BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Canada/Eastern
BEGIN:DAYLIGHT
DTSTART:20190310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20191103T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20191223T173629Z
UID:F0107881-EA34-4C8E-B134-D8CFD5F4AC22
DTSTART;TZID=Canada/Eastern:20190826T160000
DTEND;TZID=Canada/Eastern:20190826T170000
DESCRIPTION:A Joint Attention Decoding and Adaptive Beamforming Optimizatio
 n Approach for the Cocktail Party Problem\n\nThe cocktail party problem ha
 s remained to be one of the most difficult problems for hearing devices ev
 en after decades of extensive research. One of the key challenges is to de
 termine the desired talker in a cocktail party. Recently\, researchers hav
 e successfully demonstrated the decoding of auditory attention using EEG\,
  MEG or EMG. In addition\, several research studies have attempted to inco
 rporate the decoded auditory attention information into speech enhancement
  solutions. However\, the existing solutions are less optimal in the sense
  that auditory attention decoding is often separate from speech enhancemen
 t. In this talk\, we propose a joint auditory attention decoding and multi
 -channel speech enhancement approach. The proposed approach eliminates the
  need of extracting speech envelope of each talk\, which is a difficult pr
 oblem in practice by itself. Furthermore\, the proposed solution is optima
 l in the sense that the attended talker’s speech is optimized using both
  microphone inputs and EEG inputs in a united framework. We present prelim
 inary results to demonstrate the effectiveness of the algorithm and discus
 s future research directions.\n\nSpeaker(s): Dr. Tao Zhang\, \n\nRoom: A11
 3\, Bldg: ITB\, 1280 Main Street West\, Hamilton\, Ontario\, Canada\, L8S 
 4K1
LOCATION:Room: A113\, Bldg: ITB\, 1280 Main Street West\, Hamilton\, Ontari
 o\, Canada\, L8S 4K1
ORGANIZER:junchen@ece.mcmaster.ca
SEQUENCE:6
SUMMARY:Optimization Approach for the Cocktail Party Problem
URL;VALUE=URI:https://events.vtools.ieee.org/m/203044
X-ALT-DESC:Description: <br /><p><span style="color: #ff6600\; font-size: 1
 8pt\;"><strong>A Joint Attention Decoding and Adaptive Beamforming Optimiz
 ation Approach for the Cocktail Party Problem </strong></span></p>\n<p>&nb
 sp\;</p>\n<p>The cocktail party problem has remained to be one of the most
  difficult problems for hearing devices even after decades of extensive re
 search. One of the key challenges is to determine the desired talker in a 
 cocktail party. Recently\, researchers have successfully demonstrated the 
 decoding of auditory attention using EEG\, MEG or EMG. In addition\, sever
 al research studies have attempted to incorporate the decoded auditory att
 ention information into speech enhancement solutions. However\, the existi
 ng solutions are less optimal in the sense that auditory attention decodin
 g is often separate from speech enhancement. In this talk\, we propose a j
 oint auditory attention decoding and multi-channel speech enhancement appr
 oach. The proposed approach eliminates the need of extracting speech envel
 ope of each talk\, which is a difficult problem in practice by itself. Fur
 thermore\, the proposed solution is optimal in the sense that the attended
  talker&rsquo\;s speech is optimized using both microphone inputs and EEG 
 inputs in a united framework. We present preliminary results to demonstrat
 e the effectiveness of the algorithm and discuss future research direction
 s.</p>
END:VEVENT
END:VCALENDAR