Speech Emotion Recognition Using Deep Learning Techniques: A Review

By Ruhul Amin Khalil, Edward Jones, M. I. Babar, Tariqullah Jan, M. H. Zafar, Thamer Alhussain. IEEE Access, 2019

556 citations recorded by the source corpus.

Emotion recognition from speech signals is an important but challenging component of Human-Computer Interaction (HCI). In the literature of speech emotion recognition (SER), many techniques have been utilized to extract emotions from signals, including many well-established speech analysis and classification techniques. Deep Learning techniques have been recently proposed as an alternative to traditional techniques in SER. This paper presents an overview of Deep Learning techniques and discusses some recent literature where these methods are utilized for speech-based emotion recognition. The review covers databases used, emotions extracted, contributions made toward speech emotion recognition and limitations related to it.

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

View Paper: https://www.semanticscholar.org/paper/3ae3c9de97343bfc5f5f5f17a9419a5db3e5e652

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. Shuyong Gao
2. Muhammad Sajjad
3. Weizhen Song
4. .. Mustaqeem
5. Antonio Liotta
6. Xinlei Li
7. Da-Wei Yang
8. Soonil Kwon

In Experimental and Cognitive Psychology

1. Syed Asif Ahmad Qadri
2. Taiba Maijd Wani
3. Teddy Surya Gunawan
4. Mira Kartiwi
5. Eliathamby Ambikairajah
6. Muhammad Sajjad
7. .. Mustaqeem
8. Soonil Kwon

In Signal Processing

1. Syed Asif Ahmad Qadri
2. Taiba Maijd Wani
3. Teddy Surya Gunawan
4. Mira Kartiwi
5. Eliathamby Ambikairajah
6. Muhammad Sajjad
7. .. Mustaqeem
8. Antonio Liotta

Citations in the corpus

• A Comprehensive Review of Speech Emotion Recognition Systems (2021, background): “…Mixture Models (GMM), Hidden Markov Models (HMM), k-nearest neighborhood (kNN) classifiers, Support Vector Machines (SVM), decision tree, and artificial neural networks (ANN) are a few models that have been generally used to classify emotions dependent on their acoustic features of intrigue [9].”
• Clustering-Based Speech Emotion Recognition by Incorporating Learned Features and Deep BiLSTM (2020, background): “With the increase in data and cost computation deep learning approach is rapidly used for SER [15] and many researchers are used deep learning approaches for robust features representation in various fields [11].”
• A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, background): “Besides, [42] discussed the research results of the sentiment analysis using transfer learning algorithms, whereas authors in [43] surveyed the DL-based methods for SER.”