BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/London BEGIN:DAYLIGHT DTSTART:20250330T020000 TZOFFSETFROM:+0000 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:BST END:DAYLIGHT BEGIN:STANDARD DTSTART:20251026T010000 TZOFFSETFROM:+0100 TZOFFSETTO:+0000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:GMT END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250409T165645Z UID:802D6724-2BD3-4A65-8665-07791372D2B3 DTSTART;TZID=Europe/London:20250404T133000 DTEND;TZID=Europe/London:20250404T150000 DESCRIPTION:The IEEE UK&I Signal Processing Society Chapter is kicking off a new series of events with an invited speaker seminar series\, where talk s will not only focus on a specific technical area\, but will also highlig ht a portfolio of activities and opportunities in centres of excellence\, research institutes\, and research groups. The seminar will also give brie f updates on future IEEE UK&I SPS Chapter events. We hope these events wil l contribute to refreshing and building a UK signal processing research ma p.\n\nIn this first talk\, we are delighted to welcome Professor Wenwu Wan g\, a Professor in Signal Processing and Machine Learning\, School of Comp uter Science and Electronic Engineering\, University of Surrey\, UK\, who will talk about Large Language-Audio Models and their Applications. Profes sor Wang is a recognised world expert in the application of AI to audio pr ocessing\, and his talk will cover the interface of statistical-signal pro cessing techniques and the latest AI technologies.\n\nPresentation abstrac t: Large Language Models (LLMs) are being explored in audio processing to interpret and generate meaningful patterns from complex sound data\, such as speech\, music\, environmental noise\, sound effects\, and other non-ve rbal audio. Combined with acoustic models\, LLMs offer great potential for addressing a variety of problems in audio processing\, such as audio capt ioning\, audio generation\, source separation\, and audio coding. This tal k will cover recent advancements in using LLMs to address audio-related ch allenges. Topics will include the language-audio models for mapping and al igning audio with textual data\, their applications across various audio t asks\, the creation of language-audio datasets\, and potential future dire ctions in language-audio learning. We will demonstrate our recent works in this area\, for example\, AudioLDM\, AudioLDM2 and WavJourney for audio g eneration and storytelling\, AudioSep for audio source separation\, ACTUAL for audio captioning\, SemantiCodec for audio coding\, WavCraft for conte nt creation and editing\, and APT-LLMs for audio reasoning\, and the datas ets WavCaps\, Sound-VECaps\, and AudioSetCaps for training and evaluating large language-audio models.\n\nThis will be a hybrid event\, with both in -person and online attendance options. If you intend to participate in per son\, we kindly encourage you to [register](https://events.teams.microsoft .com/event/ca435c10-5711-438c-90d8-05eafb1bf778@6b902693-1074-40aa-9e21-d8 9446a2ebb5)as soon as possible\, as in-person capacity is limited. Light r efreshments\, including coffee and tea\, will be available for in-person a ttendees.\n\nSpeaker(s): Wenwu Wang\, James Hopgood\n\nRoom: CVSSP Seminar Room\, Ground level\, Room 35\, Bldg: Arthur C. Clarke Building (Block BA )\, University of Surrey\, Stag Hill Campus\, Guildford\, England\, United Kingdom\, GU2 7XH\, Virtual: https://events.vtools.ieee.org/m/476685 LOCATION:Room: CVSSP Seminar Room\, Ground level\, Room 35\, Bldg: Arthur C . Clarke Building (Block BA)\, University of Surrey\, Stag Hill Campus\, G uildford\, England\, United Kingdom\, GU2 7XH\, Virtual: https://events.vt ools.ieee.org/m/476685 ORGANIZER:g.ntavazliskatsaros@surrey.ac.uk SEQUENCE:243 SUMMARY:IEEE UK & Ireland Signal Processing Society Seminar "Large Language -Audio Models and Applications"\, Professor Wenwu Wang (Event SPS-2025-01) URL;VALUE=URI:https://events.vtools.ieee.org/m/476685 X-ALT-DESC:Description: <br /><p>The IEEE UK&amp\;I Signal Processing Socie ty Chapter is kicking off a new series of events with an invited speaker s eminar series\, where talks will not only focus on a specific technical ar ea\, but will also highlight a portfolio of activities and opportunities i n centres of excellence\, research institutes\, and research groups. The s eminar will also give brief updates on future IEEE UK&amp\;I SPS Chapter e vents. We hope these events will contribute to refreshing and building a U K signal processing research map.</p>\n<p>In this first talk\, we are deli ghted to welcome Professor Wenwu Wang\, a Professor in Signal Processing a nd Machine Learning\, School of Computer Science and Electronic Engineerin g\, University of Surrey\, UK\, who will talk about Large Language-Audio M odels and their Applications. Professor Wang is a recognised world expert in the application of AI to audio processing\, and his talk will cover the interface of statistical-signal processing techniques and the latest AI t echnologies.</p>\n<p>&nbsp\;</p>\n<p><strong>Presentation abstract:</stron g> Large Language Models (LLMs) are being explored in audio processing to interpret and generate meaningful patterns from complex sound data\, such as speech\, music\, environmental noise\, sound effects\, and other non-ve rbal audio. Combined with acoustic models\, LLMs offer great potential for addressing a variety of problems in audio processing\, such as audio capt ioning\, audio generation\, source separation\, and audio coding. This tal k will cover recent advancements in using LLMs to address audio-related ch allenges. Topics will include the language-audio models for mapping and al igning audio with textual data\, their applications across various audio t asks\, the creation of language-audio datasets\, and potential future dire ctions in language-audio learning. We will demonstrate our recent works in this area\, for example\, AudioLDM\, AudioLDM2 and WavJourney for audio g eneration and storytelling\, AudioSep for audio source separation\, ACTUAL for audio captioning\, SemantiCodec for audio coding\, WavCraft for conte nt creation and editing\, and APT-LLMs for audio reasoning\, and the datas ets WavCaps\, Sound-VECaps\, and AudioSetCaps for training and evaluating large language-audio models.</p>\n<p>&nbsp\;</p>\n<p data-start="102" data -end="328">This will be a <strong data-start="102" data-end="133">hybrid e vent</strong>\, with both in-person and online attendance options. If you intend to participate <strong data-start="215" data-end="228">in person</s trong>\, we kindly encourage you to <strong data-start="257" data-end="289 "><a href="https://events.teams.microsoft.com/event/ca435c10-5711-438c-90d 8-05eafb1bf778@6b902693-1074-40aa-9e21-d89446a2ebb5" target="_blank" rel=" noopener">register </a>as soon as possible</strong>\, as <strong data-star t="294" data-end="327">in-person capacity is limited</strong>. Light refre shments\, including coffee and tea\, will be available for in-person atten dees.</p>\n<p data-start="330" data-end="379">&nbsp\;</p> END:VEVENT END:VCALENDAR