期刊
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
卷 14, 期 2, 页码 1634-1654出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TAFFC.2021.3114365
关键词
Speech emotion recognition; multi task learning; representation learning; domain adaptation; unsupervised learning
Traditionally, speech emotion recognition (SER) relied on manual feature engineering, but this approach requires significant manual effort and impedes innovation. Representation learning techniques have been adopted to automatically learn intermediate representations without manual engineering, leading to improved SER performance and rapid innovation. Deep learning further enhances the effectiveness of representation learning by enabling the automatic learning of hierarchical representations. This article presents a comprehensive survey on deep representation learning for SER, highlighting techniques, challenges, and future research areas.
Traditionally, speech emotion recognition (SER) research has relied on manually handcrafted acoustic features using feature engineering. However, the design of handcrafted features for complex SER tasks requires significant manual effort, which impedes generalisability and slows the pace of innovation. This has motivated the adoption of representation learning techniques that can automatically learn an intermediate representation of the input signal without any manual feature engineering. Representation learning has led to improved SER performance and enabled rapid innovation. Its effectiveness has further increased with advances in deep learning (DL), which has facilitated deep representation learning where hierarchical representations are automatically learned in a data-driven manner. This article presents the first comprehensive survey on the important topic of deep representation learning for SER. We highlight various techniques, related challenges and identify important future areas of research. Our survey bridges the gap in the literature since existing surveys either focus on SER with hand-engineered features or representation learning in the general setting without focusing on SER.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据