The Gift of Feedback: Improving ASR Model Quality by Learning from User Corrections through Federated Learning

no code implementations • 29 Sep 2023 • Lillian Zhou, Yuxin Ding, Mingqing Chen, Harry Zhang, Rohit Prabhavalkar, Dhruv Guliani, Giovanni Motta, Rajiv Mathews

Automatic speech recognition (ASR) models are typically trained on large datasets of transcribed speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training

no code implementations • 8 Oct 2021 • Lillian Zhou, Dhruv Guliani, Andreas Kabel, Giovanni Motta, Françoise Beaufays

Transformer-based architectures have been the subject of research aimed at understanding their overparameterization and the non-uniform importance of their layers.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Enabling On-Device Training of Speech Recognition Models with Federated Dropout

no code implementations • 7 Oct 2021 • Dhruv Guliani, Lillian Zhou, Changwan Ryu, Tien-Ju Yang, Harry Zhang, Yonghui Xiao, Francoise Beaufays, Giovanni Motta

Federated learning can be used to train machine learning models on the edge on local data that never leave devices, providing privacy by default.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities

no code implementations • 14 Dec 2019 • Khe Chai Sim, Françoise Beaufays, Arnaud Benard, Dhruv Guliani, Andreas Kabel, Nikhil Khare, Tamar Lucassen, Petr Zadrazil, Harry Zhang, Leif Johnson, Giovanni Motta, Lillian Zhou

With speech input, if the user corrects only the names, the name recall rate improves to 64. 4%.

speech-recognition Speech Recognition