Learning Salient Features for Speech Emotion Recognition Using Convolutional Neural Networks

By Qi-rong Mao, Ming Dong, Zhengwei Huang, Yongzhao Zhan. IEEE transactions on multimedia, 2014

538 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/81032851d21ce3340030a3d46f01f4d67231dcfd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Björn Schuller
2. Soonil Kwon
3. Mustaqeem
4. Stefanos P. Zafeiriou
5. Erik Marchi
6. Shiliang Zhang
7. Tiejun Huang
8. Fabien Ringeval

In Experimental and Cognitive Psychology

1. Soonil Kwon
2. Mustaqeem
3. Björn Schuller
4. Stefanos P. Zafeiriou
5. Mihalis A. Nicolaou
6. Muhammad Sajjad
7. .. Mustaqeem
8. Fabien Ringeval

In Signal Processing

1. Soonil Kwon
2. Mustaqeem
3. Björn Schuller
4. Mihalis A. Nicolaou
5. Muhammad Sajjad
6. .. Mustaqeem
7. George Trigeorgis
8. Erik Marchi

Citations in the corpus

• 3-D Convolutional Recurrent Neural Networks With Attention Model for Speech Emotion Recognition (2018, methodology): “In recent years, CNN has exhibited excellent performances in the field of SER [1], [4], [6].”
• Speech Emotion Recognition Using Deep Learning Techniques: A Review (2019, background): “Preprocessing is an aditionaltask usually required to be carried out before recognition of emotion from the speech signal [120].”
• A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, methodology): “The CNNs with auto-encoder [187] are regarded as commonly used techniques for DL-based SER [187].”
• Speech emotion recognition (2018, unknown): “19 Convolutional neural networks (CNN) were also successfully employed to learn emotional feature representations.(27) The first end-to-end learning system for speech emotion recognition was recently presented by a sequence of two CNN layers operating at different time resolutions: 5ms first, then 5”
• Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network (2016, methodology): “In the field of paralinguistics, several studies have been carried out using CNNs for feature learning, e.g., recently by Milde and Biemann [14], and Mao et al. [15].”
• Clustering-Based Speech Emotion Recognition by Incorporating Learned Features and Deep BiLSTM (2020, methodology): “In the field of SER, many methods utilize CNN models with different types of input to extract salient features from speech signals to boost the recognition accuracy [30].”
• A CNN-Assisted Enhanced Audio Signal Processing for Speech Emotion Recognition (2019, methodology): “Mao et al. [9] improved the e ff ectiveness of SER for real-time applications using the salient and discriminative features analysis, for feature extraction to increase the significance of the HCI.”
• Speech Emotion Recognition from Spectrograms with Deep Convolutional Neural Network (2017, methodology): “These methods have shown promising results in the fields of speech recognition, emotion recognition, and other speech analysis applications [14-16].”
• Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid Matching (2018, methodology): “ploy 1-D convolution, such as frequency convolution [14]–[16]”
• A Review of Emotion Recognition Using Physiological Signals (2018, background): “One is using human physical signals such as facial expression [4], speech [5], gesture, posture, etc.”