BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Acoustic Fingerprinting and Music Identification - Justin Hou\, Ch
 urchill College
DTSTART:20200304T193000Z
DTEND:20200304T200000Z
UID:TALK140680@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:With so much user-generated content produced every day\, the t
 ask of finding unauthorised copyrighted content becomes increasingly diffi
 cult. This talk will first introduce some common methods used to uniquely 
 identify audio content\, before showing a more sophisticated technique pur
 portedly used by Youtube's automated Content ID technology. We will explor
 e how ideas from natural language processing and speech recognition can be
  used to produce a system based on finite state transducers to detect copy
 righted audio segments.
LOCATION:Wolfson Hall\, Churchill College
END:VEVENT
END:VCALENDAR