Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Parnia Bahar"'
Publikováno v:
SLT
2021 IEEE Spoken Language Technology Workshop (SLT)
8 Seiten (2020). doi:10.18154/RWTH-2021-02590
2021 IEEE Spoken Language Technology Workshop (SLT)
8 Seiten (2020). doi:10.18154/RWTH-2021-02590
A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers from error
Publikováno v:
IWSLT
Scopus-Elsevier
Scopus-Elsevier
This paper describes the offline and simultaneous speech translation systems developed at AppTek for IWSLT 2021. Our offline ST submission includes the direct end-to-end system and the so-called posterior tight integrated model, which is akin to the
Publikováno v:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
ACL
ACL
Sparse models require less memory for storage and enable a faster inference by reducing the necessary number of FLOPs. This is relevant both for time-critical and on-device computations using neural networks. The stabilized lottery ticket hypothesis
Autor:
Tamer Alkhouli, Andreas Guta, Parnia Bahar, Christian Herold, Evgeny Matusov, Pavel Golik, Patrick Wilken
Publikováno v:
IWSLT
AppTek and RWTH Aachen University team together to participate in the offline and simultaneous speech translation tracks of IWSLT 2020. For the offline task, we create both cascaded and end-to-end speech translation systems, paying attention to caref
Publikováno v:
ASRU
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
Recent advances in deep learning show that end-to-end speech to text translation model is a promising approach to direct the speech translation field. In this work, we provide an overview of different end-to-end architectures, as well as the usage of
Publikováno v:
The Prague bulletin of mathematical linguistics 108(1), 13-25 (2017). doi:10.1515/pralin-2017-0005
20. Annual Conference of the European Association for Machine Translation (EAMT), EAMT 2017, Prague, Czech Republic, 2017-05-29-2017-05-31
Prague Bulletin of Mathematical Linguistics, Vol 108, Iss 1, Pp 13-25 (2017)
The Prague Bulletin of Mathematical Linguistics
20. Annual Conference of the European Association for Machine Translation (EAMT), EAMT 2017, Prague, Czech Republic, 2017-05-29-2017-05-31
Prague Bulletin of Mathematical Linguistics, Vol 108, Iss 1, Pp 13-25 (2017)
The Prague Bulletin of Mathematical Linguistics
20th Annual Conference of the European Association for Machine Translation (EAMT), EAMT 2017, Prague, Czech Republic, 29 May 2017 - 31 May 2017; The Prague bulletin of mathematical linguistics 108(1), 13-25 (2017). doi:10.1515/pralin-2017-0005
P
P
Autor:
Jan Rosendahl, Parnia Bahar, Miguel Graça, Hermann Ney, Yunsu Kim, Christian Herold, Weiyue Wang, Yingbo Gao
Publikováno v:
WMT (2)
This paper describes the neural machine translation systems developed at the RWTH Aachen University for the German-English, Chinese-English and Kazakh-English news translation tasks of the Fourth Conference on Machine Translation (WMT19). For all tas
Publikováno v:
Piscataway, NJ : IEEE 5671-5675 (2019). doi:10.1109/ICASSP.2019.8682155
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing : proceedings : May 12-17, 2019, Brighton Conference Centre, Brighton, United Kingdom / sponsored by: the Institute of Electrical and Electronics Engineers Signal Processing Society
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing : proceedings : May 12-17, 2019, Brighton Conference Centre, Brighton, United Kingdom / sponsored by: the Institute of Electrical and Electronics Engineers Signal Processing Society2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, Brighton, UK, 2019-05-12-2019-05-17
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing : proceedings : May 12-17, 2019, Brighton Conference Centre, Brighton, United Kingdom / sponsored by: the Institute of Electrical and Electronics Engineers Signal Processing Society
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing : proceedings : May 12-17, 2019, Brighton Conference Centre, Brighton, United Kingdom / sponsored by: the Institute of Electrical and Electronics Engineers Signal Processing Society2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, Brighton, UK, 2019-05-12-2019-05-17
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP
Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are related by an attention approach, thereby replacing more explicit alig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47b54ac9247a082ad21efbd41ebdf653
https://publications.rwth-aachen.de/record/755714
https://publications.rwth-aachen.de/record/755714
Publikováno v:
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
ASRU
ASRU
We present competitive results using a Transformer encoder-decoder-attention model for end-to-end speech recognition needing less training time compared to a similarly performing LSTM model. We observe that the Transformer training is in general more
Publikováno v:
Stroudsburg, PA : Association for Computational Linguistics (ACL) 496-503 (2018). doi:10.18653/v1/W18-6426
Third Conference on Machine Translation-proceedings of the conference : October 31-November 1, 2018, Brussels, Belgium : WMT 2018
Third Conference on Machine Translation-proceedings of the conference : October 31-November 1, 2018, Brussels, Belgium : WMT 20183. Conference on Machine Translation, WMT, Brussels, Belgium, 2018-10-31-2018-11-01
EMNLP 2018 Third Conference on Machine Translation (WMT 2018)
WMT (shared task)
Third Conference on Machine Translation-proceedings of the conference : October 31-November 1, 2018, Brussels, Belgium : WMT 2018
Third Conference on Machine Translation-proceedings of the conference : October 31-November 1, 2018, Brussels, Belgium : WMT 20183. Conference on Machine Translation, WMT, Brussels, Belgium, 2018-10-31-2018-11-01
EMNLP 2018 Third Conference on Machine Translation (WMT 2018)
WMT (shared task)
Third Conference on Machine Translation - proceedings of the conference : October 31-November 1, 2018, Brussels, Belgium : WMT 2018 Third Conference on Machine Translation, WMT, Brussels, Belgium, 31 Oct 2018 - 1 Nov 2018; Stroudsburg, PA : Associati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::99c452f35715a4f9a8668b065b7fa327
https://publications.rwth-aachen.de/record/755705
https://publications.rwth-aachen.de/record/755705