Self-Attentional Acoustic Models

Matthias Sperber, Jan Niehues, Graham Neubig, Sebastian Stüker, Alex Waibel
September 2018
PDF Code
Type
Conference paper
Publication
Annual Conference of the International Speech Communication Association (InterSpeech)

We used XNMT as our sequence-to-sequence toolkit. The code for the pure and interleaved models can be found under xnmt/specialized_encoders/self_attentional_am.py.