I am a tenure-track Assistant Professor at the College of Information Science at the University of Arizona.
I earned my Ph.D. in Electrical and Computer Engineering and B.S. in Electrical Engineering from the University of Illinois at Urbana-Champaign. I was fortunate to be advised by Professor Mark Hasegawa-Johnson. Following my Ph.D, I also spent time visiting the WAV Lab in the Language Technologies Institute at Carnegie Mellon University, under the supervision of Professor Shinji Watanabe. During my Ph.D., I interned at Meta AI Research and Amazon Web Services.
My research goal is to build interdisciplinary speech applications that support the early identification of developmental disorders in children, such as autism, delayed speech maturity, and language disorders. During my doctoral work, I focused on developing emerging AI-powered clinical applications for early childhood (<3 years old), with an emphasis on several core tasks: speaker diarization (identify “who spoke when”), vocalization classification (identify the type of vocalizations given a speaker) between infant/toddlers and adults, and phoneme recognition of toddlers (<4 years old). These tasks have been developed for different applications and social contexts, including daylong home recordings and clinical settings, as shown by the representative work done below:
Monitoring infant psychological development
Li et al. "Analysis of acoustic and voice quality features for the classification of infant and mother vocalizations." Speech communication 133 (2021): 41-61.
Li, et al. Towards Robust Family-Infant Audio Analysis Based on Unsupervised Pretraining of Wav2vec 2.0 on Large-Scale Unlabeled Family Audio. Proc. Interspeech 2023, 1035-1039, doi: 10.21437/Interspeech.2023-460
Identifying children at risk of autism / assessing speech maturity of young children
Li, et al. Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis. Proc. Interspeech 2024, 5163-5167, doi: 10.21437/Interspeech.2024-540
Phoneme recognition of toddlers
Li, et al. "Analysis of Self-Supervised Speech Models on Children’s Speech and Infant Vocalizations," 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), Seoul, Korea, Republic of, 2024, pp. 550-554, doi: 10.1109/ICASSPW62465.2024.10626416.s
Looking ahead, I aim to improve the performance of core tasks and explore other novel AI applications in healthcare and education for children's speech processing.
I am looking for highly motivated PhD students (as fully-funded TAs/RAs) and interns to join my lab! If you are interested in working with me, please fill [this form]. After completing the form, you are also welcome to reach out via email (jialuli@arizona.edu), though optional. I will promise to read all submitted forms and emails, but I do apologize for not being able to respond to each of them.
Most important: self-motivated and eager to learn
B.S/M.S. in Computer Science, Electrical and Computer Engineering, Information Sciences, or related fields
Proficiency in Python and familiarity with deep learning frameworks
Ability to present ideas clearly in English writing and speaking.
Previous relevant research experience is preferred but not required
Academic family tree: me – Hasegawa-Johnson – Stevens – Beranek – Hunt – Chaffee – Pierce – Macfarlane – Tait – Hopkins – Sedgwick – Jones – Postlethwaite – Whisson – Taylor – Smith – Cotes – Newton.