Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Volker Steinbiss"'
Publikováno v:
Speech Communication. 17:249-262
In this article, we describe an automatic system for train timetable information over the telephone that provides accurate connections between 1200 German cities. The caller can talk to it in unrestricted, natural, and fluent speech, very much like h
Autor:
H. Bartosik, Dieter Geller, W. Höllerbauer, Reinhold Haeb-Umbach, Bach-Hiep Tran, Hermann Dr Ney, Ute Essen, Xavier L. Aubert, Christian Dugast, H.-G. Meier, Martin Oerder, Reinhard Kneser, Volker Steinbiss
Publikováno v:
Speech Communication. 17:19-38
This paper gives an overview of the Philips research system for phoneme-based, large-vocabulary, continuousspeech recognition. The system has been successfully applied to various tasks in the German and (American) English languages, ranging from smal
Autor:
Ute Essen, Bach Hiep Tran, Hermann Ney, Reinhard Kneser, Stefan Besling, Hans Günter Meier, Martin Oerder, Dieter Geller, Xavier L. Aubert, Christian Dugast, Volker Steinbiss, Reinhold Haeb-Umbach
Publikováno v:
Philips Journal of Research. 49:317-352
This paper gives an overview of the Philips Research system for continuous-speech recognition. The recognition architecture is based on an integrated statistical approach. The system has been successfully applied to various tasks in American English
Publikováno v:
Philips Journal of Research. 49:399-418
This article describes the Philips automatic train timetable information system which enables the user to call up accurate information about train connections between 1200 German cities over the telephone. In contrast to most of the inquiry systems a
Publikováno v:
International Journal of Pattern Recognition and Artificial Intelligence. :33-70
This paper gives an overview of a research system for phoneme based, large vocabulary continuous speech recognition. The system to be described has been applied to the SPICOS task, the DARPA RM task and a 12000 word dictation task. Experimental resul
Publikováno v:
INTERSPEECH
The search for the optimal word sequence can be performed efficiently even in a speech recognizer with a very large vocabulary and complex models. This is achieved using pruning methods with empirically chosen parameters and the willingness to accept
Publikováno v:
INTERSPEECH
Scopus-Elsevier
Scopus-Elsevier
In this work, fundamental properties of Bayes decision rule us- ing general loss functions are derived analytically and are ver- ified experimentally for automatic speech recognition. It is shown that, for maximum posterior probabilities larger than
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51b03f2e65e5f87b7025df93767ee044
https://doi.org/10.5167/uzh-78697
https://doi.org/10.5167/uzh-78697
Publikováno v:
ICASSP (2)
We report on recent developments of the Philips large vocabulary speech recognition system and on our experiments with the Wall Street Journal (WSJ) corpus. A two-pass decoding has been devised that allows an easy integration of more complex language
Publikováno v:
Proceedings of 2nd IEEE Workshop on Interactive Voice Technology for Telecommunications Applications.
Introduces an automatic system for train timetable information over the telephone that provides accurate connections between 1200 German cities. The caller can talk to it in unrestricted, natural, and fluent speech, very much like he or she would com
Autor:
Andrea Zielinski, H. Bergmann, Andreas Noll, H. Nye, Volker Steinbiss, Herbert Piotrowski, A. Peaseler, Horst Tomaschewski, C. Dugast, Hans-Hermann Hamer
Publikováno v:
ICASSP
Some results obtained when the recognition vocabulary size of a phoneme-based speaker-dependent continuous-speech recognizer was increased from 1000 to 10000 words are reported. The potential search space increased from 46000 to 516000 states without