Awni Hannun
Awni Hannun
Facebook AI Research
Verified email at fb.com - Homepage
TitleCited byYear
Rectifier nonlinearities improve neural network acoustic models
AL Maas, AY Hannun, AY Ng
Proc. icml 30 (1), 3, 2013
23012013
Deep speech 2: End-to-end speech recognition in english and mandarin
D Amodei, S Ananthanarayanan, R Anubhai, J Bai, E Battenberg, C Case, ...
International conference on machine learning, 173-182, 2016
11902016
Deep speech: Scaling up end-to-end speech recognition
A Hannun, C Case, J Casper, B Catanzaro, G Diamos, E Elsen, ...
arXiv preprint arXiv:1412.5567, 2014
8792014
Cardiologist-level arrhythmia detection with convolutional neural networks
P Rajpurkar, AY Hannun, M Haghpanahi, C Bourn, AY Ng
arXiv preprint arXiv:1707.01836, 2017
2632017
Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network
AY Hannun, P Rajpurkar, M Haghpanahi, GH Tison, C Bourn, ...
Nature medicine 25 (1), 65, 2019
1182019
First-pass large vocabulary continuous speech recognition using bi-directional recurrent dnns
AY Hannun, AL Maas, D Jurafsky, AY Ng
arXiv preprint arXiv:1408.2873, 2014
752014
Building DNN acoustic models for large vocabulary speech recognition
AL Maas, P Qi, Z Xie, AY Hannun, CT Lengerich, D Jurafsky, AY Ng
Computer Speech & Language 41, 195-213, 2017
512017
Persistent rnns: Stashing recurrent weights on-chip
G Diamos, S Sengupta, B Catanzaro, M Chrzanowski, A Coates, E Elsen, ...
International Conference on Machine Learning, 2024-2033, 2016
452016
Systems and methods for speech transcription
A Hannun, C Case, J Casper, B Catanzaro, G Diamos, E Elsen, ...
US Patent App. 14/735,002, 2016
252016
Unsupervised feature learning and deep learning
A Ng, J Ngiam, CY Foo, Y Mai, C Suen, A Coates, A Maas, A Hannun, ...
Technical report, Stanford University, 2013
252013
Learning Multiscale Features Directly from Waveforms
Z Zhu, JH Engel, A Hannun
Interspeech 2016, 1305-1309, 2016
222016
Recurrent neural network feature enhancement: The 2nd CHiME challenge
AL Maas, TM O’Neil, AY Hannun, AY Ng
Proceedings The 2nd CHiME Workshop on Machine Listening in Multisource …, 2013
222013
Sequence modeling with ctc
A Hannun
Distill 2 (11), e8, 2017
202017
Deployed end-to-end speech recognition
B Catanzaro, J Chen, M Chrzanowski, E Elsen, J Engel, C Fougner, ...
US Patent App. 15/358,083, 2017
152017
Increasing deep neural network acoustic model size for large vocabulary continuous speech recognition
AL Maas, AY Hannun, CT Lengerich, P Qi, D Jurafsky, AY Ng
arXiv preprint arXiv:1406.7806, 2014
152014
Wav2Letter++: A Fast Open-source Speech Recognition System
V Pratap, A Hannun, Q Xu, J Cai, J Kahn, G Synnaeve, V Liptchinsky, ...
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
14*2019
Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions
A Hannun, A Lee, Q Xu, R Collobert
arXiv preprint arXiv:1904.02619, 2019
9*2019
An end-to-end architecture for keyword spotting and voice activity detection
C Lengerich, A Hannun
arXiv preprint arXiv:1611.09405, 2016
92016
Lookahead Convolution Layer for Unidirectional Recurrent Neural Networks
C Wang, D Yogatama, A Coates, T Han, A Hannun, B Xiao
8
GlimpseNet: Attentional Methods for Full-Image Mammogram Diagnosis
W Hang, Z Liu, A Hannun
Stanford AI Lab Internal Report, Stanford University, Stanford, CA, USA, 2017
52017
The system can't perform the operation now. Try again later.
Articles 1–20