User: Guest  Login
Document type:
Konferenzbeitrag 
Author(s):
Watzel, Tobias; Kürzinger, Ludwig; Li, Lujun; Rigoll, Gerhard 
Title:
Synchronized Forward-Backward Transformer for End-to-End Speech Recognition 
Abstract:
Recently, various approaches utilize transformer networks, which apply a new concept of self-attention, in end-to-end speech recognition. These approaches mainly focus on the self-attention mechanism to improve the performance of transformer models. In our work, we demonstrate the benefit of adding a second transformer network during the training phase, which is optimized on time-reversed target labels. This new transformer receives a future context, which is usually not available for standard t...    »
 
Editor:
Karpov, Alexey; Potapova, Rodmonga 
Book / Congress title:
Speech and Computer 
Publisher:
Springer International Publishing 
Publisher address:
Cham 
Year:
2020 
Month:
Sep 
Pages:
646--656 
Print-ISBN:
978-3-030-60276-5