Shubham Toshniwal

5th year PhD Student
Toyota Technological Institute at Chicago (TTIC)
Advisor: Kevin Gimpel, Karen Livescu

Contact Details

6045 S. Kenwood Ave., Chicago, IL
shtoshni at ttic dot edu
Google Scholar

Happy Me !!
Alaska 2019

I am a 5th year graduate student working with Kevin Gimpel and Karen Livescu at Toyota Technological Institute at Chicago (TTIC). I also work closely with Allyson Ettinger at UChicago. My research is focussed on natural language understanding, specifically on modeling the underlying entities in text. In the past I have worked on speech recognition, and also at the intersection of speech and text understanding.

Before TTIC, I spent two years as a software engineer in IBM Research, New Delhi. And even before that I spent the four most fun years of my life at Indian Institute of Technology Kanpur as an undergrad in Computer Science.


Selected Publications

PeTra: A Sparsely Supervised Memory Model for People Tracking
Shubham Toshniwal, Allyson Ettinger, Kevin Gimpel, Karen Livescu
ACL 2020
[pdf] [code] [colab] [bib] [slides]

A Cross-Task Analysis of Text Span Representations
Shubham Toshniwal, Haoyue Shi, Bowen Shi, Lingyu Gao, Karen Livescu, Kevin Gimpel
RepL4NLP 2020
[pdf] [code] [bib] [slides]

Pre-trained Text Embeddings for Enhanced Text-to-Speech Synthesis
Tomoki Hayashi, Shinji Watanabe, Tomoki Toda, Kazuya Takeda, Shubham Toshniwal, Karen Livescu
Interspeech 2019
[pdf] [bib]

A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition
Shubham Toshniwal, Anjuli Kannan, Chung-Cheng Chiu, Yonghui Wu, Tara N Sainath, Karen Livescu
IEEE Workshop on Spoken Language Technology (SLT), 2018
[pdf] [bib]

Hierarchical Multitask Learning for CTC-based Speech Recognition
Kalpesh Krishna, Shubham Toshniwal, Karen Livescu
[pdf] [bib]

Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Information
Trang Tran*, Shubham Toshniwal*, Mohit Bansal, Kevin Gimpel, Karen Livescu, Mari Ostendorf
NAACL HLT 2018 (Oral)
[pdf] [code] [bib]

Multilingual Speech Recognition With A Single End-To-End Model
Shubham Toshniwal, Tara N. Sainath, Ron J. Weiss, Bo Li, Pedro Moreno, Eugene Weinstein, Kanishka Rao
ICASSP 2018 (Oral)
[pdf] [slides] [blog] [bib]

Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition
Shubham Toshniwal, Hao Tang, Liang Lu, Karen Livescu
Interspeech 2017 (Oral)
[arXiv] [slides] [summary] [bib]

Jointly learning to align and convert graphemes to phonemes with neural attention models
Shubham Toshniwal, Karen Livescu
IEEE Workshop on Spoken Language Technology (SLT), 2016
[pdf] [code] [poster] [bib]

USHER: An Intelligent Tour Companion
Shubham Toshniwal, Parikshit Sharma, Saurabh Srivastava, Richa Sehgal
International Conference on Intelligent User Interfaces (IUI) 2015
[pdf] [MIT Technology Review]