User: Guest  Login

Title:

CTC-Segmentation of Large Corpora for German End-to-End Speech Recognition

Document type:
Konferenzbeitrag
Author(s):
Kürzinger, Ludwig; Winkelbauer, Dominik; Li, Lujun; Watzel, Tobias; Rigoll, Gerhard
Abstract:
Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters and model capacity. However, these models also require more training data to achieve comparable performance.
Editor:
Karpov, Alexey; Potapova, Rodmonga
Book / Congress title:
Speech and Computer
Publisher:
Springer International Publishing
Publisher address:
Cham
Year:
2020
Month:
Sep
Pages:
267--278
Print-ISBN:
978-3-030-60276-5
 BibTeX