all AI news
AI Listens by Seeing as Well
Jan. 19, 2022, 4 p.m. | Bruno Santos
InfoQ - AI, ML & Data Engineering www.infoq.com
Meta AI released a self-supervised speech recognition model that also uses video and achieves 75% better accuracy for some amount of data than current state-of-the-art models. This new model, Audio-Visual Hidden BERT (AV-HuBERT), uses audiovisual features for improving models based only on hearing speech. Visual features used are based on lip-reading, similar to what humans do.
By Bruno Santosai artificial intelligence facial recognition machine learning ml & data engineering natural language processing news
More from www.infoq.com / InfoQ - AI, ML & Data Engineering
Article: Unpacking How Ads Ranking Works at Pinterest
2 days, 3 hours ago |
www.infoq.com
CNCF Incubates Strimzi to Simplify Kafka on Kubernetes
3 days, 16 hours ago |
www.infoq.com
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Research Assistant/Associate, Health Data Science [LKCMedicine]
@ Nanyang Technological University | NTU Novena Campus, Singapore
Senior Machine Learning Engineer, Portfolio ML
@ Affirm | Remote Canada
[Sessional Lecturer] Foundations of Data Analytics and Machine Learning - APS1070
@ University of Toronto | Toronto, ON, CA
Senior Data Scientist
@ Prosper | United States
Data Analyst
@ ZF Friedrichshafen AG | Coimbatore, TN, IN, 641659