most citedSemi-Supervised Model Training for Unbounded Conversational Speech Recognition

13 citations · 13 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CL2017★ 13 cited

Semi-Supervised Model Training for Unbounded Conversational Speech Recognition

Shane Walker, Morten Pedersen, Iroro Orife +1

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collecti…