BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Copenhagen
BEGIN:DAYLIGHT
DTSTART:20250330T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250922T134735Z
UID:9DD71D3E-6D34-4A79-B67E-7189E5FC0AD8
DTSTART;TZID=Europe/Copenhagen:20250815T090000
DTEND;TZID=Europe/Copenhagen:20250815T100000
DESCRIPTION:This is an invited IEEE SPS Distinguished Industry Speaker lect
 ure.\n\nLarge Language Models (LLMs) have significantly influenced natural
  language processing (NLP) and are increasingly affecting speech processin
 g. This talk examines the effects of LLMs on speech processing and multimo
 dal intelligence. It reviews the progression from spoken language models (
 SLMs) to multimodal LLMs (MLLMs)\, referencing the model development proce
 ss at Microsoft. The discussion includes comparisons of model architecture
 s\, advances in speech generation and understanding\, and the integration 
 of speech and text modalities. The talk concludes by presenting the recent
  Phi-4-multimodal model as an example which has superior capabilities rela
 tive to its size.\n\n---------\n\nAdditionally\, we (Pioneer Centre for AI
 ’s Signals and Decoding Collaboratory) are organising a co-located event
 :\n\n[2025 Workshop on Self-Supervised Learning for Signal Decoding](https
 ://www.aicentre.dk/events/2025-workshop-on-self-supervised-learning-for-si
 gnal-decoding)\n\nPlease note that this workshop requires separate registr
 ation\, which can be completed on the workshop webpage. Spaces for the wor
 kshop are limited.\n\nCo-sponsored by: Pioneer Centre for AI’s Signals a
 nd Decoding Collaboratory\n\nSpeaker(s): Jinyu Li\n\nAalborg\, Nordjylland
 s Amt\, Denmark\, 9000\, Virtual: https://events.vtools.ieee.org/m/490589
LOCATION:Aalborg\, Nordjyllands Amt\, Denmark\, 9000\, Virtual: https://eve
 nts.vtools.ieee.org/m/490589
ORGANIZER:zt@es.aau.dk
SEQUENCE:84
SUMMARY:IEEE SPS Distinguished Industry Speaker lecture: Unlocking multimod
 al intelligence with large language model
URL;VALUE=URI:https://events.vtools.ieee.org/m/490589
X-ALT-DESC:Description: <br /><p>This is an invited IEEE SPS Distinguished 
 Industry Speaker lecture.&nbsp\;</p>\n<p>Large Language Models (LLMs) have
  significantly influenced natural language processing (NLP) and are increa
 singly affecting speech processing. This talk examines the effects of LLMs
  on speech processing and multimodal intelligence. It reviews the progress
 ion from spoken language models (SLMs) to multimodal LLMs (MLLMs)\, refere
 ncing the model development process at Microsoft. The discussion includes 
 comparisons of model architectures\, advances in speech generation and und
 erstanding\, and the integration of speech and text modalities. The talk c
 oncludes by presenting the recent Phi-4-multimodal model as an example whi
 ch has superior capabilities relative to its size.&nbsp\;</p>\n<p>--------
 -</p>\n<p>Additionally\, we (Pioneer Centre for AI&rsquo\;s Signals and De
 coding Collaboratory) are organising a co-located event:&nbsp\;</p>\n<p><a
  href="https://www.aicentre.dk/events/2025-workshop-on-self-supervised-lea
 rning-for-signal-decoding">2025 Workshop on Self-Supervised Learning for S
 ignal Decoding</a></p>\n<p>Please note that this workshop requires separat
 e registration\, which can be completed on the workshop webpage. Spaces fo
 r the workshop are limited.&nbsp\;</p>\n<p>&nbsp\;</p>
END:VEVENT
END:VCALENDAR