Published on 22/10/202522/10/2025 by Environmental Scientists 61 / 100 Powered by Rank Math SEO SEO Score Prof. Ming-Hsiang Su | Signal Processing | Best Researcher Award Prof. Ming-Hsiang Su | Soochow University | Taiwan 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 Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78. Ming-Hsiang Su | Signal Processing | Best Researcher Award
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Featured Publications Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.
Huang, K. Y., Wu, C. H., Hong, Q. B., Su, M. H., & Chen, Y. H. (2019). Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and …, 138. Su, M. H., Wu, C. H., Huang, K. Y., Hong, Q. B., & Wang, H. M. (2017). A chatbot using LSTM-based multi-layer embedding for elderly care. 2017 International Conference on Orange Technologies (ICOT), 70-74. Hsu, J. H., Su, M. H., Wu, C. H., & Chen, Y. H. (2021). Speech emotion recognition considering nonverbal vocalization in affective conversations. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 1675-1686. Su, M. H., Wu, C. H., & Cheng, H. T. (2020). A two-stage transformer-based approach for variable-length abstractive summarization. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 2061-2072. Su, M. H., Wu, C. H., Huang, K. Y., & Hong, Q. B. (2018). LSTM-based text emotion recognition using semantic and emotional word vectors. 2018 First Asian Conference on Affective Computing and Intelligent …, 78.