Berthy Feng

Princeton, NJ ยท

I'm a senior undergrad in the CS Department at Princeton University. I do research in computer vision, natural language processing, and signal processing. [Résumé]


Undergraduate Researcher

Princeton Visual AI Lab

Conducting senior thesis research in vision + NLP, specifically methods for unsupervised learning of image captioning.

September 2018 - Present

Software Engineer Intern


Built back-end infrastructure and ML models on Machine Intelligence team of Google Photos.

Summer 2018

Research Assistant

Princeton Electrical Engineering

Created Pixplor, an "intelligent photo album" iPad app for nursing-home residents with dementia. Check out this article about the project.

Summer 2017


Learning Bandwidth Expansion Using Perceptually-Motivated Loss

Bandwidth Expansion

We introduce a perceptually motivated approach to bandwidth expansion for speech. Our method pairs a new 3-way split variant of the FFTNet neural vocoder structure with a perceptual loss function, combining objectives from both the time and frequency domains. Mean opinion score tests show that it outperforms baseline methods from both domains, even for extreme bandwidth expansion.

Collaborators: Zeyu Jin, Jiaqi Su, Prof. Adam Finkelstein

This project began as an Independent Work project and won the Princeton CS Department's Best Poster Award. It developed into a full-fledged research project and publication.

A Tale of Two Encodings: Comparing Bag-of-Words and Word2vec for VQA

COS 598B Project
Bandwidth Expansion

Analyzing the effect of different text encodings on visual question answering (VQA) models.


Princeton University

Bachelor of Science in Engineering
Computer Science + Certificate in Satistics and Machine Learning

Tau Beta Pi

Class of 2019

Laurel School

High School

Lyman Prize (Valedictorian)
State Champion and NSDA National Quarterfinalist in Extemporaneous Speaking

Class of 2015


Programming Languages & Tools
  • Python
  • Java
  • C++
  • Swift
  • JavaScript
  • React

Machine Learning Frameworks
  • TensorFlow
  • PyTorch
  • Caffe


I love music and believe good music comes from all genres, instruments, and people. I produce music using a mix of digital/analog synthesis (feel free to check out my SoundCloud). I play piano (my current goal is to master Chopin's Ballade No. 1 in g minor) and am teaching myself guitar.

When not geeking out over machine learning or music theory, I enjoy playing tennis and watching reruns of Friends.