I am a part of the team at Comcast Applied AI Research (Washington DC) that develops NLP models for the voice-enabled entertainment operating system, X1. As a senior machine learning researcher, I work on deep neural network based solutions for various problems in Natural Language Processing (NLP). One of the problems I worked on recently is to recognize human intents from multilingual voice queries made through Xfinity Voice Remote control.

Over the last 10 years, I applied concepts of machine learning in various academic research domains, e.g. affective computing, multimodal signal processing, accessibility, human-computer interaction, and behavioral prediction of humans. I developed a causal model guided deep learning architecture for a bias-free prediction of the TED Talk ratings. I invented an unsupervised algorithm to detect repetitive body-movements (Mannerisms) from MoCap signals. I did my Ph.D. from the University of Rochester. My academic advisor was M. Ehsan Hoque who leads the Human-Computer Interaction (ROCHCI) lab at the University of Rochester. During my stay at UofR, I got the chance to collaborate with several great researchers, including Daniel Gildea, Ji Liu, and Gonzalo Mateos.

Highlighted Publications

FairyTED: A Fair Rating Predictor for TED Talk Data, AAAI’20, NY, USA
UR-FUNNY: A Multimodal Language Dataset for Understanding Humor, EMNLP’19, Hong Kong, China
A Causality-Guided Prediction of the TED Talk Ratings from the Speech-Transcripts using Neural Networks
, arXiv preprint arXiv:1905.08392
SyntaViz: Visualizing Voice Queries through a Syntax-Driven Hierarchical Ontology, EMNLP’18, Brussels, Belgium, 2018 
Awe the Audience: How the Narrative Trajectories Affect Audience Perception in Public Speaking
, CHI’18, Montreal, Canada, 2018
AutoManner: An Automated Interface for Making Public Speakers Aware of Their Mannerisms, IUI’16, Sonoma, CA, USA, 2016
Unsupervised Extraction of Human-Interpretable Nonverbal Behavioral Cues in a Public Speaking Scenario, ACMMM’15, Brisbane, Australia, 2015
Automated Prediction of Job Interview Performance: The Role of What You Say and How You Say It, FG’15, Ljubljana, Slovenia, 2015.

News and Presentations

Nov 10th, 2019 Awesome news! Our FairyTED paper got accepted in AAAI 2020!!! A cool thing about this paper is that no university faculty member is there in the author list 🙂 After reading Judea Pearl’s “The Book of Why”, I realized that neural networks alone can’t do a bias-free and fair prediction. It is important to model the data generating process (possibly using causal models). I tried to convince Rupam, Ankani, and Soumen regarding the importance of the problem and, together, we pulled the paper off. I’m really very proud of this contribution.  
Aug 13th, 2019 Our UR-Funny paper got accepted in EMNLP 2019 paper
Oct 27th, 2018 I presented in the lab on Judea Pearl’s new book “The Book of Why”. My advisor, Ehsan Hoque tweeted that and Judea Pearl himself commented on that tweet! Tweet
Slides
Oct 22nd, 2018 I’ve successfully defended my PhD thesis Pictures
Slides
Aug 6th, 2018 One of my work during the internship in Comcast Lab is accepted in EMNLP 2018 Paper
April 25, 2018 I presented our TED Talk work in CHI 2018 Slides
Feb 16, 2018 I presented Chapter 5 from the Deep Learning book in Lab Slides
Jan 2018 Our paper got accepted in CHI 2018  
Oct 6th, 2017 My thesis proposal got accepted  
Sep 26, 2017 Got invited to Brain and Cognitive Science for presenting my work in NSF Research Traineeship Program (NRT) Slides
Aug 10, 2017 I presented a pyTorch Tutorial in our lab Slides
May 15, 2017 I am going to work as an intern at the Comcast Applied AI Research Lab this summer  
July 24th, 2016 I was invited for a presentation at RIT for One-Day REU Symposium Slides
Sep 1st, 2016 AutoManner code is released Code
GUI Code
Jan 15th, 2016 IUI travel grant award approved  
Dec 7th, 2015 Our paper got accepted in IUI 2016  
15th Sep, 2015 I got the ACMMM travel grant award 2015  
4th July, 2015 Our short paper in ACM Multimedia got accepted  
26th June, 2015 One item in my bucket list is checked — I met Prof. Gilbert Strang!!  
16th April, 2015 Our IUI paper (Rhema) is being featured in UoR news and other news: NY MagazinewxxinewsEngadget, Gizmag, Eurekalert, Entrepreneur, InnovationTrail. Code

older>>

I met Prof Gilbert Strang in 2015!
I met my grand-advisor Professor Rosaline Picard in 2011
With Professor Jeffrey Cohn in ACII 2011