Prof. Ming-Hsiang Su is a prominent researcher and assistant professor specializing in the fields of deep learning, natural language processing, and speech signal processing, with a particular focus on spoken dialogue systems, emotion recognition, and personality trait perception. His work integrates advanced computational techniques with real-world applications, developing intelligent systems capable of understanding, interpreting, and generating human-like speech and dialogue. Prof. Ming-Hsiang Su has contributed to the advancement of speech emotion recognition by considering both verbal and nonverbal vocal cues, and has designed sophisticated models for empathetic dialogue generation, text-to-motion transformation, and mood disorder detection through audiovisual signals. He has published extensively in high-impact journals and conferences, addressing topics such as few-shot image segmentation, sound source separation, automatic ontology population, and speaker identification. His research also extends to applied systems, including automated crop disease detection, question-answering systems, and industrial defect detection using deep learning architectures. By combining theoretical insights with practical implementations, Prof. Ming-Hsiang Su work bridges the gap between computational intelligence and human-centered applications, enhancing machine understanding of complex speech, language, and affective behaviors. Through his interdisciplinary approach, he continues to advance innovative methods for human-computer interaction, intelligent dialogue systems, and multimodal data analysis, establishing a significant impact on both academic research and practical technological applications across various domains, with 791 citations by 684 documents, 83 documents, and an h-index of 15.

Profiles: Scopus | Orcid | Google Scholar