Boris Ginsburg

Boris Ginsburg, Oktai Tatanov, Stanislav Beliaev, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Large Batch Training of Convolutional Networks

Yang You, Boris Ginsburg, Igor Gitman, 2017, 1708.03888.

Jasper: An End-to-End Convolutional Neural Acoustic Model

Boris Ginsburg, Oleksii Kuchaiev, Huyen Nguyen, 2019, INTERSPEECH.

Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq

Boris Ginsburg, Oleksii Kuchaiev, Paulius Micikevicius, 2018, 1805.10387.

OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models pdf

Boris Ginsburg, Oleksii Kuchaiev, Paulius Micikevicius, 2018, ArXiv.

Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers

Boris Ginsburg, Subhankar Ghosh, Cheng-Ping Hsieh, 2022, INTERSPEECH 2023.

Comparison of Batch Normalization and Weight Normalization Algorithms for the Large-scale Image Classification pdf

Boris Ginsburg, Igor Gitman, Boris Ginsburg, 2017, ArXiv.

TitaNet: Neural Model for Speaker Representation with 1D Depth-Wise Separable Convolutions and Global Context pdf

Boris Ginsburg, Nithin Rao Koluguri, Taejin Park, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions

Boris Ginsburg, Oleksii Kuchaiev, Yang Zhang, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Unified Transformer-based Framework for Duplex Text Normalization pdf

Boris Ginsburg, Evelina Bakhturina, Tuan Manh Lai, 2021, ArXiv.

TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction

Boris Ginsburg, Stanislav Beliaev, 2021, ArXiv.

Correction of Automatic Speech Recognition with Transformer Sequence-To-Sequence Model

Boris Ginsburg, Mariya Popova, Oleksii Hrinchuk, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

AmberNet: A Compact End-to-End Model for Spoken Language Identification

Nithin Rao Koluguri, Boris Ginsburg, J. Balam, 2022, ArXiv.

ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-supervised Speech Representations

Boris Ginsburg, Jason Li, Shehzeen Samarah Hussain, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Adapting TTS models For New Speakers using Transfer Learning

Boris Ginsburg, Jason Li, Paarth Neekhara, 2021, ArXiv.

Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition

Boris Ginsburg, Somshubra Majumdar, Oleksii Hrinchuk, 2021, 2104.01721.

Cross-Language Transfer Learning and Domain Adaptation for End-to-End Automatic Speech Recognition

Boris Ginsburg, Jing Xiao, Jianzong Wang, 2021, 2021 IEEE International Conference on Multimedia and Expo (ICME).

Powerful and Extensible WFST Framework for RNN-Transducer Losses

Boris Ginsburg, A. Laptev, Igor Gitman, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

NeMo: a toolkit for building AI applications using Neural Modules pdf

Boris Ginsburg, Oleksii Kuchaiev, Jason Li, 2019, ArXiv.

Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models

Boris Ginsburg, K. C. Puvvada, Samuel Kriman, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

SpeakerNet: 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verification.

Boris Ginsburg, Nithin Rao Koluguri, Jason Li, 2020, 2010.12653.

Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition

Boris Ginsburg, Oleksii Kuchaiev, Patrick O'Neill, 2020, 2005.04290.

Training Neural Speech Recognition Systems with Synthetic Speech Augmentation pdf

Boris Ginsburg, Jason Li, Vitaly Lavrukhin, 2018, ArXiv.

CTC Variations Through New WFST Topologies

Boris Ginsburg, A. Laptev, Somshubra Majumdar, 2021, INTERSPEECH.

TalkNet: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis

Boris Ginsburg, Stanislav Beliaev, Boris Ginsburg, 2021, Interspeech.

MarbleNet: Deep 1D Time-Channel Separable Convolutional Neural Network for Voice Activity Detection

Boris Ginsburg, Somshubra Majumdar, Fei Jia, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Hi-Fi Multi-Speaker English TTS Dataset

Boris Ginsburg, Yang Zhang, Evelina Bakhturina, 2021, Interspeech.

SPGISpeech: 5, 000 hours of transcribed financial audio for fully formatted end-to-end speech recognition pdf

Shinji Watanabe, Boris Ginsburg, Somshubra Majumdar, 2021, Interspeech.

Multi-blank Transducers for Speech Recognition

Boris Ginsburg, Shinji Watanabe, Hainan Xu, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Efficient Sequence Transduction by Jointly Predicting Tokens and Durations

Boris Ginsburg, Shinji Watanabe, Hainan Xu, 2023, arXiv.org.

Improving Noise Robustness of an End-to-End Neural Model for Automatic Speech Recognition

Boris Ginsburg, Somshubra Majumdar, Jagadeesh Balam, 2020, 2010.12715.

MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognition

Boris Ginsburg, Somshubra Majumdar, 2020, INTERSPEECH.

Training Deep AutoEncoders for Collaborative Filtering pdf

Boris Ginsburg, Oleksii Kuchaiev, Boris Ginsburg, 2017, ArXiv.

The ForSpec Temporal Logic: A New Temporal Property-Specification Language

Avner Landver, Moshe Y. Vardi, Boris Ginsburg, 2002, TACAS.

Large Batch Training of Convolutional Networks with Layer-wise Adaptive Rate Scaling

Yang You, Boris Ginsburg, Igor Gitman, 2018 .