When
Jialu Li
Assistant Professor
Information Sciences
University of Arizona
Breaking Down Barriers: Advancing Interdisciplinary Speech Applications in Early Children’s Development
Abstract: Children’s development can evolve rapidly within the first few years of life. Identifying children at risk of developmental disorders, autism, and speech and language delays is critical. Early intervention can significantly enhance their communication skills, learning potential, and social interactions. My vision aims to develop cutting-edge AI speech technology to identify those with special needs at key developmental milestones.
In this talk, I will present my research on advancing interdisciplinary speech applications to capture critical adult-child vocal interactions under different social contexts, including monitoring infant psychological development at home and detecting children who are at risk of autism at clinics. A core component of my work involves leveraging self-supervised learning methods to improve two key speech-processing tasks: speaker diarization (determining “who spoke when”) and vocalization classification (categorizing vocalization types given a speaker). Finally, I will conclude the talk by briefly outlining my future research plans for integrating children’s speech technology with AI technology to develop innovative solutions for the early identification of developmental disorders in children.