The OrienTel Project began in in 2001 with the purpose of creatiing multilingual communication services for The Middle East, The Mediterranian and Norhern Africa. A region which varies greatly in terms of accents, language and dialect. The idea was to help create systems that would allow speakers of different languages and dialects to communicate with one another using technology. The project was completed in late 2003, and through summary of their project details can be found at their WEBSITE, and the results of the project along with the validation report were posted HERE at the site for the European Language Resources Association.

At this site, we chart the progress that has been made since The Orientel Project was completed. There have been many advancments in the intervening years, and we try to keep up with these advancements and what these new technologies mean for the people of the Mediterranean and the Middle East, From Morocco in the West to the Gulf states in the east, including Turkey and Cyprus, the variety of languages and their many dialects present many problems for the development of speech recognition technology. In the Arabic-speaking world for example, the majority of the population speaks a colloquial form of Arabic that is only remotely related to the Standard used on formal occasions and in written texts. In addition, most countries have inherited from their colonial past either French or English, which still carry considerable weight in everyday interaction. All three languages have their place in daily life. This presents problems for computers who have trouble understanding and processing so many forms of the same language.


That is why we present this website to keep the people of the Mediterranean and the Middle East infromed and up to date on all the latest in the world of Speech Recognition Technologies. We provide News on matters relevent to advances in the field as well as how the new material is being implamented. We also display scientifc publications on the importance and the advancements that are being made. Lastly, we provide links to other sites similar to ours so that you might expanded your knowledge even further.

As way of a brief introduction into the complex world of Multilingul processing, we present to you these brief discriptions of some of the termenology that is used. Multilinguality need not be textual only, but will take on spoken form, when information services are to extend beyond national boundaries, or across language groups. We believe that speech recognition will play a hufe role in the future of translation and interpreting. Database access by speech will need to handle multiple languages to service customers from different language groups within a country or travelers from abroad. Nowehre is that fact more obvious than in The Mediterranean and the Middle East.

Speech recognition (also known as automatic speech recognition or computer speech recognition) converts spoken words to text. The term "voice recognition" is sometimes used to refer to speech recognition where the recognition system is trained to a particular speaker - as is the case for most desktop recognition software, hence there is an element of speaker recognition, which attempts to identify the person speaking, to better recognize what is being said. Speech recognition is a broad term which means it can recognize almost anybody's speech - such as a call-centre system designed to recognize many voices. Voice recognition is a system trained to a particular user, where it recognizes their speech based on their unique vocal sound.