I am a PhD candidate in the Institute for Computational and Mathematical Engineering (ICME). Prior to joining the Stanford community, I worked at NERA Economic Consulting in New York, where I specialized in data work with applications to antitrust litigation and mergers. I am originally from the DC area and received my Bachelor's in Mathematics with Computer Science from MIT. Previous internships include data science roles at Facebook, Google, and Microsoft.
Honors & Awards
NSF Graduate Fellowship, NSF (2018-2021)
National Physical Science Consortium Graduate Fellowship, NPSC (2016-2018)
EDGE Doctoral Fellowship, Stanford (2016)
Gene Golub Fellowship, ICME (2016)
Racial disparities in automated speech recognition.
Proceedings of the National Academy of Sciences of the United States of America
Automated speech recognition (ASR) systems, which use sophisticated machine-learning algorithms to convert spoken language to text, have become increasingly widespread, powering popular virtual assistants, facilitating automated closed captioning, and enabling digital dictation platforms for health care. Over the last several years, the quality of these systems has dramatically improved, due both to advances in deep learning and to the collection of large-scale datasets used to train the systems. There is concern, however, that these tools do not work equally well for all subgroups of the population. Here, we examine the ability of five state-of-the-art ASR systems-developed by Amazon, Apple, Google, IBM, and Microsoft-to transcribe structured interviews conducted with 42 white speakers and 73 black speakers. In total, this corpus spans five US cities and consists of 19.8 h of audio matched on the age and gender of the speaker. We found that all five ASR systems exhibited substantial racial disparities, with an average word error rate (WER) of 0.35 for black speakers compared with 0.19 for white speakers. We trace these disparities to the underlying acoustic models used by the ASR systems as the race gap was equally large on a subset of identical phrases spoken by black and white individuals in our corpus. We conclude by proposing strategies-such as using more diverse training datasets that include African American Vernacular English-to reduce these performance differences and ensure speech recognition technology is inclusive.
View details for DOI 10.1073/pnas.1915768117
View details for PubMedID 32205437
- Preventing cytokine storm syndrome in COVID-19 using α-1 adrenergic receptor antagonists. The Journal of clinical investigation 2020
A game theoretic setting of capitation versus fee-for-service payment systems.
2019; 14 (10): e0223672
We aim to determine whether a game-theoretic model between an insurer and a healthcare practice yields a predictive equilibrium that incentivizes either player to deviate from a fee-for-service to capitation payment system. Using United States data from various primary care surveys, we find that non-extreme equilibria (i.e., shares of patients, or shares of patient visits, seen under a fee-for-service payment system) can be derived from a Stackelberg game if insurers award a non-linear bonus to practices based on performance. Overall, both insurers and practices can be incentivized to embrace capitation payments somewhat, but potentially at the expense of practice performance.
View details for DOI 10.1371/journal.pone.0223672
View details for PubMedID 31589655