paper-with-me

홈 › Papers

The RWTH Aachen LVCSR system for IWSLT-2016 German Skype conversation recognition task

2016-12-01 · IWSLT 2016 12 · Wilfried Michel, Zoltán Tüske, M. Ali Basha Shaik, Ralf Schlüter, Hermann Ney

In this paper the RWTH large vocabulary continuous speech recognition (LVCSR) systems developed for the IWSLT-2016 evaluation campaign are described. This evaluation campaign focuses on transcribing spontaneous speech from Skype recordings. 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. An open vocabulary approach using subword units is also considered. LSTM and count-based full word and hybrid backoff language modeling methods are used to model the morphological richness of the German language. All these approaches are combined using confusion network combination (CNC) to yield a competitive WER.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

The RWTH Aachen Machine Translation Systems for IWSLT 2017

2017-12-01 · IWSLT 2017 12 · Parnia Bahar, Jan Rosendahl, Nick Rossenbach, Hermann Ney

This work describes the Neural Machine Translation (NMT) system of the RWTH Aachen University developed for the English$German tracks of the evaluation campaign of the International Workshop on Spoken Language Translatio…

Domain AdaptationMachine TranslationNMTTranslation

The RWTH Aachen Machine Translation System for IWSLT 2016

2016-12-01 · IWSLT 2016 12 · Jan-Thorsten Peter, Andreas Guta, Nick Rossenbach, Miguel Graça 외

This work describes the statistical machine translation (SMT) systems of RWTH Aachen University developed for the evaluation campaign of International Workshop on Spoken Language Translation (IWSLT) 2016. We have partici…

DecoderMachine TranslationRerankingTranslation

The RWTH Aachen University English-German and German-English Machine Translation System for WMT 2017

2017-09-01 · WS 2017 9 · Jan-Thorsten Peter, Andreas Guta, Tamer Alkhouli, Parnia Bahar 외
Machine TranslationTranslation

The RWTH Aachen German-English Machine Translation System for WMT 2015

2015-09-01 · WS 2015 9 · Jan-Thorsten Peter, Farzad Toutounchi, Joern Wuebker, Hermann Ney
Language ModellingMachine TranslationTranslation

The RWTH Aachen German-English Machine Translation System for WMT 2014

2014-06-01 · WS 2014 6 · Stephan Peitz, Joern Wuebker, Markus Freitag, Hermann Ney
Machine TranslationTranslation