Edit Distance based RL for RNNT decoding

no code implementations • 31 May 2023 • Dongseong Hwang, Changwan Ryu, Khe Chai Sim

RNN-T is currently considered the industry standard in ASR due to its exceptional WERs in various benchmark tests and its ability to support seamless streaming and longform transcription.

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