BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Chicago BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250928T083142Z UID:08731FF4-7D52-4EAC-B625-58B314E44C85 DTSTART;TZID=America/Chicago:20250924T100000 DTEND;TZID=America/Chicago:20250924T110000 DESCRIPTION:Title: Approaching General to Super Computer Audition\n\nFrom u nderstanding human speech and music to perceiving complex soundscapes\, th e field of computer audition is rapidly evolving toward a new frontier: sy stems that approach general listening intelligence and even exceed human a uditory capabilities. In this Distinguished IEEE SPS lecture\, we will tra ce the journey from today’s specialized audio recognition systems to tom orrow’s general-purpose and “super” computer audition—AI that can listen\, interpret\, and act across a vast range of acoustic environments. Building on decades of research in speech and audio processing\, affectiv e and paralinguistic computing\, and multimodal machine learning\, the tal k will showcase how advances in large-scale models\, self-supervised learn ing\, and cross-modal integration are reshaping what machines can hear and understand breaking audio down into its sources and richly attributing st ates and traits to these. Applications range from voice biomarkers in heal thcare and emotion-aware assistants to advanced hearing technologies—are as directly relevant to industry leaders such as Starkey. Yet\, the move t oward general and superhuman audition also raises critical questions. How do we ensure robustness\, interpretability\, and fairness in AI that liste ns to—and learns from—our most personal signals? How can we balance te chnical progress with ethical responsibility and user trust? And what are the implications of AI systems that may one day surpass human hearing in s cope and precision? This talk will offer a forward-looking perspective on the science and impact of tomorrow’s computer audition\, highlighting bo th the opportunities and challenges of designing AI that truly listens.\n\ nCo-sponsored by: Starkey\n\nSpeaker(s): Prof. Björn W. Schuller\n\nAgend a: \n9:30 – 10:00 a.m. Meet and Greet\n\n10:00 – 10:05 a.m. Welcome Re marks by Dr. Wenyu Jin\n\n10:05 – 11:00 a.m. Approaching General to Supe r Computer Audition by Prof. Björn W. Schuller\n\nRoom: Hopkins Room\, Bl dg: WFA Education Center\, 6425 Flying Cloud Dr\, Eden Prairie\, Minnesota \, United States\, 55344\, Virtual: https://events.vtools.ieee.org/m/50034 5 LOCATION:Room: Hopkins Room\, Bldg: WFA Education Center\, 6425 Flying Clou d Dr\, Eden Prairie\, Minnesota\, United States\, 55344\, Virtual: https:/ /events.vtools.ieee.org/m/500345 ORGANIZER:wenyu.jin@ieee.org SEQUENCE:57 SUMMARY:IEEE SPS DISTINGUISHED LECTURER PROGRAM TWIN CITIES SP/COM CHAPTER SEMINAR 09/24/2025 URL;VALUE=URI:https://events.vtools.ieee.org/m/500345 X-ALT-DESC:Description: <br /><p>Title: <span style="text-decoration: under line\;"><strong>Approaching General to Super Computer Audition</strong></s pan></p>\n<p class="MsoNormal">From understanding human speech and music t o perceiving complex soundscapes\, the field of computer audition is rapid ly evolving toward a new frontier: systems that approach general listening intelligence and even exceed human auditory capabilities. In this Disting uished IEEE SPS lecture\, we will trace the journey from today&rsquo\;s sp ecialized audio recognition systems to tomorrow&rsquo\;s general-purpose a nd &ldquo\;super&rdquo\; computer audition&mdash\;AI that can listen\, int erpret\, and act across a vast range of acoustic environments. Building on decades of research in speech and audio processing\, affective and parali nguistic computing\, and multimodal machine learning\, the talk will showc ase how advances in large-scale models\, self-supervised learning\, and cr oss-modal integration are reshaping what machines can hear and understand breaking audio down into its sources and richly attributing states and tra its to these. Applications range from voice biomarkers in healthcare and e motion-aware assistants to advanced hearing technologies&mdash\;areas dire ctly relevant to industry leaders such as Starkey. Yet\, the move toward g eneral and superhuman audition also raises critical questions. How do we e nsure robustness\, interpretability\, and fairness in AI that listens to&m dash\;and learns from&mdash\;our most personal signals? How can we balance technical progress with ethical responsibility and user trust? And what a re the implications of AI systems that may one day surpass human hearing i n scope and precision? This talk will offer a forward-looking perspective on the science and impact of tomorrow&rsquo\;s computer audition\, highlig hting both the opportunities and challenges of designing AI that truly lis tens.</p><br /><br />Agenda: <br /><p>9:30 &ndash\; 10:00 a.m.&nbsp\; &nbs p\; &nbsp\; &nbsp\;<strong>Meet and Greet&nbsp\;</strong></p>\n<p>10:00 &n dash\; 10:05 a.m.&nbsp\; &nbsp\; &nbsp\;<strong>Welcome Remarks</strong>&n bsp\;by&nbsp\;<em>Dr. Wenyu Jin</em></p>\n<p>10:05 &ndash\; 11:00 a.m. &nb sp\; &nbsp\; &nbsp\;<strong>Approaching General to Super Computer Audition </strong> by Prof. Bj&ouml\;rn W. Schuller</p> END:VEVENT END:VCALENDAR