Here Is How Amazon Wants to Improve Machine Dubbing
AWS researchers create a way to train an automatic dubbing system based on bi-directional language data. Using phonemes instead of words resulted in better aligned speech and MT.
Language Industry (Artificial) Intelligence — Slator Answers
AWS
Large Amazon Study on Human Dubbing Has ‘Surprising’ Implications for AI Dubbing
Amazon reviewed hundreds of hours of Prime content and found that human dubbers prioritize translation quality and speech naturalness over timing and lip sync.
Machine Dubbing: Amazon AI Opens New Chapter in Automating Media Localization
Team of Amazon AI researchers combines various deep-learning models to build automatic dubbing system. Viewer feedback reveals unnaturalness of speaking rate as main problem.
Inside Translation, Localization, and NLP on GitHub, the World’s #1 Code Sharing Site
Over two dozen charts and tables and high-level visualizations as well as analysis of GitHub code repositories relevant to the language industry.
Your information will not be shared with third parties. No Spam.