![]() International Workshop on Spoken Language Translation Proceedings of the 13th International Conference on Spoken Language Translation The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task All these approaches are combined using confusion network combination (CNC) to yield a competitive WER.", LSTM and count-based full word and hybrid backoff language modeling methods are used to model the morphological richness of the German language. An open vocabulary approach using subword units is also considered. State-of-the-art bidirectional long short-term memory (LSTM) and deep, multilingually boosted feed-forward neural network (FFNN) acoustic models are trained an narrow and broadband features. This evaluation campaign focuses on transcribing spontaneous speech from Skype recordings. Publisher = "International Workshop on Spoken Language Translation",Ībstract = "In this paper the RWTH large vocabulary continuous speech recognition (LVCSR) systems developed for the IWSLT-2016 evaluation campaign are described. Cite (Informal): The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task (Michel et al., IWSLT 2016) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: = "The erman Skype conversation recognition task",īooktitle = "Proceedings of the 13th International Conference on Spoken Language Translation", ![]() International Workshop on Spoken Language Translation. In Proceedings of the 13th International Conference on Spoken Language Translation, Seattle, Washington D.C. The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task. Ali Basha Shaik, Ralf Schlüter, and Hermann Ney. ![]() Anthology ID: 2016.iwslt-1.17 Volume: Proceedings of the 13th International Conference on Spoken Language Translation Month: December 8-9 Year: 2016 Address: Seattle, Washington D.C Venue: IWSLT SIG: SIGSLT Publisher: International Workshop on Spoken Language Translation Note: Pages: Language: URL: DOI: Bibkey: michel-etal-2016-rwth Cite (ACL): Wilfried Michel, Zoltán Tüske, M. All these approaches are combined using confusion network combination (CNC) to yield a competitive WER. Abstract In this paper the RWTH large vocabulary continuous speech recognition (LVCSR) systems developed for the IWSLT-2016 evaluation campaign are described.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |