The challenge of low-latency speech translation has recently draw signif...
Many existing speech translation benchmarks focus on native-English spee...
Multilingual speech recognition with neural networks is often implemente...
Multilingual speech recognition with supervised learning has achieved gr...
End-to-end multilingual speech recognition involves using a single model...
In this work we look into adding a new language to a multilingual NMT sy...
Transformer models are powerful sequence-to-sequence architectures that ...
Recently sequence-to-sequence models have started to achieve state-of-th...
Recently, significant improvements have been achieved in various natural...
An important concern in training multilingual neural machine translation...
Lattices are an efficient and effective method to encode ambiguity of
up...
Recently, end-to-end sequence-to-sequence models for speech recognition ...
Neural machine translation (NMT) has significantly improved the quality ...
Through the development of neural machine translation, the quality of ma...