Vishal Sunder

24 papers A 2C 1Misc 6Journal 12Unranked 3
YearRankTypeTitle / Venue / Authors
2025 Misc conf
A Non-autoregressive Model for Joint STT and TTS.
ICASSP
Vishal Sunder, Brian Kingsbury, George Saon, Samuel Thomas, Slava Shechtman, Hagai Aronowitz, Eric Fosler-Lussier, Luis A. Lastras
2025 J jnl
A Non-autoregressive Model for Joint STT and TTS.
CoRR
Vishal Sunder, Brian Kingsbury, George Saon, Samuel Thomas, Slava Shechtman, Hagai Aronowitz, Eric Fosler-Lussier, Luis A. Lastras
2025 C conf
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities.
ASRU
George Saon, Avihu Dekel, Alexander Brooks, Tohru Nagano, Abraham Daniels, Aharon Satt, Ashish R. Mittal, Brian Kingsbury, David Haws, Edmilson Da Silva Morais, Gakuto Kurata, Hagai Aronowitz, Ibrahim Ibrahim, Hong-Kwang Kuo, Kate Soule, Luis A. Lastras, Masayuki Suzuki, Ron Hoory, Samuel Thomas, Sashi Novitasari, Takashi Fukuda, Vishal Sunder, Xiaodong Cui, Zvi Kons
2025 J jnl
Improving Transducer-Based Spoken Language Understanding with Self-Conditioned CTC and Knowledge Transfer.
CoRR
Vishal Sunder, Eric Fosler-Lussier
2024 Misc conf
End-To-End Real Time Tracking of Children's Reading with Pointer Network.
ICASSP
Vishal Sunder, Beulah Karrolla, Eric Fosler-Lussier
2024 — conf
Improving Transducer-Based Spoken Language Understanding With Self-Conditioned CTC and Knowledge Transfer.
SLT
Vishal Sunder, Eric Fosler-Lussier
2023 A conf
ConvKT: Conversation-Level Knowledge Transfer for Context Aware End-to-End Spoken Language Understanding.
INTERSPEECH
Vishal Sunder, Eric Fosler-Lussier, Samuel Thomas, Hong-Kwang Jeff Kuo, Brian Kingsbury
2023 Misc conf
End-to-End Word-Level Disfluency Detection and Classification in Children's Reading Assessment.
ICASSP
Lavanya Venkatasubramaniam, Vishal Sunder, Eric Fosler-Lussier
2023 J jnl
End-to-End real time tracking of children's reading with pointer network.
CoRR
Vishal Sunder, Beulah Karrolla, Eric Fosler-Lussier
2023 Misc conf
Fine-Grained Textual Knowledge Transfer to Improve RNN Transducers for Speech Recognition and Understanding.
ICASSP
Vishal Sunder, Samuel Thomas, Hong-Kwang Jeff Kuo, Brian Kingsbury, Eric Fosler-Lussier
2022 J jnl
Building an ASR Error Robust Spoken Virtual Patient System in a Highly Class-Imbalanced Scenario Without Speech Data.
CoRR
Vishal Sunder, Prashant Serai, Eric Fosler-Lussier
2022 J jnl
Hallucination of Speech Recognition Errors With Sequence to Sequence Learning.
IEEE ACM Trans. Audio Speech Lang. Process.
Prashant Serai, Vishal Sunder, Eric Fosler-Lussier
2022 A conf
Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems.
INTERSPEECH
Vishal Sunder, Eric Fosler-Lussier, Samuel Thomas, Hong-Kwang Kuo, Brian Kingsbury
2022 J jnl
Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems.
CoRR
Vishal Sunder, Eric Fosler-Lussier, Samuel Thomas, Hong-Kwang Jeff Kuo, Brian Kingsbury
2022 Misc conf
Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding.
ICASSP
Vishal Sunder, Samuel Thomas, Hong-Kwang Jeff Kuo, Jatin Ganhotra, Brian Kingsbury, Eric Fosler-Lussier
2022 J jnl
Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding.
CoRR
Vishal Sunder, Samuel Thomas, Hong-Kwang Jeff Kuo, Jatin Ganhotra, Brian Kingsbury, Eric Fosler-Lussier
2021 J jnl
Hallucination of speech recognition errors with sequence to sequence learning.
CoRR
Prashant Serai, Vishal Sunder, Eric Fosler-Lussier
2021 Misc conf
Handling Class Imbalance in Low-Resource Dialogue Systems by Combining Few-Shot Classification and Interpolation.
ICASSP
Vishal Sunder, Eric Fosler-Lussier
2020 J jnl
Handling Class Imbalance in Low-Resource Dialogue Systems by Combining Few-Shot Classification and Interpolation.
CoRR
Vishal Sunder, Eric Fosler-Lussier
2019 — conf
CRESA: A Deep Learning Approach to Competing Risks, Recurrent Event Survival Analysis.
PAKDD (2)
Garima Gupta, Vishal Sunder, Ranjitha Prasad, Gautam Shroff
2019 — conf
One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesis.
NeSy@IJCAI
Vishal Sunder, Ashwin Srinivasan, Lovekesh Vig, Gautam Shroff, Rohit Rahul
2019 J jnl
One-shot Information Extraction from Document Images using Neuro-Deductive Program Synthesis.
CoRR
Vishal Sunder, Ashwin Srinivasan, Lovekesh Vig, Gautam Shroff, Rohit Rahul
2018 J jnl
CIKM AnalytiCup 2017 Lazada Product Title Quality Challenge An Ensemble of Deep and Shallow Learning to predict the Quality of Product Titles.
CoRR
Karamjit Singh, Vishal Sunder
2018 J jnl
Prosocial or Selfish? Agents with different behaviors for Contract Negotiation using Reinforcement Learning.
CoRR
Vishal Sunder, Lovekesh Vig, Arnab Chatterjee, Gautam Shroff