Shubham Toshniwal
Shubham Toshniwal
Senior Research Scientist, NVIDIA
E-mailová adresa ověřena na: - Domovská stránka
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ...
arXiv preprint arXiv:2206.04615, 2022
Multilingual speech recognition with a single end-to-end model
S Toshniwal, TN Sainath, RJ Weiss, B Li, P Moreno, E Weinstein, K Rao
ICASSP 2018, 2018
Lingvo: a modular and scalable framework for sequence-to-sequence modeling
J Shen, P Nguyen, Y Wu, Z Chen, MX Chen, Y Jia, A Kannan, T Sainath, ...
arXiv preprint arXiv:1902.08295, 2019
A comparison of techniques for language model integration in encoder-decoder speech recognition
S Toshniwal, A Kannan, CC Chiu, Y Wu, TN Sainath, K Livescu
SLT 2018, 2018
Multitask learning with low-level auxiliary tasks for encoder-decoder based speech recognition
S Toshniwal, H Tang, L Lu, K Livescu
Interspeech 2017, 2017
Pre-Trained Text Embeddings for Enhanced Text-to-Speech Synthesis
T Hayashi, S Watanabe, T Toda, K Takeda, S Toshniwal, K Livescu
Interspeech 2019, 2019
Parsing speech: a neural approach to integrating lexical and acoustic-prosodic information
T Tran, S Toshniwal, M Bansal, K Gimpel, K Livescu, M Ostendorf
NAACL 2018, 2017
Jointly learning to align and convert graphemes to phonemes with neural attention models
S Toshniwal, K Livescu
SLT 2016, 2016
Generating natural language dialog using a questions corpus
J Ajmera, AK Gupta, S Joshi, S Toshniwal
US Patent 10,049,152, 2018
Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks
S Toshniwal, S Wiseman, A Ettinger, K Livescu, K Gimpel
EMNLP 2020, 2020
Hierarchical multitask learning for ctc-based speech recognition
K Krishna, S Toshniwal, K Livescu
arXiv preprint arXiv:1807.06234, 2018
A Cross-Task Analysis of Text Span Representations
S Toshniwal, H Shi, B Shi, L Gao, K Livescu, K Gimpel
RepL4NLP 2020, 2020
On Generalization in Coreference Resolution
S Toshniwal, P Xia, S Wiseman, K Livescu, K Gimpel
CRAC@EMNLP 2021, 2021
Learning Chess Blindfolded: Evaluating Language Models on State Tracking
S Toshniwal, S Wiseman, K Livescu, K Gimpel
AAAI 2022, 2021
VibRein: an engaging and assistive mobile learning companion for students with intellectual disabilities
S Toshniwal, P Dey, N Rajput, S Srivastava
Proceedings of the annual meeting of the Australian special interest group …, 2015
Adapting pretrained text-to-text models for long text sequences
W Xiong, A Gupta, S Toshniwal, Y Mehdad, W Yih
arXiv preprint arXiv:2209.10052, 2022
PeTra: A Sparsely Supervised Memory Model for People Tracking
S Toshniwal, A Ettinger, K Gimpel, K Livescu
ACL 2020, 2020
Read, attend and pronounce: An attention-based approach for grapheme-to-phoneme conversion
S Toshniwal, K Livescu
Workshop on Machine Learning in Speech and Language Processing (MLSLP …, 2016
USHER: an intelligent tour companion
S Toshniwal, P Sharma, S Srivastava, R Sehgal
Proceedings of the 20th International Conference on Intelligent User …, 2015
Learning to Reason and Memorize with Self-Notes
J Lanchantin, S Toshniwal, J Weston, A Szlam, S Sukhbaatar
arXiv preprint arXiv:2305.00833, 2023
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–20