A Generalized Subspace Distribution Adaptation Framework for Cross-Corpus Speech Emotion Recognition

In this paper, we propose a novel transfer learning framework, named generalized subspace distribution adaptation (GSDA), to tackle the challenging cross-corpus speech emotion recognition problem. First, we learn a common low-dimensional feature subspace by utilizing a generalized subspace learning...

Full description

Saved in:
Bibliographic Details
Main Authors: Li, Shaokai, Song, Peng, Ji, Liang, Jin, Yun, Zheng, Wenming
Format: Conference Proceeding
Language:English
Subjects:
Cross-corpus Speech Emotion Recognition
Distribution Adaptation
Emotion recognition
Learning systems
Measurement
Signal processing algorithms
Speech recognition
Transfer learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a novel transfer learning framework, named generalized subspace distribution adaptation (GSDA), to tackle the challenging cross-corpus speech emotion recognition problem. First, we learn a common low-dimensional feature subspace by utilizing a generalized subspace learning method. Second, we develop a novel distance metric to reduce the divergence between the source and target corpora, which can efficiently explore the similarity and dissimilarity information in the process of knowledge transfer. Third, to demonstrate the effectiveness of our framework, we apply GSDA to the traditional subspace learning algorithms. Finally, we conduct extensive experiments by using the low-level features and deep features on three popular emotional databases, i.e., Berlin, IEMOCAP, and CVE. The results demonstrate that the proposed framework can achieve better performance than several state-of-the-art transfer learning approaches.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10097258