| A streaming on-device end-to-end model surpassing server-side conventional model quality and latency TN Sainath, Y He, B Li, A Narayanan, R Pang, A Bruguier, S Chang, W Li, ... ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 201 | 2020 |
| Lingvo: a modular and scalable framework for sequence-to-sequence modeling J Shen, P Nguyen, Y Wu, Z Chen, MX Chen, Y Jia, A Kannan, T Sainath, ... arXiv preprint arXiv:1902.08295, 2019 | 184 | 2019 |
| Exploring the nature of “trader intuition” AJ Bruguier, SR Quartz, P Bossaerts The Journal of Finance 65 (5), 1703-1723, 2010 | 139 | 2010 |
| On the compression of recurrent neural networks with an application to LVCSR acoustic modeling for embedded speech recognition R Prabhavalkar, O Alsharif, A Bruguier, L McGraw 2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016 | 111 | 2016 |
| On the choice of modeling unit for sequence-to-sequence speech recognition K Irie, R Prabhavalkar, A Kannan, A Bruguier, D Rybach, P Nguyen arXiv preprint arXiv:1902.01955, 2019 | 50 | 2019 |
| Phoebe: Pronunciation-aware contextualization for end-to-end speech recognition A Bruguier, R Prabhavalkar, G Pundak, TN Sainath ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 48 | 2019 |
| Learning personalized entity pronunciations AJ Bruguier, F Peng, F Beaufays US Patent 10,152,965, 2018 | 34 | 2018 |
| Investigating signal integration with canonical correlation analysis of fMRI brain activation data A Bruguier, K Preuschoff, S Quartz, P Bossaerts Neuroimage 41 (1), 35-44, 2008 | 24 | 2008 |
| Improved neural language model fusion for streaming recurrent neural network transducer S Kim, Y Shangguan, J Mahadeokar, A Bruguier, C Fuegen, ML Seltzer, ... ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 23 | 2021 |
| Compressed recurrent neural network models O Alsharif, RP Prabhavalkar, IC McGraw, AJ Bruguier US Patent 10,878,319, 2020 | 21 | 2020 |
| Model unit exploration for sequence-to-sequence speech recognition K Irie, R Prabhavalkar, A Kannan, A Bruguier, D Rybach, P Nguyen arXiv preprint arXiv:1902.01955, 2019 | 21 | 2019 |
| Optimizing OPC data sampling based on" orthogonal vector space" Y Sun, YM Foong, Y Wang, J Cheng, D Zhang, S Gao, N Chen, BI Choi, ... Optical Microlithography XXIV 7973, 867-876, 2011 | 20 | 2011 |
| Phoneme-based contextualization for cross-lingual speech recognition in end-to-end models K Hu, A Bruguier, TN Sainath, R Prabhavalkar, G Pundak arXiv preprint arXiv:1906.09292, 2019 | 18 | 2019 |
| Pronunciation Learning with RNN-Transducers. A Bruguier, D Gnanapragasam, L Johnson, K Rao, F Beaufays INTERSPEECH, 2556-2560, 2017 | 15 | 2017 |
| Learning personalized pronunciations for contact names recognition T Bruguier, F Peng, F Beaufays | 15 | 2016 |
| NN-grams: Unifying neural network and n-gram language models for speech recognition B Damavandi, S Kumar, N Shazeer, A Bruguier arXiv preprint arXiv:1606.07470, 2016 | 11 | 2016 |
| Dictionary Augmented Sequence-to-Sequence Neural Network for Grapheme to Phoneme Prediction. A Bruguier, A Bakhtin, D Sharma INTERSPEECH, 3733-3737, 2018 | 8 | 2018 |
| Calibration pattern selection based on noise sensitivity AJ Bruguier, W Shao, LAN Song US Patent 8,887,105, 2014 | 8 | 2014 |
| Model-based scanner tuning in a manufacturing environment CY Shih, RC Peng, TC Chien, YW Guo, JY Lee, CL Chang, PC Huang, ... Optical Microlithography XXII 7274, 269-275, 2009 | 8 | 2009 |
| Neural-FST class language model for end-to-end speech recognition A Bruguier, D Le, R Prabhavalkar, D Li, Z Liu, B Wang, E Chang, F Peng, ... ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 7 | 2022 |
