Yunting Yin, Ph.D.

About me

I am a computer scientist specializing in speech processing and natural language processing. My passion for technology extends to coding, analyzing data, and extracting meaningful insights from text and audio signals. Originally from Shanghai, China, I moved to the U.S. in 2016 to pursue my undergraduate studies and have been captivated by the culture and lifestyle ever since. My academic journey has been shaped by exceptional mentors, which inspired me to pursue a career in education. I look forward to fostering a similar environment of guidance and support for my students. I also love horses, so you might find me at the EC equestrian center occasionally.

Education

-Ph.D., Stony Brook University, 2024
-B.S., Pace University, 2019

Professional memberships

IEEE
IEEE WIE

Research projects

I have three ongoing research projects that I am looking for students to collaborate on. Please read these abstracts and reach out to me if interested.

(1) Aging Analysis on Veteran Dataset
This project is an extension of our previous work to investigate whether paralinguistic vocal attributes improve estimates of the age and risk of mortality in older adults. We obtain interviews of male US veterans from the Veteran History Project database managed by the Library of Congress. Computational analyses produced vocal age estimates that were correlated with both age and predicted time until death when age was held constant. We further extend this work by performing language analysis on the transcripts derived from audio recordings and data from the National Death Index.

(2) LLM Event Forecasting
Statisticians and psychologists have studied how humans make decisions, and what practices lead to better judgment. Large language models (LLMs) have broad knowledge from their extensive training on large corpus, and thus are expected to make better than random guessing predictions on a broad set of questions. This forecasting project studies how LLMs can make predictions on real-world events and evaluate their accuracy on a self-curated dataset containing problems from forecasting sites like Good Judgment Open.

(3) Evaluating Bias in Facial Expression Recognition Systems
Large-scale image datasets for Facial Expression Recognition (FER) are often built using web-scraping and crowdsourced annotations. While these methods enable researchers to gather millions of images in-the-wild quickly and cost-effectively, they also introduce bias. In this project, we investigate the presence of bias in FER systems by evaluating model performance across various demographic groups.

In this Fall 2024 semester, I submitted two papers with talented Earlham students. Here are brief descriptions of our work:

(1) Dictionary definitions are historically the arbitrator of what words mean, but this primacy has come under threat by recent progress in NLP, including word embeddings and generative models like ChatGPT. We conduct an exploratory study of the degree of alignment between word definitions from classical dictionaries and these newer computational artifacts.

(2) Recent advances in text-to-speech have made it possible to generate natural-sounding audio from text. However, audiobook narrations involve dramatic vocalizations and intonations by the reader, with greater reliance on emotions, dialogues, and descriptions in the narrative. Using our dataset of 93 aligned book-audiobook pairs, we study how machine learning models for prosody prediction properties (pitch, volume, and rate of speech) from narrative text using language modeling.

Scholarly interest

Data Science
Speech Processing
Natural Language Processing

Published works

Yunting Yin. “A Study of Aging Through Speech and Language Analysis”, Doctoral dissertation, Stony Brook University. ProQuest Dissertations and Theses Global, 2024.

Yunting Yin, Douglas William Hanes, Steven Skiena, and Sean A P Clouston. “Quantifying Healthy Aging in Older Veterans using Computational Audio Analysis”, in the Journals of Gerontology: Series A, 2023.

Zuhui Wang, Yunting Yin, and I.V. Ramakrishnan. “Enhancing Image-Text Matching with Adaptive Feature Aggregation”, ICASSP 2024.

Yunting Yin, and Steven Skiena. “Inferring Age from Linguistic and Verbal Cues in Celebrity Interviews”, 2023 International Conference on Frontiers of Artificial Intelligence and Machine Learning.

Nanjie Deng, Junchao Xia, Lauren Wickstrom, Clement Lin, Kaibo Wang, Peng He, Yunting Yin, and Danzhou Yang. “Ligand Selectivity in the Recognition of Protoberberine Alkaloids by Hybrid-2 Human Telomeric G-Quadruplex: Binding Free Energy Calculation, Fluorescence Binding, and NMR Experiments”, in Molecules 2019, 24(8), 1574.