Abstract | ||
---|---|---|
In this paper we present the ongoing work at RWTH Aachen University for building a speech- to-speech translation system within the TC- Star project. The corpus we work on consists of parliamentary speeches held in the European Plenary Sessions. To our knowledge, this is the first project that focuses on speech-to-speech translation applied to a real-life task. We de- scribe the statistical approach used in the de- velopment of our system and analyze its perfor- mance under different conditions: dealing with syntactically correct input, dealing with the ex- act transcription of speech and dealing with the (noisy) output of an automatic speech recog- nition system. Experimental results show that our system is able to perform adequately in each of these conditions. Paper type: (R) Research Keywords: Speech Translation, Methodologies for MT, Text and speech corpora for MT, MT evaluation results. |
Year | Venue | DocType |
---|---|---|
2005 | MTSummit | Conference |
Citations | PageRank | References |
6 | 1.78 | 3 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
David Vilar | 1 | 322 | 21.49 |
Evgeny Matusov | 2 | 466 | 38.01 |
Sasa Hasan | 3 | 245 | 17.35 |
Richard Zens | 4 | 2094 | 114.40 |
Hermann Ney | 5 | 14178 | 1506.93 |