Training speech recognition models with federated learning: A quality/cost framework D Guliani, F Beaufays, G Motta ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 77 | 2021 |
Personalization of end-to-end speech recognition on mobile devices for named entities KC Sim, F Beaufays, A Benard, D Guliani, A Kabel, N Khare, T Lucassen, ... 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 23-30, 2019 | 58 | 2019 |
Partial variable training for efficient on-device federated learning TJ Yang, D Guliani, F Beaufays, G Motta ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 27 | 2022 |
Enabling on-device training of speech recognition models with federated dropout D Guliani, L Zhou, C Ryu, TJ Yang, H Zhang, Y Xiao, F Beaufays, G Motta ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 14 | 2022 |
Exploring heterogeneous characteristics of layers in ASR models for more efficient training L Zhou, D Guliani, A Kabel, G Motta, F Beaufays ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 3 | 2022 |
Identifying and correcting automatic speech recognition (asr) misrecognitions in a decentralized manner R Mathews, R Prabhavalkar, G Motta, M Chen, L Zhou, D Guliani, ... US Patent App. 17/958,887, 2024 | | 2024 |
The Gift of Feedback: Improving ASR Model Quality by Learning from User Corrections Through Federated Learning L Zhou, Y Ding, M Chen, H Zhang, R Prabhavalkar, D Guliani, G Motta, ... 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-7, 2023 | | 2023 |
Exploring Heterogeneous Characteristics of Layers In ASR Models For More Efficient Training D Guliani, L Zhou, A Kebel, G Motta, F Beaufays US Patent App. 17/938,015, 2023 | | 2023 |