
Maichou Lor
· PhD, RNVerifiedUniversity of Wisconsin-Madison · Nursing
Active 2001–2026
About
Maichou Lor, PhD, RN, FAAN, is an Associate Professor and the Helen Denne Schulte Professor of Nursing at the University of Wisconsin–Madison School of Nursing. Her overall research program aims to reduce health disparities by improving symptom management and quality of life for patients with communication challenges, particularly those with limited English proficiency (LEP). Her research focuses on exploring the influence of cultural, language, and historical factors on communication, as well as designing and testing culturally and linguistically innovative health assessment approaches for LEP patients using applied informatics. Her areas of focus include health equity, language and interpreting access, health literacy, and the development of culturally and linguistically appropriate health interventions. She also concentrates on health issues affecting minority populations, such as Hmong health, symptom science, palliative care, pain assessment, and aging and care for older adults. Her work involves addressing biological, psychological, and social factors impacting pain reporting, and developing health interventions involving family caregivers to support older adults, including addressing hearing loss among minority older adults. Dr. Lor's contributions are centered on advancing health systems and public health through her research on health disparities and culturally competent care.
Research topics
- Political Science
- Gerontology
- Law
- Audiology
- Medicine
Selected publications
2026-02-17
articleOpen accessSenior author<sec> <title>UNSTRUCTURED</title> A multi‑layered fraud‑mitigation approach is essential to ensure data integrity in medical survey research; basic measures alone (e.g. captcha) would permit widespread fraud. </sec>
Patient Education and Counseling · 2026-01-06
article1st authorCorresponding“Empowering your kids”: Parenting among 1.5- and second-generation HMong American mothers.
Asian American Journal of Psychology · 2026-03-26
articleSenior authorBMC Primary Care · 2026-04-30
articleOpen accessarXiv (Cornell University) · 2026-01-14
preprintOpen accessTonal low-resource languages are widely spoken yet remain underserved by modern speech technology. A key challenge is learning representations that are robust to nuisance variation such as gender while remaining tone-aware for different lexical meanings. To address this, we propose SITA, a lightweight adaptation recipe that enforces Speaker-Invariance and Tone-Awareness for pretrained wav2vec-style encoders. SITA uses staged multi-objective training: (i) a cross-gender contrastive objective encourages lexical consistency across speakers, while a tone-repulsive loss prevents tone collapse by explicitly separating same-word different-tone realizations; and (ii) an auxiliary Connectionist Temporal Classification (CTC)-based ASR objective with distillation stabilizes recognition-relevant structure. We evaluate primarily on Hmong, a highly tonal and severely under-resourced language where off-the-shelf multilingual encoders fail to represent tone effectively. On a curated Hmong word corpus, SITA improves cross-gender lexical retrieval accuracy, while maintaining usable ASR accuracy relative to an ASR-adapted XLS-R teacher. We further observe similar gains when transferring the same recipe to Mandarin, suggesting SITA is a general, plug-in approach for adapting multilingual speech encoders to tonal languages.
ArXiv.org · 2026-01-14
articleOpen accessTonal low-resource languages are widely spoken yet remain underserved by modern speech technology. A key challenge is learning representations that are robust to nuisance variation such as gender while remaining tone-aware for different lexical meanings. To address this, we propose SITA, a lightweight adaptation recipe that enforces Speaker-Invariance and Tone-Awareness for pretrained wav2vec-style encoders. SITA uses staged multi-objective training: (i) a cross-gender contrastive objective encourages lexical consistency across speakers, while a tone-repulsive loss prevents tone collapse by explicitly separating same-word different-tone realizations; and (ii) an auxiliary Connectionist Temporal Classification (CTC)-based ASR objective with distillation stabilizes recognition-relevant structure. We evaluate primarily on Hmong, a highly tonal and severely under-resourced language where off-the-shelf multilingual encoders fail to represent tone effectively. On a curated Hmong word corpus, SITA improves cross-gender lexical retrieval accuracy, while maintaining usable ASR accuracy relative to an ASR-adapted XLS-R teacher. We further observe similar gains when transferring the same recipe to Mandarin, suggesting SITA is a general, plug-in approach for adapting multilingual speech encoders to tonal languages.
American Journal of Transplantation · 2025-08-01 · 1 citations
articleExperiences of Hmong Women in the Perinatal Period
Journal of Obstetric, Gynecologic & Neonatal Nursing · 2025-03-30 · 1 citations
articleSenior authorCommunicating pain through storytelling: how Hmong patients' messages get missed in consultations
Patient Education and Counseling · 2025-07-15
article1st authorCorrespondingJournal of Racial and Ethnic Health Disparities · 2025-08-27
article
Recent grants
Frequent coauthors
- 16 shared
Nereida Congost‐Maestre
University of Alicante
- 15 shared
Roger Brown
University of Wisconsin–Madison
- 10 shared
Theresa A. Koleck
University of Pittsburgh
- 9 shared
Barbara J. Bowers
University of Wisconsin–Madison
- 9 shared
Debra Saliba
RAND Corporation
- 8 shared
Elizabeth O’Donnell
- 7 shared
Adriana Arcia
University of San Diego
- 6 shared
Suzanne Bakken
Columbia University Irving Medical Center
Education
Postdoctoral Research Fellow, School of Nursing
Columbia University
MS, Nursing
University of Wisconsin Madison
- 2017
Doctor of Philosophy (Ph.D.), School of Nursing
University of Wisconsin Madison
- Resume-aware match score
- Save to shortlist
- AI-drafted outreach
See your match with Maichou Lor
PhdFit ranks faculty by your research interests, methods, and publications — grounded in their actual work, not templates.
- Free to start
- No credit card
- 30-second signup