[Seminar] Speech Modeling for Affective Computing
Monday, February 24, 2025
11:00 am - 12:00 pm
Speaker
Wei-Cheng
(Winston)
Lin
Bosch
Research
–
Bosch
Center
for
Artificial
Intelligence
Location
PGH 232
Abstract
Affective computing seeks to develop computational frameworks capable of recognizing, understanding, and responding to human emotions. As a foundational component of human-centered AI, it enables applications in areas such as human-computer interaction (HCI), healthcare, and education. However, modeling emotions from behavioral signals presents significant challenges due to the subjective nature of emotion perception and expression. In this talk, I will discuss approaches to modeling emotions from speech data by addressing three key challenges: 1) efficient temporal modeling, 2) semi-supervised representation learning, and 3) robust subjectivity modeling. I will also share exciting next steps in affective computing field, highlighting its integration with recent progresses in multimodal modeling, GenAI and agentic workflows.
About the Speaker
Dr. Wei-Cheng Lin is a Research Scientist at Bosch Research – Bosch Center for Artificial Intelligence (BCAI), USA. He earned his Ph.D. in Electrical Engineering from the University of Texas at Dallas (UTD) in 2023. His research focuses on multimodal signal processing, speech and audio processing, deep learning, and affective computing. His work has been published in top-tier ACM and IEEE Transactions journals spanning signal processing and affective computing. He was recognized with the Best Dissertation Award from the Association for the Advancement of Affective Computing (AAAC) in 2024.
- Location
- Room 232, Philip Guthrie Hoffman Hall (PGH), 3551 Cullen Blvd, Houston, TX 77204, USA