Gaussian Model based Source Separation Implementation for Speech Separation
Ramjan Khatik1, S M Shashidhar2
1Ramjan Khatik, Ph.D Research Scholar, Visvesvaraya Technological University, Belgaum (Karnataka), India.
2Dr. S M Shashidhar, Principal, PDIT, Hospete.
Manuscript received on 20 November 2019 | Revised Manuscript received on 04 December 2019 | Manuscript Published on 10 December 2019 | PP: 393-396 | Volume-8 Issue-3S2 October 2019 | Retrieval Number: C10751083S219/2019©BEIESP | DOI: 10.35940/ijrte.C1075.1083S219
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This Paper is an attempt to develop the Independent Component Analysis (ICA) based source separation implementation on the speech signals. The blind source separation technique which work on the basis of the Gaussian process is developed and the performance is analyzed. Blind source separation is the process in which the source separation of the main signal and the noise is separated without any reference available. Matlab based implementation is carried out and the results are obtained. The results thus obtained are satisfactory.
Keywords: Blind Source Separation, Gaussian Model, Independent Component Analysis.
Scope of the Article: Component-Based Software Engineering