Abstract: Techniques for utilizing blind source separation as a front-end to an acoustic echo canceller are described herein. The techniques include removing a first portion of an acoustic echo from an audio signal using blind source separation and a reference signal. The techniques then further remove a second portion of the acoustic echo using an acoustic echo canceller and the reference signal. Further, output of the blind source separation may be used to improve double-talk detection.

Abstract: A wireless transmit/receive unit (WTRU) and a dynamic spectrum management (DSM) engine are described. The WTRU includes a transceiver, a radio frequency (RF) spectrum sensing unit and a processing unit. The transceiver transmits over a wireless link. The RF spectrum sensing unit measures information indicative of usage of a spectrum by other devices. The processing unit detects a change in performance of the wireless link, controls the transceiver to transmit a notification to a DSM engine indicating that the change in the performance of the wireless link was detected on a condition that the processing unit detects the change in performance of the wireless link, and receives a sensing task request for the WTRU to measure the information indicative of the usage of the spectrum by other devices based on the notification transmitted to the DSM engine indicating that the change in the performance of the wireless link was detected.