Here I am presenting an idea, that can bring revolution in the Human-human Interaction. The Multilingual Project will help to overcome the language barrier by developing a device or environment that can perform personalised speech to speech translation, such that the user’s spoken input in one language will be transformed to desired language while continuing to sound like user’s voice as output response.
The personalised system will help in cross lingual communication therefore no need to learn a new language while communicating with a person whose native language is not the language which is yours one. This speech to speech translation is little explored area which need a great effort for research and development.
In this project, the main task is to explore the use of speaker adaptation across languages so that, by performing automatic speech recognition, can learn the characteristics of an individual speaker, and then use those characteristics when producing output speech in another language. Other than this, task includes building a system that can make the computer to learn.
Currently, working on voice recognition. Voice recognition is the important step which will make the base for the project. A model i.e. Markov model that can be used as voice synthesis and recognition will be great for the project.
If you find the project interesting and like to work for the same, feel free to contact. We need persons, ready for research in Computer-Human interaction and voice manipulation.