[go: up one dir, main page]

×
This paper describes the University of Edinburgh (UEDIN) English ASR system for the IWSLT 2013 Evaluation. Notable features of the system include deep neural ...
Notable features of the system include deep neural network acoustic models in both tandem and hybrid configuration, cross-domain adaptation with multi-level ...
This paper describes the University of Edinburgh (UEDIN) English ASR system for the IWSLT 2013 Evaluation. Notable features of the system include deep ...
This paper describes the University of Edinburgh (UEDIN) English ASR system for the IWSLT 2013 Evaluation. Notable features of the system include deep ...
Request PDF | On Jan 1, 2013, Peter Bell and others published The UEDIN english ASR system for the IWSLT 2013 evaluation | Find, read and cite all the ...
Abstract. This study presents the NICT automatic speech recognition. (ASR) system submitted for the IWSLT 2013 ASR evaluation.
The UEDIN English ASR system for the IWSLT 2013 evaluation. view. electronic edition @ aclanthology.org (open access) · no references & citations available.
Results: ASR German. One outlier talk gives WER > 80%. Different training conditions among systems. Page 18. Progress in ASR English (best systems). 6. 7. 8. 9.
The UEDIN systems for IWSLT 2013 participated in all the MT tracks and the German-to-English and Englishto-French SLT tracks, and explored the use of ...
Dec 9, 2013 · In this paper we described our English speech-to-text system with which we participated in the IWSLT 2013 TED task evaluation on the ASR track.