Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Christian Fügen"'
Autor:
A. Waibel, Christian Fügen
Publikováno v:
IEEE Signal Processing Magazine. 25:70-79
In this article we have reviewed state-of-the-art speech translation systems. We have discussed issues of performance as well as deployment, and we reviewed the history and technical underpinnings of this growing and challenging research area. The fi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c4400eb9b485f9e262019e7237db19c
https://doi.org/10.1109/msp.2008.918415
https://doi.org/10.1109/msp.2008.918415
Publikováno v:
Machine Translation. 21:209-252
With increasing globalization, communication across language and cultural boundaries is becoming an essential requirement of doing business, delivering education, and providing public services. Due to the considerable cost of human translation servic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6ce7df1d66e0b40ba18e333c54342e88
https://doi.org/10.1007/s10590-008-9047-0
https://doi.org/10.1007/s10590-008-9047-0
Autor:
Hartwig Holzapfel, Kai Nickel, Alex Waibel, Florian Kraft, Rainer Stiefelhagen, Michael Voit, Christian Fügen, Petra Gieselmann, Hazim Kemal Ekenel
Publikováno v:
IEEE Transactions on Robotics. 23:840-851
In this paper, we present our work in building technologies for natural multimodal human-robot interaction. We present our systems for spontaneous speech recognition, multimodal dialogue processing, and visual perception of a user, which includes loc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::35ed04faa2c03f2b080e486eed6e7cab
https://doi.org/10.1109/tro.2007.907484
https://doi.org/10.1109/tro.2007.907484
Publikováno v:
IEEE Potentials. 26:30-35
In this article, we introduced an iterative system for improving speech recognition in the context of human mediated translation scenarios. In contrast to related work conducted in this field, we included scenarios in which only spoken language repre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b3d93727e1206ac5ffc6a45d94c5709
https://doi.org/10.1109/mp.2007.361642
https://doi.org/10.1109/mp.2007.361642
Publikováno v:
INTERSPEECH
We propose a method for efficient off-line speech transcription through respeaking. Speech is segmented into smaller utterances using an initial automatic transcript. Respeaking is performed segment by segment, while confidence filtering helps save s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9cc44a44436b6ae5f26cb57c7a5a0295
https://doi.org/10.21437/interspeech.2013-294
https://doi.org/10.21437/interspeech.2013-294
Autor:
Christian Fügen, Djamel Mostefa, Khalid Choukri, Alex Waibel, Olivier Hamon, Muntsin Kolss, Victoria Arranz
Publikováno v:
EACL
This paper presents the end-to-end evaluation of an automatic simultaneous translation system, built with state-of-the-art components. It shows whether, and for which situations, such a system might be advantageous when compared to a human interprete
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b3a11d4b5e2a159d616d397a52e1be45
https://doi.org/10.3115/1609067.1609105
https://doi.org/10.3115/1609067.1609105
Publikováno v:
INTERSPEECH
Scopus-Elsevier
Scopus-Elsevier
The project Technology and Corpora for Speech to Speech Translation (TC-STAR) aims at making a break-through in speech-to-speech translation research, significantly reducing the gap between the performance of machines and humans at this task. Technol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e099951191b0cd0d54be439ccaea5423
https://doi.org/10.21437/interspeech.2007-588
https://doi.org/10.21437/interspeech.2007-588
Autor:
Muntsin Kolss, Christian Fügen
Publikováno v:
INTERSPEECH
Speech translation systems commonly couple automatic speech recognition (ASR) and machine translation (MT) components. Hereby the automatic segmentation of the ASR output for the subsequent MT is critical for the overall performance. In simultaneous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a4df2c7cb8b92804c9a69e4d0b849b07
https://doi.org/10.21437/interspeech.2007-653
https://doi.org/10.21437/interspeech.2007-653
Publikováno v:
ICASSP (4)
In this paper we describe our work in coupling automatic speech recognition (ASR) and machine translation (MT) in a speech translation enhanced automatic speech recognition (STE-ASR) framework for transcribing and translating European parliament spee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::916c0437d5a3c9ea2d3d7e697d40a04f
https://doi.org/10.1109/icassp.2007.367314
https://doi.org/10.1109/icassp.2007.367314
Publikováno v:
ICASSP (1)
In this paper, we describe our efforts to develop acoustic models suitable for distant microphone automatic speech recognition. Our goal is to investigate how the performance of a system trained on a combination of close-talking and distant microphon
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b35c9ef0e39e43978929a115cf1c5283
https://doi.org/10.1109/icassp.2005.1415282
https://doi.org/10.1109/icassp.2005.1415282