Keynote Speakers

Dr. Yutian Chen. DeepMind, London, UK. “Using WaveNet to reunite speech-impaired users with their original voices”.

Dr Yutian Chen is a staff research scientist at DeepMind. He obtained his PhD in machine learning at the University of California, Irvine, and later worked at the University of Cambridge as a research associate (Postdoc) before joining DeepMind. Yutian took part in the AlphaGo and AlphaGo Zero project, developed Game Go AI programs that defeated the world champions. The AlphaGo project was ranked in the top 10 discoveries of the decade 2010s by the New Scientist magazine. Yutian has conducted research in multiple machine learning areas including Bayesian methods, deep learning, reinforcement learning, generative models and meta-learning with applications in gaming AI, computer vision and text-to-speech. Yutian also serves as reviewers and area chairs for multiple academic conferences and journals.

Dr. Erik Cambria. SenticNet, Singapore. “Neurosymbolic AI for Sentiment Analysis”.

Dr. Erik Cambria is the Founder of SenticNet, a Singapore-based company offering B2B sentiment analysis services, and an Associate Professor at NTU, where he also holds the appointment of Provost Chair in Computer Science and Engineering. Prior to joining NTU, he worked at Microsoft Research Asia (Beijing) and HP Labs India (Bangalore) and earned his PhD through a joint programme between the University of Stirling and MIT Media Lab. His research focuses on neurosymbolic AI for explainable natural language processing in domains like sentiment analysis, dialogue systems, and financial forecasting. He is recipient of several awards, e.g., IEEE Outstanding Career Award, was listed among the AI's 10 to Watch, and was featured in Forbes as one of the 5 People Building Our AI Future. He is an IEEE Fellow, Associate Editor of many top-tier AI journals, e.g., INFFUS and IEEE TAFFC, and is involved in various international conferences as program chair and SPC member.

Dr. Alan Cowen. Hume AI, New York, USA. “Fundamental advances in understanding nonverbal behavior"

Dr. Alan Cowen is an applied mathematician and computational emotion scientist developing new data-driven methods to study human experience and expression. He was previously a researcher at the University of California and visiting scientist at Google, where he helped establish affective computing research efforts. His discoveries have been featured in leading journals such as Nature, PNAS, Science Advances, and Nature Human Behavior and covered in press outlets ranging from CNN to Scientific American. His research applies new computational tools to address how emotional behaviors can be evoked, conceptualized, predicted, and annotated, how they influence our social interactions, and how they bring meaning to our everyday lives.

Competition Tasks and Rules

The Multi-task High-Dimensional Emotion, Age & Country Task (ExVo Multi-Task).

In the ExVo MultiT task, participants will be challenged with predicting the average intensity of each of 10 emotions perceived in vocal bursts, as well as the speaker's Age and Native-Country, as a multi-task process. For emotion and age, the participants will perform a regression task, and for native-country, classification. Participants will report the Concordance Correlation Coefficient (CCC), for the emotion regression task, Mean Absolute Error (MAE) for Age (in years), and Unweighted Average Recall (UAR) for the country classification task. The baseline for this challenge is based on a combined score computed by the harmonic mean between CCC, (inverted) MAE, and UAR.

The Generative Emotional Vocal Burst Task (ExVo Generate).

In the ExVo Generate task, participants will be tasked with applying generative modelling approaches to produce vocal bursts that are associated with 10 distinct emotions. Each team will submit 100 machine-generated vocalizations that differentially convey either a selection of or all 10 emotions—“awe,” “fear,” etc.—with maximal intensity and fidelity. The ExVo organization team will provide a method for scoring the generated samples with a Fréchet Inception Distance (FID), using a baseline predictive model based on the training set. The final evaluation will incorporate human ratings gathered by Hume AI of a random subset of 5/100 samples per targeted emotion. These ratings of the generated vocal bursts will be gathered using the same methodology and from the same participant, population used to collect the training data, with each vocal burst judged in terms of the perceived intensity of each target emotion. Generated samples will be evaluated based on the correlation between normed (0-1) average intensity ratings for the 10 classes and the identity matrix consisting of dummy variables for each class. The baseline for the challenge is based on a combined score from the provided FID of a given class and the human evaluation.

Additionally, winning teams from the ExVo Generate task have the opportunity to demo their approach at the ICML Machine Learning for Audio Synthesis Workshop.

The Few-Shot Emotion Recognition task (ExVo Few-Shot).

In the ExVo Few-Shot task, the participants will predict the same 10 emotions as a multi-output regression task, using a model or multiple models. Participants will be provided with at least 2 samples per speaker in all splits (train, validation, test) and will be tasked with performing two-shot personalized emotion recognition. The subject IDs and corresponding emotion labels with two samples per speaker in the test set will be withheld until a week before the deadline for final evaluation of ExVo Few-Shot models on the test data. Participants will report the Concordance Correlation Coefficient (CCC) across all 10 emotion outputs as an evaluation metric.

Important Dates (AoE)

• Challenge Opening (data available): April 1, 2022 ✓

• Baselines and paper released: April 8, 2022 ✓

• ExVo MultiTask track submission deadline: May 26, 2022 ✓

• ExVo Few-Shot (test labels): May 27, 2022 ✓

• ExVo Few-Shot and ExVo Generate track submission deadline: June 1, 2022 ✓

• Workshop paper submission: June 3, 2022 June 6, 2022

• Notification of Acceptance/Rejection: June 13, 2022 ✓

• Workshop Video Upload Deadline: July 1, 2022 ✓

• Workshop: Saturday, July 23, 2022 (301-303 T450)

Organizers

Alice Baird. Hume AI, New York, USA. Alice Baird is an audio researcher with interdisciplinary expertise in machine learning, computational paralinguistics, stress, and emotional well-being. She completed her PhD at the University of Augsburg’s Chair of Embedded Intelligence for Health Care and Wellbeing in 2021, where she was supervised by Dr Björn Schuller. Her work on emotion understanding from speech, physiological, and multimodal data has been published extensively in leading journals and conferences including INTERSPEECH, ICASSP, IEEE Intelligent Systems, and the IEEE Journal of Biomedical and Health Informatics (i10-index: 29). Alice has had extensive experience with competition organization, holding data chair for both the INTERSPEECH Computational Paralinguistics Challenge (ComParE) and ACM MM Multimodal Sentiment Challenge (MuSe). She recently joined Hume AI as an AI research scientist. 

Panagiotis Tzirakis. Hume AI, New York, USA. Dr Tzirakis is a computer scientist and AI researcher with expertise in deep learning and emotion recognition across modalities. He earned his Ph.D. with the Intelligent Behaviour Understanding Group (iBUG) at Imperial College London, where he advanced multimodal emotion recognition efforts. He has published in top outlets including Information Fusion, International Journal of Computer Vision, and several IEEE conference proceedings (e.g. ICASSP, INTERSPEECH) on topics including 3D facial motion synthesis, multi-channel speech enhancement, the detection of Gibbon calls, and emotion recognition from audio and video (i10-index: 16). He recently joined Hume AI as an AI research scientist. 

Kory W. Mathewson. DeepMind, Montreal QC.   Kory Mathewson is a Research Scientist with DeepMind and a Lab Scientist with the Creative Destruction Lab. Kory holds a Ph.D. in Computing Science from the University of Alberta with the Alberta Machine Intelligence Institute. His research focuses on studying the interaction between humans and machines, with a focus on conversational dialog systems and human-robot interfaces. Kory’s work has been featured in Time magazine, the Wall Street Journal, and the New York Times. His recent work explores new algorithms for laughter generation. Kory is also an accomplished performance artist with more than 15 years of experience in improvisation with Rapid Fire Theatre and Improbotics. He fuses his interests by developing artificial intelligences to perform alongside. Kory is a co-organizer of the WordPlay: When Language Meets Games workshop at NeurIPS and previously organized the Future of Interactive Machine Learning, also at NeurIPS. For more, see: https://korymathewson.com/ and Google Scholar.

Gauthier Gidel. Mila, Université de Montréal, Montreal QC. Gauthier Gidel is an assistant professor at the University of Montreal in the department of computer science and operational research and a core member of Mila. Gauthier did his Ph.D. at the University of Montreal, during which he was awarded a Borealis AI fellowship and two DIRO excellence grants. He is currently a recipient of a Canada CIFAR AI Chair. His research revolves around optimization, game theory, machine learning. He has published several top-tier conference papers on Generative Adversarial Networks (GANs) and recently specifically worked on laughter generation using GANs as part of an artistic collaboration with National Film Board of Canada.

Eilif B. Muller. Mila, Université de Montréal, CHU Ste-Justine Research Center, Montréal QC.  Dr. Muller is a Canada CIFAR AI Chair at Mila, an IVADO Assistant Research Professor in the Department of Neuroscience at the Université de Montréal, a Fond de Recherche du Québec en Santé (FRQS) Research Scholar, and principal investigator of the Architectures of Biological Learning Lab (ABL-Lab) at the CHU Sainte-Justine Research Center.  His research at the intersection of neuroscience and AI employs simulation and modeling to understand learning function and dysfunction in the mammalian brain, and has resulted in publications in top journals such as Cell, Nature Neuroscience, Nature Communications, and Cerebral Cortex (h-index: 25; i10-index: 38), and diverse media coverage including a feature length documentary film, In Silico. He was previously deputy director of simulation neuroscience at the Blue Brain Project, EPFL, Switzerland, and an Applied Research Scientist at Element AI Montreal, QC, and is part of an artistic collaboration with the National Film Board of Canada on laughter generation with GANs.

Björn Schuller. Imperial College London, United Kingdom. Björn W. Schuller received his diploma, doctoral degree, habilitation, and Adjunct Teaching Professor in Machine Intelligence and Signal Processing all in EE/IT from TUM in Munich/Germany. He is Full Professor of Artificial Intelligence and the Head of GLAM – the Group on Language, Audio, & Music at Imperial College London/UK, Full Professor and Chair of Embedded Intelligence for Health Care and Wellbeing at the University of Augsburg/Germany, co-founding CEO and current CSO of audEERING – an Audio Intelligence company based near Munich and in Berlin, Germany amongst other Professorships and Affiliations. He (co-)authored 1000+ publications (43k+ citations, i10-index: 563), is Field Chief Editor of Frontiers in Digital Health and was Editor in Chief of the IEEE Transactions on Affective Computing amongst manifold further commitments and service to the community including Technical Chair of INTERSPEECH 2019 and organization of more than 25 research challenges. 

Erik Cambria. Nanyang Technological University Singapore. Erik Cambria is the Founder of SenticNet, a Singapore-based company offering B2B sentiment analysis services, and an Associate Professor at NTU, where he also holds the appointment of Provost Chair in Computer Science and Engineering. Prior to joining NTU, he worked at Microsoft Research Asia (Beijing) and HP Labs India (Bangalore) and earned his PhD through a joint program between the University of Stirling and MIT Media Lab. His research focuses on neurosymbolic AI for explainable natural language processing in domains like sentiment analysis, dialogue systems, and financial forecasting. He is the recipient of several awards, e.g., IEEE Outstanding Career Award, was listed among the AI's 10 to Watch, and was featured in Forbes as one of the 5 People Building Our AI Future. He is an IEEE Fellow, Associate Editor of many top-tier AI journals, e.g., INFFUS and IEEE TAFFC, and is involved in various international conferences as program chair and SPC member.

Dacher Keltner. The University of California, Berkeley, California, U.S.A. Dr. Keltner is one of the world’s foremost emotion scientists. He is a professor of psychology at UC Berkeley and the director of the Greater Good Science Center. He has over 200 scientific publications (i10-index: 222) and six books, including Born to Be Good, The Compassionate Instinct, and The Power Paradox. He has written for many popular outlets, from The New York Times to Slate. He was also the scientific advisor behind Pixar’s Inside Out, is involved with the education of health care providers and judges, and has consulted extensively for Google, Facebook, Apple, and Pinterest, on issues related to emotion and well-being.

Alan Cowen. Hume AI, New York, U.S.A. Dr. Cowen is an applied mathematician and computational emotion scientist developing new data-driven methods to study human experience and expression. He was previously a researcher at the University of California and visiting scientist at Google, where he helped establish affective computing research efforts. His discoveries have been featured in top journals such as Nature, PNAS, Science Advances, and Nature Human Behavior (i10-index: 16) and covered in press outlets ranging from CNN to Scientific American. His research applies new computational tools to address how emotional behaviors can be evoked, conceptualized, predicted, and annotated, how they influence our social interactions, and how they bring meaning to our everyday lives.