Convolutional Auto-Encoder and Adversarial Domain Adaptation for Cross-Corpus Speech Emotion Recognition

作     者：Wang, Yang Fu, Hongliang Tao, Huawei Yang, Jing Ge, Hongyi Xie, Yue 

作者机构：Henan Univ Technol Key Lab Grain Informat Proc & Control Minist Educ Zhengzhou 450001 Peoples R China Henan Univ Technol Coll Informat Sci & Engn Zhengzhou 450001 Peoples R China Nanjing Inst Technol Sch Commun Engn Nanjing 211167 Peoples R China 

出 版 物：《IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS》 (IEICE Trans Inf Syst)

年 卷 期：2022年第E105D卷第10期

页      面：1803-1806页

核心收录：

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Nat-ural Science Foundation of China Natural Science Project of Henan Education Department Start-up Fund for High-level Talents of Henan University of Tech-nology 62001215 61601170 61975053 21A120003 22A520004 22A510001 31401148 

主　　题：cross-corpus speech emotion recognition convolutional auto-encoder adversarial domain adaptation 

摘      要：This letter focuses on the cross-corpus speech emotion recognition (SER) task, in which the training and testing speech signals in cross-corpus SER belong to different speech corpora. Existing algorithms are incapable of effectively extracting common sentiment information between different corpora to facilitate knowledge transfer. To address this challenging problem, a novel convolutional auto-encoder and adversarial domain adaptation (CAEADA) framework for cross-corpus SER is proposed. The framework first constructs a one-dimensional convolutional auto-encoder (1D-CAE) for feature processing, which can explore the correlation among adjacent one-dimensional statistic features and the feature representation can be enhanced by the architecture based on encoder-decoder-style. Subsequently the adversarial domain adaptation (ADA) module alleviates the feature distributions discrepancy between the source and target domains by confusing domain discriminator, and specifically employs maximum mean discrepancy (MMD) to better accomplish feature transformation. To evaluate the proposed CAEADA, extensive experiments were conducted on EmoDB, eNTERFACE, and CASIA speech corpora, and the results show that the proposed method outperformed other approaches.