BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250309T164502Z
UID:9544E019-BAE7-4C9F-8860-CC7400DAC433
DTSTART;TZID=America/Los_Angeles:20250307T183000
DTEND;TZID=America/Los_Angeles:20250307T210000
DESCRIPTION:Abstract\n\nThe field of speech processing is currently dominat
 ed by end-to-end (E2E) models\, which utilize a single model to optimize d
 irectly towards the final objective function rather than optimizing multip
 le sub-models separately. This trend is particularly notable in automatic 
 speech recognition (ASR). In this talk\, we will provide an overview of E2
 E ASR models and discuss recent advancements from an industry perspective.
  Subsequently\, we will examine the trend of E2E modeling beyond ASR\, wit
 h applications such as multi-speaker ASR and simultaneous speech translati
 on\, where ASR traditionally serves as only one of several components. Thi
 s trend ultimately unlocks multimodal intelligence by integrating speech c
 apabilities into large language models (LLM). We will highlight the most r
 ecent developments in this area\, which present unprecedented opportunitie
 s for the field.\n\nSpeaker(s): Jinyu Li\, \n\nAgenda: \n6:30 – 7:00 Che
 ck-in\, networking\, food\, and drink\n\n7:00 – 8:00 PM – Presentation
  by Dr. Jinyu Li\n\n8:00 – 8:30 PM – Q & A\n\nRoom: 1302\, Bldg: Sobra
 to Campus for Discovery and Innovation Building \, Santa Clara University\
 , 500 El Camino Real\, Santa Clara\, California\, United States\, 95053\, 
 Virtual: https://events.vtools.ieee.org/m/467238
LOCATION:Room: 1302\, Bldg: Sobrato Campus for Discovery and Innovation Bui
 lding \, Santa Clara University\, 500 El Camino Real\, Santa Clara\, Calif
 ornia\, United States\, 95053\, Virtual: https://events.vtools.ieee.org/m/
 467238
ORGANIZER:pzh@ieee.org
SEQUENCE:22
SUMMARY:Advancing Speech Processing with End-to-End Modeling and LLM Integr
 ation
URL;VALUE=URI:https://events.vtools.ieee.org/m/467238
X-ALT-DESC:Description: <br /><p class="MsoNormal">&nbsp\;</p>\n<p class="M
 soNormal"><strong>Abstract</strong></p>\n<p class="MsoNormal">The field of
  speech processing is currently dominated by end-to-end (E2E) models\, whi
 ch utilize a single model to optimize directly towards the final objective
  function rather than optimizing multiple sub-models separately. This tren
 d is particularly notable in automatic speech recognition (ASR). In this t
 alk\, we will provide an overview of E2E ASR models and discuss recent adv
 ancements from an industry perspective. Subsequently\, we will examine the
  trend of E2E modeling beyond ASR\, with applications such as multi-speake
 r ASR and simultaneous speech translation\, where ASR traditionally serves
  as only one of several components. This trend ultimately unlocks multimod
 al intelligence by integrating speech capabilities into large language mod
 els (LLM). We will highlight the most recent developments in this area\, w
 hich present unprecedented opportunities for the field.</p><br /><br />Age
 nda: <br /><p class="MsoNormal">6:30 &ndash\; 7:00 Check-in\, networking\,
  food\, and drink</p>\n<p class="MsoNormal">7:00 &ndash\; 8:00 PM &ndash\;
  Presentation by Dr. Jinyu Li</p>\n<p class="MsoNormal">8:00 &ndash\; 8:30
  PM &ndash\; Q &amp\; A</p>
END:VEVENT
END:VCALENDAR