Blind source separation for adaptive speech control
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).