Publications (Google Scholar Profile)
2025
A Non-autoregressive Model for Joint STT and TTS
Vishal Sunder, Brian Kingsbury, George Saon, Samuel Thomas, Slava Shechtman, Hagai Aronowitz, Eric Fosler-Lussier and Luis Lastras. To appear at ICASSP 2025
2024
Improving Transducer-Based Spoken Language Understanding with Self-Conditioned CTC and Knowledge Transfer
Vishal Sunder, Eric Fosler-Lussier. SLT 2024
End-to-End Real Time Tracking of Children’s Reading with Pointer Network
Vishal Sunder, Beulah Karrolla, Eric Fosler-Lussier. ICASSP 2024
2023
ConvKT: Conversation-Level Knowledge Transfer for Context Aware End-to-End Spoken Language Understanding
Vishal Sunder, Eric Fosler-Lussier, Samuel Thomas, Hong-Kwang J. Kuo, Brian Kingsbury. INTERSPEECH 2023
Fine-Grained Textual Knowledge Transfer to Improve RNN Transducers for Speech Recognition and Understanding
Vishal Sunder, Samuel Thomas, Hong-Kwang J. Kuo, Brian Kingsbury, Eric Fosler-Lussier. ICASSP 2023
End-to-End Word-Level Disfluency Detection and Classification in Children’s Reading Assessment
Lavanya Venkatasubramaniam*, Vishal Sunder*, Eric Fosler-Lussier. ( * means equal contribution) ICASSP 2023
2022
Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems
Vishal Sunder, Eric Fosler-Lussier, Samuel Thomas, Hong-Kwang J. Kuo, Brian Kingsbury. INTERSPEECH 2022
Towards end-to-end integration of dialog history for improved spoken language understanding
Vishal Sunder, Samuel Thomas, Hong-Kwang J. Kuo, Jatin Ganhotra, Brian Kingsbury, Eric Fosler-Lussier. ICASSP 2022
Building an ASR Error Robust Spoken Virtual Patient System in a Highly Class-Imbalanced Scenario Without Speech Data
Vishal Sunder, Prashant Serai, Eric Fosler-Lussier. Preprint
2021
Hallucination of speech recognition errors with sequence to sequence learning
Prashant Serai, Vishal Sunder, Eric Fosler-Lussier. IEEE/ACM Transactions on Audio, Speech and Language Processing
Handling Class Imbalance in Low-Resource Dialogue Systems by Combining Few-Shot Classification and Interpolation
Vishal Sunder, Eric Fosler-Lussier. ICASSP 2021
2019
One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesis
Vishal Sunder, Ashwin Srinivasan, Lovekesh Vig, Gautam Shroff, Rohit Rahul. The 14th International Workshop on Neural-Symbolic Learning and Reasoning at IJCAI 2019.
CRESA: A Deep Learning Approach to Competing Risk Recurrent Event Survival Analysis
Garima Gupta, Vishal Sunder, Ranjitha Prasad, Gautam Shroff. The 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD-2019).
2018
Prosocial or Selfish? Agents with different behaviors for Contract Negotiation using Reinforcement Learning
Vishal Sunder, Lovekesh Vig, Arnab Chatterjee, Gautam Shroff. The 11th International Workshop on Automated Negotiations held in conjunction with IJCAI/ECAI 2018.
2017
Information Bottleneck Inspired Method For Chat Text Segmentation
Vishal Sunder, Mohit Yadav, Lovekesh Vig, Gautam Shroff. The 8th International Joint Conference on Natural Language Processing (IJCNLP-2017)