activity
20182022
most citedSurprisal-Triggered Conditional Computation with Neural Networks

5 citations · 8 across the 4 of their papers we have counts for

collaborators
Showing eess.ASShow all

1 paper · 1 filter

eess.AS2019

Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models

Loren Lugosch, Brett Meyer, Derek Nowrouzezahrai +1

End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employi…