BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Pacific BEGIN:DAYLIGHT DTSTART:20240310T030000 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:20240423T230552Z UID:D21E5AF4-D19D-4931-84AE-6427A18AC270 DTSTART;TZID=US/Pacific:20240422T180000 DTEND;TZID=US/Pacific:20240422T203000 DESCRIPTION:$3 registration is mainly to prevent wastage of food because of casual registrations and no-shows.\n\nSynopsis:\n\nThe first talk investi gates the challenges faced by refugee populations globally\, emphasizing e thnocentric biases. Focusing on Syrian refugees and contrasting media cove rage of the Ukrainian crisis\, the talk describes how to leverage empirica l research in human-computer interaction (HCI). The key goal of the projec t that will be discussed is to assess bias among Ukrainian and Syrian refu gees using eye-tracking technology to study participants' decision-making and analyze pupil size data. The talk will investigate whether biases obse rved in media portrayal of refugees can be detected through HCI research.\ n\nThe second talk presents insights into understanding music using machin e learning to analyze and categorize various aspects of music. The talk wi ll explore how music is digitally represented using features analogous to building a fingerprint for each song. The presentation then explores vario us dimensionality reduction techniques for music feature analysis. The spe akers present a novel approach using representation learning in lower dime nsions to evaluate the efficacy of mel-spectrogram features in capturing m usic characteristics across diverse languages. By visualizing the features in transformed spaces\, the speakers explain how insights can be gained i nto fine-grained attributes like vocalist timbre\, gender\, language\, and industry prominence. Spectral and non-spectral algorithms\, including PCA \, t-SNE\, and UMAP\, are employed to analyze music datasets. The speakers ’ findings demonstrate UMAP's superior performance in discerning subtle musical nuances. The research paper that the speakers co-authored on a sim ilar topic won the best paper award at the 10th ICMC\, a Springer conferen ce in 2024. The audience will discover how machines are learning the langu age of music\, opening doors for new music exploration and analysis tools. \n\nSpeaker(s): Dr. Attar\, Samhita\, Kriti\n\nAgenda: \n5:30pm - 6pm Netw orking over cheese pizza\n\n6pm - 7pm Dr. Nada Attar on "Ethnocentric Bias and Refugee Perception - An Eye-Tracking Study using Human-Computer Inter action"\n\n7:01pm - 8pm Samhita Konduri and Kriti Pendyala on "Discovering the Nuances of Music with Machine Learning"\n\n8pm - 8:30pm Photos and ne tworking\n\nSEMI\, 673 S Milpitas Blvd\, Milpitas\, California\, United St ates\, 95035\, Virtual: https://events.vtools.ieee.org/m/411486 LOCATION:SEMI\, 673 S Milpitas Blvd\, Milpitas\, California\, United States \, 95035\, Virtual: https://events.vtools.ieee.org/m/411486 ORGANIZER:pendyala@ieee.org SEQUENCE:43 SUMMARY:Twin talks: Navigating Ethnocentric Bias using Human-Computer Inter action and Discovering the Nuances of Music with Machine Learning URL;VALUE=URI:https://events.vtools.ieee.org/m/411486 X-ALT-DESC:Description: <br /><p class="p1"><span style="font-family: arial \, helvetica\, sans-serif\;">$3 registration is mainly to prevent wastage of food because of casual registrations and no-shows.</span></p>\n<p><span style="font-family: arial\, helvetica\, sans-serif\;"><em><strong>Synopsi s:</strong></em></span></p>\n<p class="MsoNormal" style="mso-margin-top-al t: auto\; mso-margin-bottom-alt: auto\;"><span style="font-family: arial\, helvetica\, sans-serif\;">The first talk investigates the challenges face d by refugee populations globally\, emphasizing ethnocentric biases. Focus ing on Syrian refugees and contrasting media coverage of the Ukrainian cri sis\, the talk describes how to leverage empirical research in human-compu ter interaction (HCI). The key goal of the project that will be discussed is to assess bias among Ukrainian and Syrian refugees using eye-tracking t echnology to study participants' decision-making and analyze pupil size da ta. The talk will investigate whether biases observed in media portrayal o f refugees can be detected through HCI research.</span></p>\n<p class="Mso Normal" style="mso-margin-top-alt: auto\; mso-margin-bottom-alt: auto\;">< span style="font-family: arial\, helvetica\, sans-serif\;">The second talk presents insights into understanding music using machine learning to anal yze and categorize various aspects of music. The talk will explore how mus ic is digitally represented using features analogous to building a fingerp rint for each song. The presentation then explores various dimensionality reduction techniques for music feature analysis. The speakers present a no vel approach using representation learning in lower dimensions to evaluate the efficacy of mel-spectrogram features in capturing music characteristi cs across diverse languages. By visualizing the features in transformed sp aces\, the speakers explain how insights can be gained into fine-grained a ttributes like vocalist timbre\, gender\, language\, and industry prominen ce. Spectral and non-spectral algorithms\, including PCA\, t-SNE\, and UMA P\, are employed to analyze music datasets. The speakers&rsquo\; findings demonstrate UMAP's superior performance in discerning subtle musical nuanc es. The research paper that the speakers co-authored on a similar topic wo n the best paper award at the 10<sup>th</sup> ICMC\, a Springer conference in 2024. The audience will discover how machines are learning the languag e of music\, opening doors for new music exploration and analysis tools.</ span></p><br /><br />Agenda: <br /><p>5:30pm - 6pm Networking over cheese pizza</p>\n<p>6pm - 7pm Dr. Nada Attar on "Ethnocentric Bias and Refugee P erception - An Eye-Tracking Study using Human-Computer Interaction"</p>\n< p>7:01pm - 8pm Samhita Konduri and Kriti Pendyala on "Discovering the Nuan ces of Music with Machine Learning"</p>\n<p>8pm - 8:30pm Photos and networ king</p> END:VEVENT END:VCALENDAR