Speech emotion recognition based on improved masking EMD and convolutional recurrent neural network

被引:7
作者
Sun, Congshan [1 ]
Li, Haifeng [1 ]
Ma, Lin [1 ]
机构
[1] Harbin Inst Technol, Fac Comp, Harbin, Peoples R China
来源
FRONTIERS IN PSYCHOLOGY | 2023年 / 13卷
基金
中国国家自然科学基金;
关键词
speech emotion recognition; empirical mode decomposition; mode mixing; convolutional neural networks; bidirectional gated recurrent units; EMPIRICAL MODE DECOMPOSITION; HILBERT SPECTRUM; SIGNAL; FEATURES;
D O I
10.3389/fpsyg.2022.1075624
中图分类号
B84 [心理学];
学科分类号
04 ; 0402 ;
摘要
Speech emotion recognition (SER) is the key to human-computer emotion interaction. However, the nonlinear characteristics of speech emotion are variable, complex, and subtly changing. Therefore, accurate recognition of emotions from speech remains a challenge. Empirical mode decomposition (EMD), as an effective decomposition method for nonlinear non-stationary signals, has been successfully used to analyze emotional speech signals. However, the mode mixing problem of EMD affects the performance of EMD-based methods for SER. Various improved methods for EMD have been proposed to alleviate the mode mixing problem. These improved methods still suffer from the problems of mode mixing, residual noise, and long computation time, and their main parameters cannot be set adaptively. To overcome these problems, we propose a novel SER framework, named IMEMD-CRNN, based on the combination of an improved version of the masking signal-based EMD (IMEMD) and convolutional recurrent neural network (CRNN). First, IMEMD is proposed to decompose speech. IMEMD is a novel disturbance-assisted EMD method and can determine the parameters of masking signals to the nature of signals. Second, we extract the 43-dimensional time-frequency features that can characterize the emotion from the intrinsic mode functions (IMFs) obtained by IMEMD. Finally, we input these features into a CRNN network to recognize emotions. In the CRNN, 2D convolutional neural networks (CNN) layers are used to capture nonlinear local temporal and frequency information of the emotional speech. Bidirectional gated recurrent units (BiGRU) layers are used to learn the temporal context information further. Experiments on the publicly available TESS dataset and Emo-DB dataset demonstrate the effectiveness of our proposed IMEMD-CRNN framework. The TESS dataset consists of 2,800 utterances containing seven emotions recorded by two native English speakers. The Emo-DB dataset consists of 535 utterances containing seven emotions recorded by ten native German speakers. The proposed IMEMD-CRNN framework achieves a state-of-the-art overall accuracy of 100% for the TESS dataset over seven emotions and 93.54% for the Emo-DB dataset over seven emotions. The IMEMD alleviates the mode mixing and obtains IMFs with less noise and more physical meaning with significantly improved efficiency. Our IMEMD-CRNN framework significantly improves the performance of emotion recognition.
引用
收藏
页数:14
相关论文
共 56 条
  • [1] Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks
    Adavanne, Sharath
    Politis, Archontis
    Nikunen, Joonas
    Virtanen, Tuomas
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2019, 13 (01) : 34 - 48
  • [2] Deep-Net: A Lightweight CNN-Based Speech Emotion Recognition System Using Deep Frequency Features
    Anvarjon, Tursunov
    Mustaqeem
    Kwon, Soonil
    [J]. SENSORS, 2020, 20 (18) : 1 - 16
  • [3] When Old Meets New: Emotion Recognition from Speech Signals
    Arano, Keith April
    Gloor, Peter
    Orsenigo, Carlotta
    Vercellis, Carlo
    [J]. COGNITIVE COMPUTATION, 2021, 13 (03) : 771 - 783
  • [4] Comparison of hemispheric asymmetry measurements for emotional recordings from controls
    Aydin, Serap
    Demirtas, Serdar
    Tunga, M. Alper
    Ates, Kahraman
    [J]. NEURAL COMPUTING & APPLICATIONS, 2018, 30 (04) : 1341 - 1351
  • [5] Basu S, 2017, PROCEEDINGS OF THE 2017 INTERNATIONAL CONFERENCE ON INVENTIVE COMMUNICATION AND COMPUTATIONAL TECHNOLOGIES (ICICCT), P109, DOI 10.1109/ICICCT.2017.7975169
  • [6] Speech/Music Classification Using Features From Spectral Peaks
    Bhattacharjee, Mrinmoy
    Prasanna, S. R. Mahadeva
    Guha, Prithwijit
    [J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2020, 28 (28) : 1549 - 1559
  • [7] Burkhardt Felix, 2005, P 9 EUR C SPEECH COM
  • [8] IEMOCAP: interactive emotional dyadic motion capture database
    Busso, Carlos
    Bulut, Murtaza
    Lee, Chi-Chun
    Kazemzadeh, Abe
    Mower, Emily
    Kim, Samuel
    Chang, Jeannette N.
    Lee, Sungbok
    Narayanan, Shrikanth S.
    [J]. LANGUAGE RESOURCES AND EVALUATION, 2008, 42 (04) : 335 - 359
  • [9] Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
    Cao, Yixin
    Wang, Xiang
    He, Xiangnan
    Hu, Zikun
    Chua, Tat-Seng
    [J]. WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019), 2019, : 151 - 161
  • [10] Real-Time Speech Emotion Analysis for Smart Home Assistants
    Chatterjee, Rajdeep
    Mazumdar, Saptarshi
    Sherratt, R. Simon
    Halder, Rohit
    Maitra, Tanmoy
    Giri, Debasis
    [J]. IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2021, 67 (01) : 68 - 76