I am a speech-language pathologist, acoustic phonetician, and neural network engineer developing next-generation clinical speech technologies. I have expertise across the full lifecycle of clinical AI development: speech representations, neural network training, clinical trialing, and scalable deployment.

My work bridges clinical practice, speech science, and AI to develop theoretically motivated and clinically validated tools to help clinicians extend the reach of best-practice speech therapy.

I am currently an NIH NIDCD T32 post-doctoral fellow in the Speech Communication Lab at the University of Maryland, mentored by Dr. Carol Espy-Wilson, where I am training in acoustic-to-articulatory speech inversion and speech modeling.

Research Themes

Clinically Tested AI Speech Therapy

My research develops clinical AI systems based on speech-language pathology best practice. I am the lead inventor on the patent-pending PERCEPT AI system: a neural network that predicts clinician judgment of the “R” sound during speech therapy. My doctoral work with Jonathan Preston has shown that speech production improves with ChainingAI, a therapy platform delivering motor-based intervention with automated feedback. ChainingAI allows learners to practice evidence-based Speech Motor Chaining at home. Three additional clinical trials for AI speech therapies are ongoing.

Automatic Kinematic Speech Analyses

A separate line of my research investigates acoustic-to-articulatory speech inversion, a technique that estimates vocal tract gestures from audio alone. My research has shown that speech inversion vocal tract gestures can differentiate subtypes of speech sound errors in children with single-sound speech disorders and quantify speech coordination differences in childhood apraxia of speech. My ongoing work examines how automated kinematic speech analyses can enhance the types of feedback that AI clinicians can give.

Ultrasound Biofeedback and Acoustic Biofeedback for Speech Therapy

My colleagues and I have shown that motor learning is enhanced during speech therapy that includes biofeedback, such as ultrasound biofeedback and acoustic biofeedback. We have shown that biofeedback is effective, particularly when delivered through intensive schedules, even for children who have not responded to traditional speech therapy.

Open-Access Child Speech Data

I have curated the PERCEPT Corpora, which are currently the largest open-access speech corpora focused on speech sound disorders in American English. I am the sole US-based co-founder of the Interspeech Child Speech Science and Speech Technology special sessions.

Speech Profiles of Speech Sound Disorders in Children

I have also investigated how different types of speech sound disorders manifest across articulatory, perceptual, and acoustic dimensions, as well as how to quantify these speech dimensions.

The tools I use to address these research themes include: Azure DevOps, Amazon AWS, Google Speech API, HTCondor/Cluster Computing, Linux, MATLAB, Montreal Forced Aligner/Kaldi, NLTK, Phon, Praat, Python, PyTorch/CUDA, R, REDCap API, Regex, REST APIs, SAS, Stanza/CoreNLP