Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer
ASRU, Volume abs/1801.00841, 2017, Pages 193-199.
We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from transcribed acoustic data. We explore various model architectures and demonstrate how the model can b...More
Full Text (Upload PDF)
PPT (Upload PPT)