Get started
Author

Boris Ginsburg

Mixed Precision Training
2017 · Micikevicius, Paulius, Narang, Sharan, et al. · arXiv (Cornell University) · 1,177
PDF
Large Batch Training of Convolutional Networks
2017 · You, Yang, Gitman, Igor, et al. · arXiv (Cornell University) · 486
PDF
Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions
2020 · Samuel Kriman, Stanislav Beliaev, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 278
Jasper: An End-to-End Convolutional Neural Acoustic Model
2019 · Jason Li, Vitaly Lavrukhin, et al. · Interspeech (USB) · 248
PDF
Scaling SGD Batch Size to 32K for ImageNet Training.
2017 · Yang You, Igor Gitman, et al. · arXiv (Cornell University) · 200
NeMo: a toolkit for building AI applications using Neural Modules
2019 · Kuchaiev, Oleksii, Li, Jason, et al. · arXiv (Cornell University) · 193
PDF
The ForSpec Temporal Logic: A New Temporal Property-Specification Language
2002 · Roy Armoni, Limor Fix, et al. · Lecture notes in computer science · 167
PDF
TitaNet: Neural Model for Speaker Representation with 1D Depth-Wise Separable Convolutions and Global Context
2022 · Nithin Rao Koluguri, Taejin Park, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 119
OpenChem: A Deep Learning Toolkit for Computational Chemistry and Drug Design
2021 · Maria Korshunova, Boris Ginsburg, et al. · Journal of Chemical Information and Modeling · 109
PDF
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
2022 · Lee, Sang-gil, Ping, Wei, et al. · arXiv (Cornell University) · 103
PDF
MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition
2020 · Somshubra Majumdar, Boris Ginsburg · Interspeech (USB) · 99
PDF
Factorization tricks for LSTM networks
2017 · Kuchaiev, Oleksii, Ginsburg, Boris · arXiv (Cornell University) · 99
PDF
Fast Conformer With Linearly Scalable Attention For Efficient Speech Recognition
2023 · Dima Rekesh, Nithin Rao Koluguri, et al. · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · 96
PDF
Correction of Automatic Speech Recognition with Transformer Sequence-To-Sequence Model
2020 · Oleksii Hrinchuk, Mariya Popova, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 85
PDF
Computational mammography using deep neural networks
2016 · A. Dubrovina, P. Kisilev, et al. · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · 85
Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks
2019 · Ginsburg, Boris, Castonguay, Patrice, et al. · arXiv (Cornell University) · 83
PDF
Hi-Fi Multi-Speaker English TTS Dataset
2021 · Evelina Bakhturina, Vitaly Lavrukhin, et al. · Interspeech (USB) · 72
Training Deep AutoEncoders for Collaborative Filtering
2017 · Kuchaiev, Oleksii, Ginsburg, Boris · arXiv (Cornell University) · 65
PDF
MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection
2021 · Fei Jia, Somshubra Majumdar, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 55
Comparison of Batch Normalization and Weight Normalization Algorithms for the Large-scale Image Classification
2017 · Gitman, Igor, Ginsburg, Boris · arXiv (Cornell University) · 51
PDF
Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition
2021 · Majumdar, Somshubra, Balam, Jagadeesh, et al. · arXiv (Cornell University) · 46
PDF
Training Neural Speech Recognition Systems with Synthetic Speech Augmentation
2018 · Li, Jason, Gadde, Ravi, et al. · arXiv (Cornell University) · 40
PDF
Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq
2018 · Kuchaiev, Oleksii, Ginsburg, Boris, et al. · arXiv (Cornell University) · 39
PDF
SPGISpeech: 5,000 Hours of Transcribed Financial Audio for Fully Formatted End-to-End Speech Recognition
2021 · Patrick K. O’Neill, Vitaly Lavrukhin, et al. · Interspeech (USB) · 36
SALM: Speech-Augmented Language Model with in-Context Learning for Speech Recognition and Translation
2024 · Zhehuai Chen, He Huang, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 35
PDF
Works count: 204
Citation count: 4,871
H-index: 28
I10-index: 55
Year
Topic
Type