| 2026 | EACL | Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning. | Minseok Kim, Jingxiang Chen, Seong-Gyun Leem, Yin Huang, Rashi Rungta, Zhicheng Ouyang, Haibin Wu, Surya Teja Appini, Ankur Bansal, Yang Bai, Yue Liu, Florian Metze, Ahmed Aly, Anuj Kumar, Ariya Rastrow, Zhaojiang Lin |
| 2025 | ICASSP | Noise-Robust Speech Emotion Recognition Using Shared Self-Supervised Representations with Integrated Speech Enhancement. | Jing-Tong Tzeng, Seong-Gyun Leem, Ali N. Salman, Chi-Chun Lee, Carlos Busso |
| 2024 | Interspeech | Keep, Delete, or Substitute: Frame Selection Strategy for Noise-Robust Speech Emotion Recognition. | Seong-Gyun Leem, Daniel Fulford, Jukka-Pekka Onnela, David Gard, Carlos Busso |
| 2023 | ACII | Analyzing the Effect of Affective Priming on Emotional Annotations. | Luz Martinez-Lucas, Ali N. Salman, Seong-Gyun Leem, Shreya G. Upadhyay, Chi-Chun Lee, Carlos Busso |
| 2023 | ASRU | Combining Relative and Absolute Learning Formulations to Predict Emotional Attributes From Speech. | Abinay Reddy Naini, Shruthi Subramanium, Seong-Gyun Leem, Carlos Busso |
| 2023 | ICASSP | Adapting a Self-Supervised Speech Representation for Noisy Speech Emotion Recognition by Using Contrastive Teacher-Student Learning. | Seong-Gyun Leem, Daniel Fulford, Jukka-Pekka Onnela, David Gard, Carlos Busso |
| 2023 | Interspeech | The Importance of Calibration: Rethinking Confidence and Performance of Speech Multi-label Emotion Classifiers. | Huang-Cheng Chou, Lucas Goncalves, Seong-Gyun Leem, Chi-Chun Lee, Carlos Busso |
| 2023 | Interspeech | Computation and Memory Efficient Noise Adaptation of Wav2Vec2.0 for Noisy Speech Emotion Recognition with Skip Connection Adapters. | Seong-Gyun Leem, Daniel Fulford, Jukka-Pekka Onnela, David Gard, Carlos Busso |
| 2022 | ICASSP | Not All Features are Equal: Selection of Robust Features for Speech Emotion Recognition in Noisy Environments. | Seong-Gyun Leem, Daniel Fulford, Jukka-Pekka Onnela, David Gard, Carlos Busso |
| 2021 | Interspeech | Separation of Emotional and Reconstruction Embeddings on Ladder Network to Improve Speech Emotion Recognition Robustness in Noisy Conditions. | Seong-Gyun Leem, Daniel Fulford, Jukka-Pekka Onnela, David Gard, Carlos Busso |