IEEE SPS DISTINGUISHED LECTURER PROGRAM TWIN CITIES SP/COM CHAPTER SEMINAR 09/24/2025

#Missouri#Slope#IEEE

Title: Approaching General to Super Computer Audition

From understanding human speech and music to perceiving complex soundscapes, the field of computer audition is rapidly evolving toward a new frontier: systems that approach general listening intelligence and even exceed human auditory capabilities. In this Distinguished IEEE SPS lecture, we will trace the journey from today’s specialized audio recognition systems to tomorrow’s general-purpose and “super” computer audition—AI that can listen, interpret, and act across a vast range of acoustic environments. Building on decades of research in speech and audio processing, affective and paralinguistic computing, and multimodal machine learning, the talk will showcase how advances in large-scale models, self-supervised learning, and cross-modal integration are reshaping what machines can hear and understand breaking audio down into its sources and richly attributing states and traits to these. Applications range from voice biomarkers in healthcare and emotion-aware assistants to advanced hearing technologies—areas directly relevant to industry leaders such as Starkey. Yet, the move toward general and superhuman audition also raises critical questions. How do we ensure robustness, interpretability, and fairness in AI that listens to—and learns from—our most personal signals? How can we balance technical progress with ethical responsibility and user trust? And what are the implications of AI systems that may one day surpass human hearing in scope and precision? This talk will offer a forward-looking perspective on the science and impact of tomorrow’s computer audition, highlighting both the opportunities and challenges of designing AI that truly listens.