Anuj Diwan

CS PhD Student

Computer Science Department, UT Austin

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 Student Researcher at Google DeepMind in the Brain team mentored by Dr. Yu Zhang and Ankur Bapna for Summer 2023. In 2022, I spent a wonderful summer at FAIR (Meta AI) mentored by Dr. Abdelrahman Mohamed.

My research interests are in Speech Processing and Natural Language Processing. 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 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)

Publications

Anuj Diwan, Anirudh Srinivasan, David Harwath, Eunsol Choi (2023). Unit-based Speech-to-Speech Translation Without Parallel Data. Preprint.

PDF

Anuj Diwan, Eunsol Choi, David Harwath (2023). When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants. ACL 2023.

PDF Poster

Anuj Diwan, Ching-Feng Yeh, Wei-Ning Hsu, Paden Tomasello, Eunsol Choi, David Harwath, Abdelrahman Mohamed (2022). Continual Learning for On-Device Speech Recognition using Disentangled Conformers. ICASSP 2023.

PDF Poster

Anuj Diwan, Layne Berry, Eunsol Choi, David Harwath, Kyle Mahowald (2022). Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality. EMNLP 2022.

PDF Cite Code Slides

Anuj Diwan, Puyuan Peng, Raymond J. Mooney (2022). Zero-shot Video Moment Retrieval With Off-the-Shelf Models. TL4NLP@NeurIPS 2022.

PDF Cite Poster

Anuj Diwan, Preethi Jyothi (2021). Reduce and Reconstruct: ASR for Low-Resource Phonetic Languages. Interspeech 2021.

PDF Cite Slides

Shreya Khare, Ashish Mittal, Anuj Diwan, Sunita Sarawagi, Preethi Jyothi, Samarth Bharadwaj (2021). Low Resource ASR: The surprising effectiveness of High Resource Transliteration. Interspeech 2021.

PDF Cite Slides

Anuj Diwan, Rakesh Vaideeswaran, Sanket Shah, Ankita Singh, Srinivasa Raghavan, Shreya Khare, Vinit Unni, Saurabh Vyas, Akash Rajpuria, Chiranjeevi Yarra, Ashish Mittal, Prasanta Kumar Ghosh, Preethi Jyothi, Kalika Bali, Vivek Seshadri, Sunayana Sitaram, Samarth Bharadwaj, Jai Nanavati, Raoul Nanavati, Karthik Sankaranarayanan, Tejaswi Seeram, Basil Abraham (2021). Multilingual and code-switching ASR challenges for low resource Indian languages. Interspeech 2021.

PDF Cite