Group Gated Fusion on Attention-based Bidirectional Alignment for Multimodal Emotion Recognition

被引:15
|
作者
Liu, Pengfei [1 ]
Li, Kun [1 ]
Meng, Helen [2 ]
机构
[1] SpeechX Ltd, Shenzhen, Peoples R China
[2] Chinese Univ Hong Kong, Hong Kong, Peoples R China
来源
关键词
multimodal emotion recognition; attention models; information fusion; NEURAL-NETWORKS; FEATURES;
D O I
10.21437/Interspeech.2020-2067
中图分类号
R36 [病理学]; R76 [耳鼻咽喉科学];
学科分类号
100104 ; 100213 ;
摘要
Emotion recognition is a challenging and actively-studied research area that plays a critical role in emotion-aware human-computer interaction systems. In a multimodal setting, temporal alignment between different modalities has not been well investigated yet. This paper presents a new model named as Gated Bidirectional Alignment Network (GBAN), which consists of an attention-based bidirectional alignment network over LSTM hidden states to explicitly capture the alignment relationship between speech and text, and a novel group gated fusion (GGF) layer to integrate the representations of different modalities. We empirically show that the attention-aligned representations outperform the last-hidden-states of LSTM significantly, and the proposed GBAN model outperforms existing state-of-the-art multimodal approaches on the IEMOCAP dataset.
引用
收藏
页码:379 / 383
页数:5
相关论文
共 50 条
  • [31] Emotion Recognition Based on Feedback Weighted Fusion of Multimodal Emotion Data
    Wei, Wei
    Jia, Qingxuan
    Feng, Yongli
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (IEEE ROBIO 2017), 2017, : 1682 - 1687
  • [32] Marfusion: An Attention-Based Multimodal Fusion Model for Human Activity Recognition in Real-World Scenarios
    Zhao, Yunhan
    Guo, Siqi
    Chen, Zeqi
    Shen, Qiang
    Meng, Zhengyuan
    Xu, Hao
    [J]. APPLIED SCIENCES-BASEL, 2022, 12 (11):
  • [33] Real-time emotion recognition using end-to-end attention-based fusion network
    Shit, Sahadeb
    Rana, Aiswarya
    Das, Dibyendu Kumar
    Ray, Dip Narayan
    [J]. JOURNAL OF ELECTRONIC IMAGING, 2023, 32 (01)
  • [34] Emotion recognition based on convolutional gated recurrent units with attention
    Ye, Zhu
    Jing, Yuan
    Wang, Qinghua
    Li, Pengrui
    Liu, Zhihong
    Yan, Mingjing
    Zhang, Yongqing
    Gao, Dongrui
    [J]. CONNECTION SCIENCE, 2023, 35 (01)
  • [35] Multimodal Alignment and Attention-Based Person Search via Natural Language Description
    Ji, Zhong
    Li, Shengjia
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2020, 7 (11) : 11147 - 11156
  • [36] AMAM: An Attention-based Multimodal Alignment Model for Medical Visual Question Answering
    Pan, Haiwei
    He, Shuning
    Zhang, Kejia
    Qu, Bo
    Chen, Chunling
    Shi, Kun
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 255
  • [37] Exploring temporal representations by leveraging attention-based bidirectional LSTM-RNNs for multi-modal emotion recognition
    Li, Chao
    Bao, Zhongtian
    Li, Linhao
    Zhao, Ziping
    [J]. INFORMATION PROCESSING & MANAGEMENT, 2020, 57 (03)
  • [38] An attention-based hybrid deep learning model for EEG emotion recognition
    Zhang, Yong
    Zhang, Yidie
    Wang, Shuai
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (05) : 2305 - 2313
  • [39] AHRNN: Attention-Based Hybrid Robust Neural Network for emotion recognition
    Xu, Ke
    Liu, Bin
    Tao, Jianhua
    Lv, Zhao
    Fan, Cunhang
    Song, Leichao
    [J]. COGNITIVE COMPUTATION AND SYSTEMS, 2022, 4 (01) : 85 - 95
  • [40] An attention-based hybrid deep learning model for EEG emotion recognition
    Yong Zhang
    Yidie Zhang
    Shuai Wang
    [J]. Signal, Image and Video Processing, 2023, 17 : 2305 - 2313