High Throughput Efficient Design of Blind Source Separation
A multi stage approach to speech enhancement methods improves the quality of separation over standard techniques such as spectral subtraction and beamforming. Two algorithms are implemented for convolutive mixtures in two of the important stages of a speech enhancement system, the source separation stage and the background denoising stage. The CBSS separation network derived from the information maximization (Infomax) approach is adopted. The proposed CBSS chip design consists mainly of Infomax filtering modules and scaling factor computation modules. In an Infomax filtering module, input samples are filtered by an Infomax filter with the weights updated by Infomax-driven stochastic learning rules. For source separation, a blind source separation method based on second order statistics has been adopted whereas for background denoising, a method based on minimum statistics of subband power, has been used. An efficient real time algorithm for convolutive blind source separation of broad band signals has been realized, by exploiting the second order statistics and non-stationarity of the signals. Baugh-wooley multiplier is used to enhance the project using some advanced setup.
Author's Name: Moses Varaprasad Gummadi, Girish Pechetti and Krishnamadhav Dunnala