<div dir="ltr"><span id="gmail-docs-internal-guid-af29e0ce-7fff-6e8c-e79d-c418c9bbf6af"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"> <span style="background-color:transparent;color:rgb(0,0,0);font-family:Arial;font-size:10pt;white-space:pre-wrap">Dear Community,</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">We are delighted to announce that the first annual ICML Expressive Vocalization (ExVo) Workshop and Competition will be open for registration on April 1st 2022. Organized by leading multidisciplinary researchers in emotion science and AI research and co-sponsored by Hume AI and Mila, in this first iteration of ExVo, we explore the machine learning problem of understanding and generating vocal bursts—a wide range of expressive non-verbal vocalizations such as laughs, sighs, grunts, cries, and screams (to name but a few). </span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Participants of the ExVo Challenge will be presented with three tasks that utilize a newly introduced, large-scale dataset with 60k recordings from 1.7k speakers. The dataset and three tasks draw attention to new innovations in emotion science and capture 10 dimensions of emotion reliably perceived in distinct vocal bursts: Awe, Excitement, Amusement, Awkwardness, Fear, Horror, Distress, Triumph, Sadness and Surprise. </span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">The three tasks include:</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">The Multi-task High-Dimensional Emotion, Age & Country Task (ExVo Multi-task).</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"> Participants will train models to predict the average intensity of each of 10 emotions perceived in vocal bursts, as well as the speaker's age and country, using multitask learning.</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">The Generative Emotional Vocal Burst Task (ExVo Generate).</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"> Participants will use generative models to produce vocal bursts that are associated with 10 distinct emotions. Each team will submit five machine-generated vocalizations that separately convey each emotion—“awe,” “fear,” and more—with maximal intensity and fidelity. The ExVo organization team will provide an automated method for scoring generated samples, but the final evaluation will be performed using human survey ratings.</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-weight:700;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">The Few-Shot Emotion Recognition task (ExVo Few-Shot).</span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"> Participants will predict 10 emotions associated with each speaker’s vocal bursts using multi-output regression with two-shot speaker personalization. Participants will be provided with at least 2 labeled samples per speaker in all splits (train, validation, test). The speaker IDs and the 2 labeled samples per speaker in the test set will be withheld until a week before the deadline for final evaluation of ExVo Few-Shot models.</span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">The ExVo Workshop will also be accepting contributions on other related topics:</span></p><ul style="margin-top:0px;margin-bottom:0px"><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:12pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Detecting and Understanding Vocal Emotional Behavior</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Multi-Task Learning in Affective Computing</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Generating Nonverbal Vocalizations or Speech Prosody</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Personalized Machine Learning for Affective Computing</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:11pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:12pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Other topics related to Affective Verbal and Nonverbal Vocalization</span></p></li></ul><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">See the following website for more information, rules and deadlines:  <a href="goog_21825214">http://</a></span><span style="text-decoration-line:underline;font-size:10pt;font-family:Arial;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><a href="http://www.competitions.hume.ai">www.competitions.hume.ai</a></span></p><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Attached you will find a CfP which can be shared with interested colleagues, and the general deadlines are as follows: </span><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"><br><br></span></p><ul style="margin-top:0px;margin-bottom:0px"><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Challenge start (data release): April 1st </span></p></li><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Baselines and White paper out: April 8th</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Submission for participants and papers: May 27th </span></p></li><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Notification of Acceptance: June 12th</span></p></li><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Camera-Ready, Posters/Slides: June 17th </span></p></li><li dir="ltr" style="list-style-type:disc;font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre"><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt" role="presentation"><span style="font-size:10pt;background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Workshop TBD: ~July 22nd/23rd  </span></p></li></ul><br><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">We look forward to hearing from interested parties! Please get in touch with any questions! </span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap"> </span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">Best,</span></p><p dir="ltr" style="line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style="font-size:10pt;font-family:Arial;color:rgb(0,0,0);background-color:transparent;font-variant-numeric:normal;font-variant-east-asian:normal;vertical-align:baseline;white-space:pre-wrap">ExVo Workshop & Competition organizing team </span></p></span><br class="gmail-Apple-interchange-newline"></div>