Using AI to Create Any Voice with Ron Weissman, Zohaib Ahmed, Jim Connor
b'
Studio software and computer vision have empowered the adoption of virtual characters and virtual movie sets.\\xa0 The next logical question was: why are we limited to actual human voices in the dialogue?\\xa0
The emergence of AI is powering a new approach to analyzing voices, identifying and tagging speaking patterns by age, sex, education, cultural heritage, and accent to fix audio tracks in movies.\\xa0 This podcast discusses the Company\\u2019s technology to create a synthesized voice that is designed to fit the character in a movie, animation or audio dialogue.
The challenge in a movie is casting actors who have both the image and voice to convincingly fit into the story\\u2019s setting, whether it is in space, on another planet in the future, at a historical time such as the civil war, or even a prehistoric time. Well, this is not just any simulated audio, this is the ability to create a voice that reflects a specific age, sex, education, profession all within a specific cultural background, complete with a regional accent.
'