Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments

no code implementations • ICLR 2020 • Boris Ginsburg, Patrice Castonguay, Oleksii Hrinchuk, Oleksii Kuchaiev, Vitaly Lavrukhin, Ryan Leary, Jason Li, Huyen Nguyen, Yang Zhang, Jonathan M. Cohen

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay.

General Classification Image Classification +5

GPU-Accelerated Viterbi Exact Lattice Decoder for Batched Online and Offline Speech Recognition

1 code implementation • 22 Oct 2019 • Hugo Braun, Justin Luitjens, Ryan Leary, Tim Kaldewey, Daniel Povey

We present an optimized weighted finite-state transducer (WFST) decoder capable of online streaming and offline batch processing of audio using Graphics Processing Units (GPUs).

speech-recognition Speech Recognition

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

15 code implementations • 22 Oct 2019 • Samuel Kriman, Stanislav Beliaev, Boris Ginsburg, Jocelyn Huang, Oleksii Kuchaiev, Vitaly Lavrukhin, Ryan Leary, Jason Li, Yang Zhang

We propose a new end-to-end neural acoustic model for automatic speech recognition.

Speech Recognition Audio and Speech Processing

NeMo: a toolkit for building AI applications using Neural Modules

1 code implementation • 14 Sep 2019 • Oleksii Kuchaiev, Jason Li, Huyen Nguyen, Oleksii Hrinchuk, Ryan Leary, Boris Ginsburg, Samuel Kriman, Stanislav Beliaev, Vitaly Lavrukhin, Jack Cook, Patrice Castonguay, Mariya Popova, Jocelyn Huang, Jonathan M. Cohen

NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks

3 code implementations • 27 May 2019 • Boris Ginsburg, Patrice Castonguay, Oleksii Hrinchuk, Oleksii Kuchaiev, Vitaly Lavrukhin, Ryan Leary, Jason Li, Huyen Nguyen, Yang Zhang, Jonathan M. Cohen

We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay.

General Classification speech-recognition +2

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

10 code implementations • 5 Apr 2019 • Jason Li, Vitaly Lavrukhin, Boris Ginsburg, Ryan Leary, Oleksii Kuchaiev, Jonathan M. Cohen, Huyen Nguyen, Ravi Teja Gadde

In this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data.

Language Modelling Speech Recognition

Exploratory Analysis of Social Media Prior to a Suicide Attempt

no code implementations • WS 2016 • Glen Coppersmith, Kim Ngo, Ryan Leary, Anthony Wood

Emotion Classification