BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME;VALUE=TEXT:AI in Sound: Perception, Creative Generation, and Voice Synthesis
PRODID:-//Harvard events data//EN
BEGIN:VEVENT
UID:event_1577271_0
SUMMARY:AI in Sound: Perception, Creative Generation, and Voice Synthesis
DESCRIPTION:<p><span>This presentation will cover current research in sound and Artificial Intelligence,&nbsp;aimed at a general audience. Topics include auditory perception phenomena, AI-based tools for sound generation and mixing (e.g., latent space exploration, voice-to-instrument conversion), and voice synthesis techniques, including voice cloning and articulatory models. Live demonstrations will illustrate these concepts in an engaging and understandable way.</span></p><drupal-media data-entity-type="media" data-entity-uuid="fe43bd1d-01c4-48ab-89f6-3a5d2281d5b7">&nbsp;</drupal-media><p><strong>Speaker: </strong><span><strong>Mateo Cámara</strong> </span><em><span>(Assistant Professor, Universidad Politécnica de Madrid; Visiting Scientist at MIT)</span></em></p><p><strong>Sponsors: </strong>RCCHU; Universidad Politécnica de Madrid, MIT</p>
LOCATION:RCCHU Conference Room
STATUS:CONFIRMED
DTSTART:20250605T220000Z
DTEND:20250605T230000Z
END:VEVENT
END:VCALENDAR