Almost none of the 2,000+ languages spoken in Africa have widely availab...
Personalization of speech models on mobile devices (on-device
personaliz...
State-of-the-art automatic speech recognition (ASR) systems are trained ...
Self-supervised training has shown promising gains in pretraining models...
Fast contextual adaptation has shown to be effective in improving Automa...
Self- and semi-supervised learning methods have been actively investigat...
Streaming end-to-end speech recognition models have been widely applied ...
We summarize the results of a host of efforts using giant automatic spee...
While current state-of-the-art Automatic Speech Recognition (ASR) system...
Training machine learning models on mobile devices has the potential of
...
We study the effectiveness of several techniques to personalize end-to-e...
Speaker-independent speech recognition systems trained with data from ma...
End-to-end (E2E) models, which directly predict output character sequenc...
Current state-of-the-art automatic speech recognition systems are traine...
We demonstrate a network visualization technique to analyze the recurren...
Sequence-to-sequence models provide a simple and elegant solution for
bu...