This technique aims at obtaining an estimation of the sources that produce some measurable field, given a set of distributed measurements of the field itself. Specifically applied to audio sources, the field is a sound field measured through several microphones located remotely in some specific locations.
The problem is known as the “cocktail party problem,” as in a party there are usually a lot of sound sources and yet human beings are able to focus their attention on a specific source, like the person with whom one is having a conversation. This problem is very difficult to solve, since the sound field is generally affected by the characteristics of the room (the reverberation phenomenon), and the sources and sensors may be arbitrarily located and moving in the space. We have developed several techniques for blind source separation of audio sources and we have filed, patent applications for two of them in Japan.
There are multiple applications for these techniques, for example in teleconference systems, human-machine interface devices, remote control of home appliances, among others.
Contact: Leandro Di Persia