Title OrienTel - Telephony Databases Across Northern Africa and the Middle East
Author(s) Dorota Iskra (1), Rainer Siemund (2), Jamal Borno (2), Asuncion Moreno (4), Ossama Emam (3), Khalid Choukri (5), Oren Gedge (6), Herbert Tropf (7), Albino Nogueiras (4), Imed Zitouni (8), Anastasios Tsopanoglou (9), Nikos Fakotakis (10)

(1) SPEX, (2) ScanSoft, (3) IBM, (4) UPC, (5) ELDA, (6) NSC, (7) Siemens, (8) Lucent, (9) Knowledge, (10) University of Patras

Session P9-SE
Abstract OrienTel is a project that over the past two-and-half years developed speech databases and phonetic standards across Northern Africa, the Middle East and the Arabian Gulf. The project is funded by the European Commission and is coordinated by ScanSoft (Germany and Belgium). Other partners are ELDA (France), IBM (Germany), NSC (Israel), Siemens (Germany), Lucent (UK), Knowledge, the University of Patras (both Greece) and UPC (Spain), plus SPEX (the Netherlands) as validation agency. Now that OrienTel has passed the finish line, the present paper gives an update of the design conventions, and an account of the project's achievements. The paper also illustrates some of the challenges that the consortium faced which are mostly related to the validation and the research subjects.
Keyword(s) Speech databases, ASR, telephony applications, Arabic
Language(s) Arabic, Hebrew, Turkish, Greek, English, French, German
Full Paper 552.pdf