Vitaly Lavrukhin
Nvidia (United States)(US)
Publications by Year
Research Areas
Speech Recognition and Synthesis, Natural Language Processing Techniques, Speech and Audio Processing, Music and Audio Processing, Topic Modeling
Most-Cited Works
- → Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions(2020)277 cited
- → Jasper: An End-to-End Convolutional Neural Acoustic Model(2019)214 cited
- → NeMo: a toolkit for building AI applications using Neural Modules(2019)176 cited
- → Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks(2019)88 cited
- → Hi-Fi Multi-Speaker English TTS Dataset(2021)65 cited
- → Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition(2021)43 cited
- → Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq(2018)41 cited
- → Training Neural Speech Recognition Systems with Synthetic Speech Augmentation(2018)41 cited