research
∙
10/28/2020
Non-Autoregressive Transformer ASR with CTC-Enhanced Decoder Input
Non-autoregressive (NAR) transformer models have achieved significantly ...
share
research
∙
10/23/2019
Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks
Self-attention network (SAN) can benefit significantly from the bi-direc...
research
∙
09/19/2019
A Random Gossip BMUF Process for Neural Language Modeling
LSTM language model is an essential component of industrial ASR systems....
research
∙
09/02/2019