Blind source separation for adaptive speech control

Moir, T
Alam, F
Harris, J
Item type
Conference Contribution
Degree name
Journal Title
Journal ISSN
Volume Title
AUT University

Crosstalk resistant adaptive noise cancellation (CTRANC) is a method of separat-ing convolutively mixed sources where little a priori information is known about the system. Possible areas of application for such an algorithm include speech sig-nal processing, in telecommunications, and in the biomedical industry. In this pa-per we propose a novel adaptation to the traditional CTRANC which increases computational efficiency when the number of sources fits the requirement of where and . Preliminary results also show a modest im-provement in separation performance when comparing it to the multiple-input multiple-output method proposed by Mei and Yin (2004).

The eighteenth annual Conference on Mechatronics and Machine Vision in Practice, Brisbane, Australia, 2011-12-06 - 2011-12-08
Publisher's version
Rights statement
NOTICE: this is the author’s version of a work that was accepted for presentation. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication.