A novel Adaptive Weighted Transfer Subspace Learning Method for Cross-Database Speech Emotion Recognition
Summary :
In this letter, we present an adaptive weighted transfer subspace learning (AWTSL) method for cross-database speech emotion recognition (SER), which can efficiently eliminate the discrepancy between source and target databases. Specifically, on one hand, a subspace projection matrix is first learned to project the cross-database features into a common subspace. At the same time, each target sample can be represented by the source samples by using a sparse reconstruction matrix. On the other hand, we design an adaptive weighted matrix learning strategy, which can improve the reconstruction contribution of important features and eliminate the negative influence of redundant features. Finally, we conduct extensive experiments on four benchmark databases, and the experimental results demonstrate the efficacy of the proposed method.
- Publication
- IEICE TRANSACTIONS on Information Vol.E105-D No.9 pp.1643-1646
- Publication Date
- 2022/09/01
- Publicized
- 2022/06/09
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022EDL8021
- Type of Manuscript
- LETTER
- Category
- Speech and Hearing
Authors
Keke ZHAO
Yantai University
Peng SONG
Yantai University
Shaokai LI
Yantai University
Wenjing ZHANG
Yantai University
Wenming ZHENG
Southeast 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
Keke ZHAO, Peng SONG, Shaokai LI, Wenjing ZHANG, Wenming ZHENG, "A novel Adaptive Weighted Transfer Subspace Learning Method for Cross-Database Speech Emotion Recognition" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 9, pp. 1643-1646, September 2022, doi: 10.1587/transinf.2022EDL8021.
Abstract: In this letter, we present an adaptive weighted transfer subspace learning (AWTSL) method for cross-database speech emotion recognition (SER), which can efficiently eliminate the discrepancy between source and target databases. Specifically, on one hand, a subspace projection matrix is first learned to project the cross-database features into a common subspace. At the same time, each target sample can be represented by the source samples by using a sparse reconstruction matrix. On the other hand, we design an adaptive weighted matrix learning strategy, which can improve the reconstruction contribution of important features and eliminate the negative influence of redundant features. Finally, we conduct extensive experiments on four benchmark databases, and the experimental results demonstrate the efficacy of the proposed method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDL8021/_p
Copy
@ARTICLE{e105-d_9_1643,
author={Keke ZHAO, Peng SONG, Shaokai LI, Wenjing ZHANG, Wenming ZHENG, },
journal={IEICE TRANSACTIONS on Information},
title={A novel Adaptive Weighted Transfer Subspace Learning Method for Cross-Database Speech Emotion Recognition},
year={2022},
volume={E105-D},
number={9},
pages={1643-1646},
abstract={In this letter, we present an adaptive weighted transfer subspace learning (AWTSL) method for cross-database speech emotion recognition (SER), which can efficiently eliminate the discrepancy between source and target databases. Specifically, on one hand, a subspace projection matrix is first learned to project the cross-database features into a common subspace. At the same time, each target sample can be represented by the source samples by using a sparse reconstruction matrix. On the other hand, we design an adaptive weighted matrix learning strategy, which can improve the reconstruction contribution of important features and eliminate the negative influence of redundant features. Finally, we conduct extensive experiments on four benchmark databases, and the experimental results demonstrate the efficacy of the proposed method.},
keywords={},
doi={10.1587/transinf.2022EDL8021},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - A novel Adaptive Weighted Transfer Subspace Learning Method for Cross-Database Speech Emotion Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1643
EP - 1646
AU - Keke ZHAO
AU - Peng SONG
AU - Shaokai LI
AU - Wenjing ZHANG
AU - Wenming ZHENG
PY - 2022
DO - 10.1587/transinf.2022EDL8021
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2022
AB - In this letter, we present an adaptive weighted transfer subspace learning (AWTSL) method for cross-database speech emotion recognition (SER), which can efficiently eliminate the discrepancy between source and target databases. Specifically, on one hand, a subspace projection matrix is first learned to project the cross-database features into a common subspace. At the same time, each target sample can be represented by the source samples by using a sparse reconstruction matrix. On the other hand, we design an adaptive weighted matrix learning strategy, which can improve the reconstruction contribution of important features and eliminate the negative influence of redundant features. Finally, we conduct extensive experiments on four benchmark databases, and the experimental results demonstrate the efficacy of the proposed method.
ER -
English
