Invention:
This technology is a program that uses AI to adjust a speaker’s accent in audio/video recordings for clearer comprehension while maintaining the original speaker’s tone, as opposed to dubbing over with a generic speaker. The technology will allow clearer communication between people with different voice tones and foreign backgrounds (WUSTL).
Background:
Communication becomes especially difficult when individuals with different accents interact, as our brains are accustomed to specific sound patterns. The absence of familiar sounds may cause individuals to perceive the other speaker's accent as “strange” or “foreign.” Even among individuals with comparable accents, understanding speech is a highly intricate task. The acoustic signals that people decipher undergo various changes unrelated to meaning.
Applications:
- Audio and video editing software
- Online voice communication software platforms
- Offshore telemarketing and call centers
Advantages:
- Instant accent translation
- Generates the edited voice with the user’s own voice tone instead of a generic one
