Generalizing RNN-Transducer to Out-Domain Audio via Sparse Self-Attention Layers.

Juntae Kim Jeehye Lee Yoonhan Lee

Published in: CoRR (2021)

Keyphrases

nearest neighbor
recurrent neural networks
multimedia
domain specific
domain independent
knowledge base
high dimensional
sparse data
cross domain
domain experts
speaker identification
focus of attention
visual attention
visual information
real time
signal processing
search engine