Real-Time Joint Blind Speech Separation and Dereverberation in Presence of Overlapping Speakers

Blind source separation and speech dereverberation are two important and common issues in the field of audio processing especially in the context of real meetings. In this paper a real time framework implementing a sequential source separation and speech dereverberation algorithm based on blind channel identification is taken as starting point. The major drawback of this approach consists in the inability of the BCI stage of estimating the room impulse responses when two or more sources are concurrently active. To overcome the aforementioned disadvantage a speaker diarization system have been successfully inserted in the reference framework to pilot the BCI stage. In such a way the identification task can be accomplished by using directly the microphone mixture making the overall structure well suited for real-time applications. The proposed solution works in frequency domain and the NU-Tech software platform has been used on purpose for real-time simulations.