Speaker Biography
Yuan Jiahong is a Professor at the School of Humanities and Social Sciences, University of Science and Technology of China. He received his Ph.D. in Linguistics from Cornell University in 2004. He has previously held positions at the Department of Linguistics and the Linguistic Data Consortium at the University of Pennsylvania, the AI Lab at Liulishuo (Silicon Valley), and Baidu Research USA.
His primary research interests lie at the intersection of data-driven phonetics, linguistics, and artificial intelligence. He has served as Principal Investigator for numerous research projects funded by the U.S. National Science Foundation, the UK Economic and Social Research Council, and the National Social Science Fund of China. His current research focuses on early detection and prediction of Alzheimer's disease using spontaneous speech, deep learning-based speech analysis methods, and tone recognition in model-brain alignment studies.
Lecture Time & Venue
Time: July 3, 14:00–15:30
Venue: Lecture Hall 136, Teaching Building No. 5
Lecture Title
Tone Recognition and Speaker Normalization Mechanisms in Model-Brain Alignment
Lecture Abstract
Recent advancements in artificial intelligence have created new opportunities for interdisciplinary research at the intersection of linguistics, neuroscience, and computational modeling. In the domain of speech recognition, for instance, the application of Transformer models and pre-training–fine-tuning approaches has led to significant improvements in recognition accuracy, including the automatic recognition of lexical tones in continuous speech. This progress raises a critical question: to what extent can these models simulate the processing mechanisms of the human brain? From the perspective of model-brain alignment, this talk will explore learning mechanisms, normalization strategies, neural decoding in tone recognition, and the role of deep brain regions in pitch normalization.
