Soonil Kwon
Papers
2
Total Citations
470
H-Index
2
About
Soonil Kwon is a researcher specializing in speech emotion recognition (SER) and deep learning-based audio signal processing, with significant contributions to the development of intelligent systems capable of understanding human emotional states from speech data. His most influential work, "Clustering-Based Speech Emotion Recognition by Incorporating Learned Features and Deep BiLSTM" (2020), has garnered an impressive 396 citations, establishing him as a notable voice in the field. This paper introduced a sophisticated approach combining clustering techniques with bidirectional long short-term memory networks to improve the accuracy of emotional state recognition — a challenge with far-reaching implications for human-robot interaction, behavior assessment, and virtual applications. Building on this foundation, Kwon further advanced the field with his 2021 work on 1D convolutional neural networks, proposing a stacked architecture with dilated CNN features that demonstrated strong performance across diverse SER applications, including robotics and emergency response systems. With a cumulative citation count surpassing 470, Kwon's research has meaningfully shaped modern approaches to affective computing, inspiring subsequent work in real-time emotion-aware machine learning systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2