About Me

I am Anuj Diwan (अनुज दिवाण), a second year PhD student in the Computer Science Department at the University of Texas at Austin. I am fortunate to be co-advised by Prof. David Harwath and Prof. Eunsol Choi and I am part of the UT NLP group. I am also a Part-Time Student Researcher at FAIR (Meta AI) mentored by Dr. Abdelrahman Mohamed since Summer 2022.

My research interests are in Natural Language Processing, Speech Recognition, and Machine Learning. I’m currently working on speech-to-speech translation and parameter-efficient continual learning for speech tasks. I’ve worked on vision-language compositionality and multilingual+ code-switching speech recognition in the past.

I received my undergraduate B.Tech (with Honors) degree in Computer Science and a Minor degree in Statistics from IIT Bombay in 2021. I had a great time working with Prof. Preethi Jyothi and Prof. Sunita Sarawagi at IIT Bombay. I have interned at FAIR (Meta AI) in Summer 2022, Adobe Research India in Summer 2020 and ICTEAM, INMA, UCLouvain, Belgium in Summer 2019.

In my spare time, I enjoy reading, quizzing, solving wordgames, and watching the latest movies and TV shows.

Interests
  • Speech Recognition
  • Natural Language Processing
  • Artificial Intelligence
  • Machine Learning
Education
  • PhD in Computer Science, 2021-present

    University of Texas at Austin

  • B.Tech in Computer Science and Engineering with Honours, 2017-2021

    Indian Institute of Technology Bombay

  • Minor in Statistics, 2017-2021

    Indian Institute of Technology Bombay

CV

Curriculum Vitae (Last updated Nov 2022)

CV

Publications

(2022). Continual Learning for On-Device Speech Recognition using Disentangled Conformers. ICASSP 2023.

PDF

(2022). Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality. EMNLP 2022.

PDF Cite Code Slides

(2022). Zero-shot Video Moment Retrieval With Off-the-Shelf Models. TL4NLP@NeurIPS 2022.

PDF Cite Poster

(2021). Reduce and Reconstruct: ASR for Low-Resource Phonetic Languages. Interspeech 2021.

PDF Cite Slides

(2021). Low Resource ASR: The surprising effectiveness of High Resource Transliteration. Interspeech 2021.

PDF Cite Slides

(2021). Multilingual and code-switching ASR challenges for low resource Indian languages. Interspeech 2021.

PDF Cite

Experience

 
 
 
 
 
AI Research Intern, Summer 2022
May 2022 – Present Seattle, WA
 
 
 
 
 
Research Intern, Summer 2020
Apr 2020 – Jul 2020 Bangalore, India
 
 
 
 
 
Research Intern, Summer 2019
May 2019 – Jul 2019 Louvain-la-Neuve, Belgium