A Comparison of Transformer and LSTM Encoder Decoder Models for ASR

We present competitive results using a Transformer encoder-decoder-attention model for end-to-end speech recognition needing less training time compared to a similarly performing LSTM model. We observe that the Transformer training is in general more stable compared to the LSTM, although it also see...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) S. 8 - 15
Hauptverfasser:	Zeyer, Albert, Bahar, Parnia, Irie, Kazuki, Schluter, Ralf, Ney, Hermann
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.12.2019
Schlagworte:	attention Convergence Convolutional codes Data models Decoding Encoding end-to-end ASR Hidden Markov models LSTM Training Transformer
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!