transfer Learning Based Non-Linear Feature Extraction for Acoustic Event Classification
Summary :
Recent acoustic event classification research has focused on training suitable filters to represent acoustic events. However, due to limited availability of target event databases and linearity of conventional filters, there is still room for improving performance. By exploiting the non-linear modeling of deep neural networks (DNNs) and their ability to learn beyond pre-trained environments, this letter proposes a DNN-based feature extraction scheme for the classification of acoustic events. The effectiveness and robustness to noise of the proposed method are demonstrated using a database of indoor surveillance environments.
- Publication
- IEICE TRANSACTIONS on Information Vol.E100-D No.9 pp.2249-2252
- Publication Date
- 2017/09/01
- Publicized
- 2017/06/09
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2017EDL8048
- Type of Manuscript
- LETTER
- Category
- Speech and Hearing
Authors
Seongkyu MUN
Korea University
Minkyu SHIN
Korea University
Suwon SHON
Korea University
Wooil KIM
Incheon National University
David K. HAN
Korea University
Hanseok KO
Korea University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Seongkyu MUN, Minkyu SHIN, Suwon SHON, Wooil KIM, David K. HAN, Hanseok KO, "DNN Transfer Learning Based Non-Linear Feature Extraction for Acoustic Event Classification" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 9, pp. 2249-2252, September 2017, doi: 10.1587/transinf.2017EDL8048.
Abstract: Recent acoustic event classification research has focused on training suitable filters to represent acoustic events. However, due to limited availability of target event databases and linearity of conventional filters, there is still room for improving performance. By exploiting the non-linear modeling of deep neural networks (DNNs) and their ability to learn beyond pre-trained environments, this letter proposes a DNN-based feature extraction scheme for the classification of acoustic events. The effectiveness and robustness to noise of the proposed method are demonstrated using a database of indoor surveillance environments.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDL8048/_p
Copy
@ARTICLE{e100-d_9_2249,
author={Seongkyu MUN, Minkyu SHIN, Suwon SHON, Wooil KIM, David K. HAN, Hanseok KO, },
journal={IEICE TRANSACTIONS on Information},
title={DNN Transfer Learning Based Non-Linear Feature Extraction for Acoustic Event Classification},
year={2017},
volume={E100-D},
number={9},
pages={2249-2252},
abstract={Recent acoustic event classification research has focused on training suitable filters to represent acoustic events. However, due to limited availability of target event databases and linearity of conventional filters, there is still room for improving performance. By exploiting the non-linear modeling of deep neural networks (DNNs) and their ability to learn beyond pre-trained environments, this letter proposes a DNN-based feature extraction scheme for the classification of acoustic events. The effectiveness and robustness to noise of the proposed method are demonstrated using a database of indoor surveillance environments.},
keywords={},
doi={10.1587/transinf.2017EDL8048},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - DNN Transfer Learning Based Non-Linear Feature Extraction for Acoustic Event Classification
T2 - IEICE TRANSACTIONS on Information
SP - 2249
EP - 2252
AU - Seongkyu MUN
AU - Minkyu SHIN
AU - Suwon SHON
AU - Wooil KIM
AU - David K. HAN
AU - Hanseok KO
PY - 2017
DO - 10.1587/transinf.2017EDL8048
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2017
AB - Recent acoustic event classification research has focused on training suitable filters to represent acoustic events. However, due to limited availability of target event databases and linearity of conventional filters, there is still room for improving performance. By exploiting the non-linear modeling of deep neural networks (DNNs) and their ability to learn beyond pre-trained environments, this letter proposes a DNN-based feature extraction scheme for the classification of acoustic events. The effectiveness and robustness to noise of the proposed method are demonstrated using a database of indoor surveillance environments.
ER -
English
