Abstract not found

This paper describes Sehda’s S 2 MT (Syntactic Statistical Machine Translation) system submitted to the Korean-English track in the evaluation campaign of the IWSLT-05 workshop. The S 2 MT is a phrase-based statistical system trained on linguistically processed parallel data. 1.

This paper describes the design phases of the VoiceTRAN Communicator, which integrates speech recognition, machine translation, and text-to-speech synthesis using the Galaxy architecture. The aim of the work was to build a robust multimodal speech-to-speech translation system able to translate simple domain-specific sentences in the language pair Slovenian-English. The work represents a joint collaboration between several Slovenian research organizations that are active in human language technologies. Govorni komunikator VoiceTRAN Prispevek opisuje delo na razvoju govornega komunikatorja VoiceTRAN, ki združuje tehnologije prepoznavanja govora, strojnega prevajanja in sinteze govora. Podajamo opis arhitekture sistema ter posameznih sistemskih modulov. Nadalje opisujemo jezikovne