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
Hume AI creates emotionally intelligent voice interactions with Claude
Hume AI trained its speech-language foundation model to verbalize Claude responses, powering natural, empathic voice conversations that help developers build trust with users in healthcare, customer service, and consumer applications.
How EverFriends.ai uses empathic AI for eldercare
To truly connect with users and provide a natural, empathic experience, EverFriends.ai needed an AI solution capable of understanding and responding to emotional cues. They found their answer in Hume's Empathic Voice Interface (EVI). EVI merges generative language and voice into a single model trained specifically for emotional intelligence, enabling it to emphasize the right words, laugh or sigh at appropriate times, and much more, guided by language prompting to suit any particular use case.
How can emotionally intelligent voice AI support our mental health?
Recent advances in voice-to-voice AI, like EVI 2, offer emotionally intelligent interactions, picking up on vocal cues related to mental and physical health, which could enhance both clinical care and daily well-being.