Applying Blind Source Separation and Deconvolution to Real-World Acoustic Environments
A subset of signal processing researchers strive to enable digital systems to isolate individual sound sources from an environment containing several. As part of this effort, we experiment with an approach known as "blind source separation and deconvolution" (BSSD). The main contribution of this paper is the application of current BSSD algorithms to unconstrained real-world applications.
This paper costs $20 for non-members, $5 for AES members and is free for E-Library subscribers.