Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Thomas Zenkel"'
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ab033d6b8fd3a69e0b849f3466812efa
https://doi.org/10.18653/v1/2021.findings-emnlp.299
https://doi.org/10.18653/v1/2021.findings-emnlp.299
Publikováno v:
ACL
Word alignment was once a core unsupervised learning task in natural language processing because of its essential role in training statistical machine translation (MT) models. Although unnecessary for training neural MT models, word alignment still p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a7b9730f32ee54622c36da2d90b9c5f3
http://arxiv.org/abs/2004.14675
http://arxiv.org/abs/2004.14675
Autor:
Ngoc-Quan Pham, Thomas Zenkel, Matthias Sperber, Alex Waibel, Jan Niehues, Sebastian Stüker, Markus Müller
Publikováno v:
Prague Bulletin of Mathematical Linguistics, Vol 111, Iss 1, Pp 125-135 (2018)
The Prague Bulletin of Mathematical Linguistics, 111 (1), 125–135
The Prague Bulletin of Mathematical Linguistics, 111 (1), 125–135
In this paper we introduce an open source toolkit for speech translation. While there already exists a wide variety of open source tools for the essential tasks of a speech translation system, our goal is to provide an easy to use recipe for the comp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a3dce9c96f2839ea8ab2f91eb9457dc
Publikováno v:
INTERSPEECH
This paper proposes a novel approach to create an unit set for CTC based speech recognition systems. By using Byte Pair Encoding we learn an unit set of an arbitrary size on a given training text. In contrast to using characters or words as units thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4998ff913e16ff40275487dd15e9bc14
http://arxiv.org/abs/1712.06855
http://arxiv.org/abs/1712.06855
Autor:
Jan Niehues, Thomas Zenkel, Sebastian Stüker, Alex Waibel, Matthias Sperber, Florian Metze, Ramon Sanabria
Publikováno v:
INTERSPEECH
Connectionist Temporal Classification has recently attracted a lot of interest as it offers an elegant approach to building acoustic models (AMs) for speech recognition. The CTC loss function maps an input sequence of observable feature vectors to an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::202334a8789e238cf8c7d4ae3a566916
https://doi.org/10.21437/interspeech.2017-1683
https://doi.org/10.21437/interspeech.2017-1683
Autor:
Prandi, Bianca
The present work explores computer-assisted simultaneous interpreting (CASI) from a primarily cognitive perspective. Despite concerns over the potentially negative impact of computer-assisted interpreting (CAI) tools on interpreters'cognitive load (C