Projects per year
This paper describes the University of Edinburgh (UEDIN) English ASR system for the IWSLT 2013 Evaluation. Notable features of the system include deep neural network acoustic models in both tandem and hybrid configuration, cross-domain adaptation with multi-level adaptive networks, and the use of a recurrent neural network language model. Improvements to our system since the 2012 evaluation – which include the use of a significantly improved n-gram language model – result in a 19% relative WER reduction on the tst2012 set.
|Title of host publication||Proceedings of the 10th International Workshop on Spoken Language Translation (IWSLT 2013)|
|Number of pages||6|
|Publication status||Published - 2013|