AH
Awni Y. Hannun
cs.LGcs.CLeess.AScs.SDstat.MLcs.NEcs.CRcs.AICardiologistscs.CV
On Valency
published · living versionsW_4bw3veuq·v1 · currentpublished
Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks
with Pranav Rajpurkar, Masoumeh Haghpanahi, Codie Bourn, Andrew Y. Ng
1 version
W_rk3e7h7w·v1published
Preprints & journals
39 papers in the corpus · 2014–2025Compute-Optimal Quantization-Aware Training2509.22935v2 · Aleksandr Dremov, David Grangier, Angelos Katharopoulos et al.2025 · 0 citationsInternational Conference on Learning Representations (ICLR), 2026
Need a Small Specialized Language Model? Plan Early!2402.01093v2 · David Grangier, Angelos Katharopoulos, Pierre Ablin et al.2024 · 2 citationsarXiv
Adaptive Training Distributions with Scalable Online Bilevel Optimization2311.11973v1 · David Grangier, Pierre Ablin, Awni Hannun2023 · 0 citationsarXiv
Transfer Learning for Structured Pruning under Limited Task Data2311.06382v1 · Lucio Dery, David Grangier, Awni Hannun2023 · 0 citationsarXiv
Flashlight: Enabling Innovation in Tools for Machine Learning2201.12465v2 · Jacob Kahn, Vineel Pratap, Tatiana Likhomanenko et al.2022 · 16 citationsarXiv
Star Temporal Classification: Sequence Classification with Partially Labeled Data2201.12208v2 · Vineel Pratap, Awni Hannun, Gabriel Synnaeve et al.2022 · 5 citationsarXiv
Parallel Composition of Weighted Finite-State Transducers2110.02848v1 · Shubho Sengupta, Vineel Pratap, Awni Hannun2021 · 3 citationsarXiv
CrypTen: Secure Multi-Party Computation Meets Machine Learning2109.00984v2 · Brian Knott, Shobha Venkataraman, Awni Hannun et al.2021 · 227 citationsarXiv
The History of Speech Recognition to the Year 20302108.00084v1 · Awni Hannun2021 · 16 citationsarXiv
The Role of Evolution in Machine Intelligence2106.11151v1 · Awni Hannun2021 · 2 citationsarXiv
Gradient Matching for Domain Generalization2104.09937v3 · Yuge Shi, Jeffrey Seely, Philip H.S. Torr et al.2021 · 120 citationsarXiv
Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems2103.11766v2 · Ruihan Wu, Chuan Guo, Awni Hannun et al.2021 · 6 citationsarXiv
Measuring Data Leakage in Machine-Learning Models with Fisher Information2102.11673v3 · Awni Hannun, Chuan Guo, Laurens van der Maaten2021 · 19 citationsarXiv
Data Appraisal Without Data Sharing2012.06430v2 · Mimee Xu, Laurens van der Maaten, Awni Hannun2020 · 1 citationarXiv
Differentiable Weighted Finite-State Transducers2010.01003v1 · Awni Hannun, Vineel Pratap, Jacob Kahn et al.2020 · 24 citationsarXiv
The Trade-Offs of Private Prediction2007.05089v1 · Laurens van der Maaten, Awni Hannun2020 · 5 citationsarXiv
Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters2007.03001v2 · Vineel Pratap, Anuroop Sriram, Paden Tomasello et al.2020 · 118 citationsarXiv
Iterative Pseudo-Labeling for Speech Recognition2005.09267v2 · Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn et al.2020 · 112 citationsarXiv
Semi-Supervised Speech Recognition via Local Prior Matching2002.10336v1 · Wei-Ning Hsu, Ann Lee, Gabriel Synnaeve et al.2020 · 26 citationsarXiv
Scaling Up Online Speech Recognition Using ConvNets2001.09727v1 · Vineel Pratap, Qiantong Xu, Jacob Kahn et al.2020 · 52 citationsarXiv
Secure multiparty computations in floating-point arithmetic2001.03192v1 · Chuan Guo, Awni Hannun, Brian Knott et al.2020 · 18 citationsInformation and Inference: a Journal of the IMA, iaaa038: 1-33, 2021
Certified Data Removal from Machine Learning Models1911.03030v6 · Chuan Guo, Tom Goldstein, Awni Hannun et al.2019 · 160 citationsarXiv
Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition1910.07323v1 · Adrien Dufraux, Emmanuel Vincent, Awni Hannun et al.2019 · 9 citationsarXiv
Privacy-Preserving Multi-Party Contextual Bandits1910.05299v3 · Awni Hannun, Brian Knott, Shubho Sengupta et al.2019 · 8 citationsarXiv
Self-Training for End-to-End Speech Recognition1909.09116v2 · Jacob Kahn, Ann Lee, Awni Hannun2019 · 205 citationsarXiv
Word-level Speech Recognition with a Letter to Word Encoder1906.04323v2 · Ronan Collobert, Awni Hannun, Gabriel Synnaeve2019 · 5 citationsarXiv
Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions1904.02619v1 · Awni Hannun, Ann Lee, Qiantong Xu et al.2019 · 83 citationsarXiv
Publisher Correction: Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network.30679787 · Hannun, Awni Y, Rajpurkar, Pranav, Haghpanahi, Masoumeh et al.2019 · 55 citationsNature medicine. 2019;25(3):530
A Fully Differentiable Beam Search Decoder1902.06022v1 · Ronan Collobert, Awni Hannun, Gabriel Synnaeve2019 · 24 citationsarXiv
Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network.30617320 · Hannun, Awni Y, Rajpurkar, Pranav, Haghpanahi, Masoumeh et al.2019 · 3,140 citationsNature medicine. 2019;25(1):65-69
wav2letter++: The Fastest Open-source Speech Recognition System1812.07625v1 · Vineel Pratap, Awni Hannun, Qiantong Xu et al.2018 · 174 citationsarXiv
Ambulatory Atrial Fibrillation Monitoring Using Wearable Photoplethysmography with Deep Learning1811.07774v2 · Maxime Voisin, Yichen Shen, Alireza Aliamiri et al.2018 · 75 citationsarXiv
Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks1707.01836v1 · Pranav Rajpurkar, Awni Y. Hannun, Masoumeh Haghpanahi et al.2017 · 611 citationsarXivon Valency
An End-to-End Architecture for Keyword Spotting and Voice Activity Detection1611.09405v1 · Chris Lengerich, Awni Hannun2016 · 41 citationsarXiv
Learning Multiscale Features Directly From Waveforms1603.09509v2 · Zhenyao Zhu, Jesse H. Engel, Awni Hannun2016 · 70 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
First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs1408.2873v2 · Awni Y. Hannun, Andrew L. Maas, Daniel Jurafsky et al.2014 · 144 citationsarXiv
Building DNN Acoustic Models for Large Vocabulary Speech Recognition1406.7806v2 · Andrew L. Maas, Peng Qi, Ziang Xie et al.2014 · 120 citationsarXiv
Career total: 59 works. 39 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.