Quaero Speech-to-Text and Text Translation Evaluation Systems

Sebastian Stüker (), Kevin Kilgour () and Jan Niehues ()
Additional contact information
Sebastian Stüker: Karlsruhe Institute of Technology, Research Group 3-01 ‘Multilingual Speech Recognition’
Kevin Kilgour: Karlsruhe Institute of Technology, Research Group 3-01 ‘Multilingual Speech Recognition’
Jan Niehues: Karlsruhe Institute of Technology, Interactive Systems Laboratories

A chapter in High Performance Computing in Science and Engineering '10, 2011, pp 529-542 from Springer

Abstract: Abstract Our laboratory has used the HP XC4000, the high performance computer of the federal state Baden-Wnrttemberg, in order to participate in the second Quaero evaluation for automatic speech recognition (ASR) and Machine Translation (MT). State-of-the-art automatic speech recognition and machine translation systems train use stochastic models which are trained on large amounts of training data using techniques from the field of machine learning. Using these techniques the systems search for the most likely speech recognition hypothesis, translation hypothesis respectively. The 2009 evaluation systems are further developments of the 2008 evaluation systems which incorporate more training data and updated models. The speech recognition and machine translation models were, at leas in part, trained on the XC4000 high performance cluster. The speech recognition evaluation itself was also mainly executed on the XC4000. In this paper we report on the newly developed system and how we utilized the XC4000 in order to train their models and to run the actual evaluation.

Keywords: Machine Translation; Automatic Speech Recognition; Acoustic Model; Statistical Machine Translation; Automatic Speech Recognition System (search for similar items in EconPapers)
Date: 2011
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-642-15748-6_38

Ordering information: This item can be ordered from
http://www.springer.com/9783642157486

DOI: 10.1007/978-3-642-15748-6_38

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().