EE
Erich Elsen
cs.LGstat.MLcs.CLcs.SDeess.AScs.AIcs.CVcs.NEcs.DCcs.CE
On Valency
published · living versionsW_rk3e7h7w·v1 · currentpublished
Deep Speech: Scaling up end-to-end speech recognition
with Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro +6
1 version
Preprints & journals
29 papers in the corpus · 2007–2026OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning2603.08655v1 · Krista Opsahl-Ong, Arnav Singhvi, Jasmine Collins et al.2026 · 0 citationsarXiv
The State of Sparse Training in Deep Reinforcement Learning2206.10369v1 · Laura Graesser, Utku Evci, Erich Elsen et al.2022 · 5 citationsarXiv
Training Compute-Optimal Large Language Models2203.15556v1 · Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch et al.2022 · 925 citationsarXiv
Unified Scaling Laws for Routed Language Models2202.01169v2 · Aidan Clark, Diego de las Casas, Aurelia Guy et al.2022 · 40 citationsarXiv
Step-unrolled Denoising Autoencoders for Text Generation2112.06749v3 · Nikolay Savinov, Junyoung Chung, Mikolaj Binkowski et al.2021 · 35 citationsarXiv
Improving language models by retrieving from trillions of tokens2112.04426v3 · Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann et al.2021 · 382 citationsarXiv
Scaling Language Models: Methods, Analysis & Insights from Training Gopher2112.11446v2 · Jack W. Rae, Sebastian Borgeaud, Trevor Cai et al.2021 · 234 citationsarXiv
Top-KAST: Top-K Always Sparse Training2106.03517v1 · Siddhant M. Jayakumar, Razvan Pascanu, Jack W. Rae et al.2021 · 38 citationsAdvances in Neural Information Processing Systems, 33, 20744-20754
On the Generalization Benefit of Noise in Stochastic Gradient Descent2006.15081v1 · Samuel L. Smith, Erich Elsen, Soham De2020 · 39 citationsarXiv
Sparse GPU Kernels for Deep Learning2006.10901v2 · Trevor Gale, Matei Zaharia, Cliff Young et al.2020 · 177 citationsarXiv
A Practical Sparse Approximation for Real Time Recurrent Learning2006.07232v1 · Jacob Menick, Erich Elsen, Utku Evci et al.2020 · 9 citationsarXiv
AlgebraNets2006.07360v2 · Jordan Hoffmann, Simon Schmitt, Simon Osindero et al.2020 · 2 citationsarXiv
End-to-End Adversarial Text-to-Speech2006.03575v3 · Jeff Donahue, Sander Dieleman, Miko\laj Bi'nkowski et al.2020 · 121 citationsarXiv
Rigging the Lottery: Making All Tickets Winners1911.11134v3 · Utku Evci, Trevor Gale, Jacob Menick et al.2019 · 282 citationsProceedings of the 37th International Conference on Machine Learning (2020) 471-481
Fast Sparse ConvNets1911.09723v1 · Erich Elsen, Marat Dukhan, Trevor Gale et al.2019 · 110 citationsarXiv
High Fidelity Speech Synthesis with Adversarial Networks1909.11646v2 · Miko\laj Bi'nkowski, Jeff Donahue, Sander Dieleman et al.2019 · 190 citationsarXiv
The Difficulty of Training Sparse Neural Networks1906.10732v3 · Utku Evci, Fabian Pedregosa, Aidan Gomez et al.2019 · 47 citationsarXiv
Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods1906.03139v1 · Karel Lenc, Erich Elsen, Tom Schaul et al.2019 · 4 citationsarXiv
The State of Sparsity in Deep Neural Networks1902.09574v1 · Trevor Gale, Erich Elsen, Sara Hooker2019 · 440 citationsarXiv
Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset1810.12247v5 · Curtis Hawthorne, Andriy Stasyuk, Adam Roberts et al.2018 · 301 citationsarXiv
Efficient Neural Audio Synthesis1802.08435v2 · Nal Kalchbrenner, Erich Elsen, Karen Simonyan et al.2018 · 526 citationsarXiv
Parallel WaveNet: Fast High-Fidelity Speech Synthesis1711.10433v1 · Aaron van den Oord, Yazhe Li, Igor Babuschkin et al.2017 · 518 citationsarXiv
Onsets and Frames: Dual-Objective Piano Transcription1710.11153v2 · Curtis Hawthorne, Erich Elsen, Jialin Song et al.2017 · 186 citationsarXiv
Mixed Precision Training1710.03740v3 · Paulius Micikevicius, Sharan Narang, Jonah Alben et al.2017 · 1,177 citationsarXiv
Exploring Sparsity in Recurrent Neural Networks1704.05119v2 · Sharan Narang, Erich Elsen, Gregory Diamos et al.2017 · 218 citationsarXiv
DSD: Dense-Sparse-Dense Training for Deep Neural Networks1607.04381v2 · Song Han, Jeff Pool, Sharan Narang et al.2016 · 164 citationsarXiv
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin1512.02595v1 · Dario Amodei, Rishita Anubhai, Eric Battenberg et al.2015 · 2,110 citationsarXiv
Deep Speech: Scaling up end-to-end speech recognition1412.5567v2 · Awni Hannun, Carl Case, Jared Casper et al.2014 · 1,490 citationsarXivon Valency
N-Body Simulations on GPUs0706.3060v1 · Erich Elsen, V. Vishal, Mike Houston et al.2007 · 36 citationsarXiv
Career total: 46 works. 29 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.