BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/London BEGIN:DAYLIGHT DTSTART:20260329T020000 TZOFFSETFROM:+0000 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:BST END:DAYLIGHT BEGIN:STANDARD DTSTART:20261025T010000 TZOFFSETFROM:+0100 TZOFFSETTO:+0000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:GMT END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260428T141319Z UID:C4E2C021-3C49-4738-8285-3DC40CD4FC00 DTSTART;TZID=Europe/London:20260417T200000 DTEND;TZID=Europe/London:20260417T210000 DESCRIPTION:IEEE SMC IIT SBC x IEEE Systems Council Tunisia Section\n\nIEEE SMC IIT SBC\, in collaboration with the IEEE Systems Council Tunisia Sect ion\, organized a technical talk entitled “Advancing Speech Enhancement with Machine Learning: Lightweight Models\,” delivered by Dr. Nasir Sale em. The session focused on recent advances in speech enhancement for resou rce-constrained environments such as smartphones\, hearing aids\, and embe dded systems. The main points discussed during the talk included:\n\n- lig htweight and efficient machine learning models for speech enhancement\n\n- model compression techniques for reducing computational complexity\n\n- e fficient neural network architectures for real-time applications\n\n- low- complexity time-frequency representations\n\n- speech enhancement in noisy and real-world acoustic conditions\n\n- recent developments in audio-visu al speech enhancement\n\n- methods for achieving low-latency and energy-ef ficient performance\n\n- maintaining speech quality and intelligibility in practical deployment scenarios\n\nThe talk provided valuable insights for students and researchers interested in speech processing\, machine learni ng\, and intelligent audio systems.\n\nSpeaker(s): Nassir Saleem\, \n\nVir tual: https://events.vtools.ieee.org/m/553888 LOCATION:Virtual: https://events.vtools.ieee.org/m/553888 ORGANIZER:ayoub.bougacha@ieee.org SEQUENCE:62 SUMMARY:Advancing Speech Enhancement with Machine Learning: Lightweight Mod els URL;VALUE=URI:https://events.vtools.ieee.org/m/553888 X-ALT-DESC:Description: <br /><h1 style="text-align: center\;"><span class= "TextRun SCXW132515156 BCX0" lang="EN-US" xml:lang="EN-US" data-contrast=" auto"><span class="NormalTextRun SCXW132515156 BCX0"><span style="color: r gb(53\, 152\, 219)\;">IEEE SMC IIT SBC</span> x <span style="color: rgb(22 \, 145\, 121)\;">IEEE Systems Council Tunisia Section</span></span></span> </h1>\n<p>&nbsp\;</p>\n<div class="OutlineElement Ltr SCXW132515156 BCX0"> \n<p class="Paragraph SCXW132515156 BCX0"><span class="TextRun SCXW1325151 56 BCX0" lang="EN-US" xml:lang="EN-US" data-contrast="auto"><span class="N ormalTextRun SCXW132515156 BCX0"><strong>IEEE SMC IIT SBC</strong>\, in co llaboration with the <strong>IEEE Systems Council Tunisia Section</strong> \, organized a technical talk entitled &ldquo\;Advancing Speech Enhancemen t with Machine Learning: Lightweight Models\,&rdquo\; delivered by Dr. Nas ir Saleem. The session focused on recent advances in speech enhancement fo r resource-constrained environments such as smartphones\, hearing aids\, a nd embedded systems. The main points discussed during the talk included:</ span></span><span class="EOP Selected SCXW132515156 BCX0" data-ccp-props=" {}">&nbsp\;</span></p>\n</div>\n<div class="OutlineElement Ltr SCXW1325151 56 BCX0">\n<ul>\n<li class="Paragraph SCXW132515156 BCX0" lang="FR-FR" xml :lang="FR-FR"><span class="TextRun SCXW132515156 BCX0" lang="EN-US" xml:la ng="EN-US" data-contrast="auto"><span class="NormalTextRun SCXW132515156 B CX0">lightweight and efficient machine learning models for speech enhancem ent</span></span><span class="EOP Selected SCXW132515156 BCX0" data-ccp-pr ops="{}">&nbsp\;</span></li>\n</ul>\n</div>\n<div class="OutlineElement Lt r SCXW132515156 BCX0">\n<ul>\n<li class="Paragraph SCXW132515156 BCX0" lan g="FR-FR" xml:lang="FR-FR"><span class="TextRun SCXW132515156 BCX0" lang=" EN-US" xml:lang="EN-US" data-contrast="auto"><span class="NormalTextRun SC XW132515156 BCX0">model compression techniques for reducing computational complexity</span></span><span class="EOP Selected SCXW132515156 BCX0" data -ccp-props="{}">&nbsp\;</span></li>\n</ul>\n</div>\n<div class="OutlineEle ment Ltr SCXW132515156 BCX0">\n<ul>\n<li class="Paragraph SCXW132515156 BC X0" lang="FR-FR" xml:lang="FR-FR"><span class="TextRun SCXW132515156 BCX0" lang="EN-US" xml:lang="EN-US" data-contrast="auto"><span class="NormalTex tRun SCXW132515156 BCX0">efficient neural network architectures for real-t ime applications</span></span><span class="EOP Selected SCXW132515156 BCX0 " data-ccp-props="{}">&nbsp\;</span></li>\n</ul>\n</div>\n<div class="Outl ineElement Ltr SCXW132515156 BCX0">\n<ul>\n<li class="Paragraph SCXW132515 156 BCX0" lang="FR-FR" xml:lang="FR-FR"><span class="TextRun SCXW132515156 BCX0" lang="EN-US" xml:lang="EN-US" data-contrast="auto"><span class="Nor malTextRun SCXW132515156 BCX0">low-complexity time-frequency representatio ns</span></span><span class="EOP Selected SCXW132515156 BCX0" data-ccp-pro ps="{}">&nbsp\;</span></li>\n</ul>\n</div>\n<div class="OutlineElement Ltr SCXW132515156 BCX0">\n<ul>\n<li class="Paragraph SCXW132515156 BCX0" lang ="FR-FR" xml:lang="FR-FR"><span class="TextRun SCXW132515156 BCX0" lang="E N-US" xml:lang="EN-US" data-contrast="auto"><span class="NormalTextRun SCX W132515156 BCX0">speech enhancement in noisy and real-world acoustic condi tions</span></span><span class="EOP Selected SCXW132515156 BCX0" data-ccp- props="{}">&nbsp\;</span></li>\n</ul>\n</div>\n<div class="OutlineElement Ltr SCXW132515156 BCX0">\n<ul>\n<li class="Paragraph SCXW132515156 BCX0" l ang="FR-FR" xml:lang="FR-FR"><span class="TextRun SCXW132515156 BCX0" lang ="EN-US" xml:lang="EN-US" data-contrast="auto"><span class="NormalTextRun SCXW132515156 BCX0">recent developments in audio-visual speech enhancement </span></span><span class="EOP Selected SCXW132515156 BCX0" data-ccp-props ="{}">&nbsp\;</span></li>\n</ul>\n</div>\n<div class="OutlineElement Ltr S CXW132515156 BCX0">\n<ul>\n<li class="Paragraph SCXW132515156 BCX0" lang=" FR-FR" xml:lang="FR-FR"><span class="TextRun SCXW132515156 BCX0" lang="EN- US" xml:lang="EN-US" data-contrast="auto"><span class="NormalTextRun SCXW1 32515156 BCX0">methods for achieving low-latency and energy-efficient perf ormance</span></span><span class="EOP Selected SCXW132515156 BCX0" data-cc p-props="{}">&nbsp\;</span></li>\n</ul>\n</div>\n<div class="OutlineElemen t Ltr SCXW132515156 BCX0">\n<ul>\n<li class="Paragraph SCXW132515156 BCX0" lang="FR-FR" xml:lang="FR-FR"><span class="TextRun SCXW132515156 BCX0" la ng="EN-US" xml:lang="EN-US" data-contrast="auto"><span class="NormalTextRu n SCXW132515156 BCX0">maintaining speech quality and intelligibility in pr actical deployment scenarios</span></span><span class="EOP Selected SCXW13 2515156 BCX0" data-ccp-props="{}">&nbsp\;</span></li>\n</ul>\n</div>\n<div class="OutlineElement Ltr SCXW132515156 BCX0">\n<p class="Paragraph SCXW1 32515156 BCX0" lang="FR-FR" xml:lang="FR-FR"><span class="TextRun SCXW1325 15156 BCX0" lang="EN-US" xml:lang="EN-US" data-contrast="auto"><span class ="NormalTextRun SCXW132515156 BCX0">&nbsp\;</span></span><span class="Text Run SCXW132515156 BCX0" lang="EN-US" xml:lang="EN-US" data-contrast="auto" ><span class="NormalTextRun SCXW132515156 BCX0">The talk provided valuable insights for students and researchers interested in speech processing\, m achine learning\, and intelligent audio systems.</span></span><span class= "EOP Selected SCXW132515156 BCX0" data-ccp-props="{}">&nbsp\;</span></p>\n </div> END:VEVENT END:VCALENDAR