Disordered Speech

AI for disordered speech profiling

Speech changes are often among the earliest signs of neurodegenerative disease. At Mayo Clinic, I develop AI pipelines to analyze speech from individuals with conditions such as apraxia of speech and dysarthria, identifying acoustic and temporal markers linked to cognitive and motor decline. By modeling features such as articulation, vocal quality, and prosody, our research aims to develop scalable, non-invasive tools for early detection and continuous monitoring of neurological disorders.

Related Publications

2026

  1. CLP
    Deep learning-derived measures of sound-level accuracy in primary progressive apraxia of speech: A feasibility pipeline with descriptive evidence from two cases
    Fenqi Wang, John R. Duffy, Ashley D. Bachman, Leland R. Barnard, Hugo. Botha, and Rene L. Utianski
    Clinical Linguistics & Phonetics, 2026

2025

  1. BSMCS
    Using AI to detect articulatory modulations under delayed auditory feedback in PPAOS
    Fenqi Wang, Hugo Botha, and Rene L. Utianski
    In The 5th Biennial Boston Speech Motor Control Symposium, 2025
  2. ASA
    Deep learning-driven phonetic profiling of dysarthric speech
    Fenqi Wang, Rene L. Utianski, Joseph R. Duffy, David T. Jones, and Hugo Botha
    In The 188th Meeting of Acoustical Society of America, 2025