Episode 19 ICML Expressive Vocalization Competition Panel | The Feelings Lab
Published on Apr 17, 2022
Join us for our podcast on expressive vocalizations and machine learning, where we discuss the powerful, contagious non-word utterances like yelps, laughs, and sighs that play a critical role in our social and emotional lives and provide new channels for human-computer interaction. Our guests include Hume AI CEO Dr. Alan Cowen, Creative Destruction Lab and DeepMind research scientist Dr. Kory Mathewson, Dr. Gauthier Gidel, professor at the Université de Montréal and Mila faculty member, and Hume AI Research Scientists Dr. Panagiotis Tzirakis and Alice Baird.
We begin with Dr. Alan Cowen explaining the need to study vocal bursts: the powerful, contagious non-word utterances like yelps, laughs, and sighs that play a critical role in our social and emotional lives.
Dr. Gauthier Gidel, professor at the Université de Montréal and Mila faculty member, shares the powerful story behind his involvement in the ICML Expressive Vocalization Workshop and Challenge.
DeepMind research scientist Dr. Kory Mathewson and Dr. Gauthier Gidel, professor at the Université de Montréal and Mila faculty member, discuss how new datasets like the ExVo challenge data are essential to progress in understanding vocal expression.
DeepMind research scientist Dr. Kory Mathewson and Dr. Gauthier Gidel, professor at the Université de Montréal and Mila faculty member, discuss their hopes for the future of auditory machine learning.
Subscribe
Sign up now to get notified of any updates or new articles.
Share article
Recent articles
Understanding how emotions are experienced and expressed across different cultures has long been a central focus of debate and study in psychology, cognitive science, and anthropology. What emotions do people in different cultures experience in response to the same evocative scenes and scenarios? What facial movements do they produce? How are feelings and expressions related?
EVI Web Search Demo: The First Interactive Voice AI Podcast
Hume’s Empathic Voice Interface (EVI) is now the first voice API capable of native web search.
Introducing Hume’s Empathic Voice Interface (EVI) API
Last month, we released the demo of our Empathic Voice Interface (EVI). The first emotionally intelligent voice AI API is finally here! EVI does a lot more than stitch together transcription, LLMs, and text-to-speech. With a new empathic LLM (eLLM) that processes your tone of voice, EVI unlocks new capabilities like knowing when to speak, generating more empathic language, and intelligently modulating its own tune, rhythm, and timbre. EVI is the first voice AI that really sounds like it understands you.