End-to-end multilingual speech recognition involves using a single model...
Achieving super-human performance in recognizing human speech has been a...
Transformer models are powerful sequence-to-sequence architectures that ...
Recently sequence-to-sequence models have started to achieve state-of-th...
User studies have shown that reducing the latency of our simultaneous le...
Sequence-to-Sequence (S2S) models recently started to show state-of-the-...
In this work, we learn a shared encoding representation for a multi-task...
Acoustic-to-word (A2W) models that allow direct mapping from acoustic si...
We summarize the accomplishments of a multi-disciplinary workshop explor...