BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20191103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20200915T150000
DTEND;TZID=America/New_York:20200915T160000
DTSTAMP:20260407T132125
CREATED:20200911T144535Z
LAST-MODIFIED:20200911T144535Z
UID:3349-1600182000-1600185600@seasevents.nmsdev7.com
SUMMARY:CIS Seminar: "Recovering\, manipulating and enhancing recorded speech (1905-2020)"
DESCRIPTION:This talk will survey several recent projects dealing with recorded speech. The first explores \nan optical process for recovering sound recorded onto postcards using a forgotten technology \nfrom more than a century ago. This involves scanning the postcard at multiple orientations using \na flatbed scanner\, and then reconstructing the fine scale surface texture of the card (where the \naudio is encoded) using photometric stereo\, a technique from computer vision. We will then \ndiscuss more modern applications as well\, including a text-based interface for editing recorded \naudio narration that is capable of synthesizing new words matching the voice of the narrator. \nFinally\, given that real-world audio recordings are often degraded by factors such as noise\, \nreverberation\, and equalization distortion\, we will also introduce a deep learning method to \ntransform recorded speech to sound as though it had been recorded in a studio.
URL:https://seasevents.nmsdev7.com/event/cis-seminar-recovering-manipulating-and-enhancing-recorded-speech-1905-2020/
LOCATION:Zoom – Email CIS for link\, cherylh@cis.upenn.edu
CATEGORIES:Distinguished Lecture
END:VEVENT
END:VCALENDAR