Improved training of end-to-end attention models for speech recognition

Conference object, Preprint English OPEN
Zeyer, Albert; Irie, Kazuki; Schlüter, Ralf; Ney, Hermann;

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h tasks. In particular, we report ... View more
Share - Bookmark