177 citations · 494 across the 14 of their papers we have counts for
5 papers · 1 filter
Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens
Rafael Valle, Jason Li, Ryan Prenger +1
Mellotron is a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data. By explicitly conditioning…
QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions
Samuel Kriman, Stanislav Beliaev, Boris Ginsburg +6
We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block cons…
NeMo: a toolkit for building AI applications using Neural Modules
Oleksii Kuchaiev, Jason Li, Huyen Nguyen +11
NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition. NeMo is built around neural modules, c…
Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks
Boris Ginsburg, Patrice Castonguay, Oleksii Hrinchuk +7
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for ima…
Jasper: An End-to-End Convolutional Neural Acoustic Model
Jason Li, Vitaly Lavrukhin, Boris Ginsburg +5
In this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data. Our model, Jasper, uses only 1D conv…