Error, canvas is not supported

Sushant Kafle

sushant @ mail.rit.edu
PhD Student,
Computing and Information Science,
GCCIS, RIT
I am a third year Ph.D. student in Computing and Information Science at the Golisano College of Computing and Information Science, Rochester Institute of Technology (RIT) under the advisement of Prof. Matt Huenerfauth. My current research aims to inform the design and the evaluation of Automatic Speech Recognition (ASR) technology for use in captioning for people who are deaf or hard of hearing (DHH). More specifically, my current work explores the modeling of the importance of words in understanding the meaning of a spoken message and/or a text for various group of readers.

Research Statement: I am interested in applying machine learning concepts in building linguistic- and speech-based technologies that benefit humans; by designing and validating them through real-world observations and studies with users.

Technical Interests: Natural Language Processing, Human-Computer Interaction, Speech Processing, Machine Learning.

Some research projects I'm associated with..

2018
A Corpus for Modeling Word Importance in Spoken Dialogue Transcripts.
Sushant Kafle, Matt Huenerfauth. International Conference on Language Resources and Evaluation (LREC'18)
[to appear]
Methods for Evaluation of Imperfect Captioning Tools by Deaf or Hard-of-Hearing Users at Different Reading Literacy Levels.
Larwan Berke, Sushant Kafle, Matt Huenerfauth. ACM Conference on Human Factors in Computing Systems (CHI'18)
[to appear]
2017
Evaluating the Usability of Automatically Generated Captions for People who are Deaf or Hard of Hearing.
Sushant Kafle, Matt Huenerfauth. Annual SIGACCESS Conference on Computers and Accessibility (ASSETS'17)
Best Paper Award
2016
Effect of Speech Recognition Errors on Text Understandability for People who are Deaf or Hard of Hearing.
Sushant Kafle, Matt Huenerfauth. Speech and Language Processing for Assistive Technologies (SLPAT'16)

Timeline and Events

November, 2017 Our ASSETS 2017 paper won the "Best Paper Award".
September, 2017 We announce the creation of the Corpus of Word Importance Annotations, more details here.
July, 2017 Our submission to ASSETS 2017 conference has been accepted and has also been nominated for a Best Paper Award.
May, 2017 Helped facilitate the Research Experience for Undergraduates (REU) program at the CAIR lab.
October, 2016 Participated and presented at ASSETS Doctoral Consortium 2016.
July, 2016 Our submission has been accepted to the SLPAT 2016 workshop.
May, 2016 Sucessfully defended the PhD Research Potential Assesment.
August, 2015 Started working as a reserach assistant at the CAIR Lab.
August, 2015 Joined RIT for doctoral studies in the Golisano College of Computing and Information Sciences.

Other projects I'm associated with..

Academic Projects

Word Importance LabelerDeveloped a tool with a suite of metrics for evaluating the quality automatically generated transcripts of classroom lectures based on word importance information. The tool was developed as a part of a research project at National Technical Institute for Deaf (NTID) which investigated the usability of automatic captioning for classrooms.
Speech Analysis for Word Importance ModelingInvestigated various acoustic-prosodic features from human speech to see if they provide clues about the importance of word being spoken; importance defined in terms of the contribution of the word in understanding the meaning of a spoken utterance.
Caption Quality EvaluationInvestigated various linguistic features to design a novel metric for evaluating of the usability of automatically generated captions for people who are Deaf or Hard of Hearing.
Speech Recognition Error AnalysisCategorized and analyzed different types of errors produced by Sphinx4 Speech Recognition System on 100-hrs of speech recordings from LibriSpeech Corpus. Implemented novel output alignment modules to account for fuzzy time-stamp matching and, one to many and many to one substitution errors. Created a local compute cluster to make speech recognition faster.

Non-Academic Projects

Rubik's Cubea 3d rubik's cube simulator and solver.
BusyNotean android app that lets you send appropriate automatic replies for people trying to contact you when you are busy.
Perlin Noise Implemetationan implementation of Perlin Noise Algorithm that lets you create perlin-noise textures.
Kabachan android app for social cause again women voilence. Product of VAW hackathon 2013, Kathmandu, Nepal.
Easy Yatraa web + mobile app to know the whereabouts of public vehicles. production of Startup weekend Nepal, 2013.
Marching Squarea quick implementation of Marching Square algorithm.
Quick Hulla instructive graphical implementaion of quick hull 2D.
Decision Treea dynamic canvas based decision tree generator.