In this paper, we propose an effective method for blind speech separation of convolutive mixtures in the frequency domain. The main difficulty in a frequency approach is the permutation problem. In the proposed method, we use two previous approaches to solve permutation ambiguity in the two-channel model: direction of arrival (DOA) estimation approach and assignment problem (AP) approach. We discuss the advantages and disadvantages of the two approaches, and integrate them to use the both advantages. Computer simulation experiments with speech data are presented to illustrate the proposed method.
In this paper, we propose a method for blind speech separation of convolutive mixtures in the frequency domain. The main difficulty in a frequency approach is the so-called permutation problem. In the proposed method, we use the Assignment Problem (AP) approach to solve permuation ambiguity in the frequency domain. In our work, we apply three different algorithms including Hugarian, Jonker-Volgenant and Bertsekas’s Auction to solve the AP to find the optimal solution. Computer simulation experiments are presented to illustrate the proposed method.
This paper proposes a new method to address the problem of blind speech separation in convolutive mixtures in the time domain. The main idea is extract the innovation processes of speech sources by nonGaussianity maximization and then artificially color them by re-coloration filters. Some simulation experiments of the 2x2 case are presented to illustrate the proposed approach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.