Manses:
Turkish Voice Recognition and tr2en Translation Cloud

Santez xx.xx.xxxx

Definition

Manses is a software product that aims to design and develop a Turkish Speech Recognition (SR) and translation system by using Cloud Computing technology. It basically focuses on speech recognition.

History

Today, in many areas (call centers, mobile translation systems, automatic dictation systems etc.) the use of voice recognition systems is widespread. But because of some difficulties due to Turkish language of Turkish voice recognition systems, the number of projects carried out on this language is not enough. In addition, as it is known, Turkish is one of the most widely spoken languages in the world. However, Turkey is the country with the most number of people speaks Turkish. For many years, Turkey plays a major role in the dissemination and teaching of Turkish.

Turkish language is a mature and very formal so it encourages most people to learn Turkish and to come to Turkey to meet with the culture. In addition, speech-to-text studies on Turkish language are insufficient and on the other hand an increased demand to learn Turkish is the most important reasons behind this idea. With this product, by using the latest technologies of today it is aimed to establish a Turkish speech recognition system.

The goal is to teach Turkish to foreigners, especially tourists, who do not know Turkish via a portable devices like mobile phones and to make translation of the sentences said by a person who speaks Turkish in to English.

Capabilities

Thanks to this system, teaching and dissemination of Turkish language will be provided. Besides, it will be also provided that people who do not know Turkish (for example, tourists, foreign students studying in Turkey… etc.) can establish dialogue and relationship with the people who speak Turkish in an easy way. Although the focal point is the voice recognition, it is expected that the outcomes will be used by hearing-impaired people. A hearing-impaired person can capture conversations via mobile device and send to the voice analysis system automatically and each speaker can be shown as a separate font color of on the screen of his mobile device.