20240038271. SYSTEM AND METHOD FOR GENERATING VIDEO IN TARGET LANGUAGE simplified abstract (Yahoo Assets LLC)

SYSTEM AND METHOD FOR GENERATING VIDEO IN TARGET LANGUAGE

Organization Name

Yahoo Assets LLC

Inventor(s)

Paloma De Juan of New York NY (US)

Alex J. Shaw of New York NY (US)

Eric M. Dodds of Berkeley CA (US)

Benjamin J. Culpepper of Berkeley CA (US)

Kapil Raj Thadani of New York NY (US)

Lakshmi V. Kesiraju of San Jose CA (US)

Praveen Mareedu of Jersey City NJ (US)

Sanika Shirwadkar of Milpitas CA (US)

Xingyue Zhou of Mountain View CA (US)

Yueh-Ning Ku of Sunnyvale CA (US)

SYSTEM AND METHOD FOR GENERATING VIDEO IN TARGET LANGUAGE - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240038271 titled 'SYSTEM AND METHOD FOR GENERATING VIDEO IN TARGET LANGUAGE

Simplified Explanation

The patent application describes a method and system for generating a video in a target language. Here is a simplified explanation of the abstract:

• The system identifies a first video where a speaker speaks in a first language.
• It determines a translated transcript in a second language that represents the translation of the speech in the first video.
• Using a speaker profile associated with a second speaker, the system generates first audio that includes an auditory representation of the translated transcript spoken in the voice of the second speaker.
• Based on the first video and the first audio, the system generates a second video where the mouth movements of the first speaker are aligned with the speech of the auditory representation in the first audio.

Potential applications of this technology:

• Language learning: The system can be used to generate videos where speakers in different languages are aligned, helping learners practice listening and speaking skills.
• Dubbing and localization: The technology can be used to create localized versions of videos by aligning the translated audio with the original video.
• Accessibility: The system can assist individuals with hearing impairments by generating videos with aligned captions and translated audio.

Problems solved by this technology:

• Language barrier: The system helps overcome language barriers by providing translated audio and aligned videos, allowing communication and understanding across different languages.
• Time and cost efficiency: The technology automates the process of generating translated videos, reducing the time and cost associated with manual translation and dubbing.

Benefits of this technology:

• Enhanced language learning: Learners can practice listening and speaking skills by watching videos with aligned translations.
• Improved accessibility: Individuals with hearing impairments can access videos with aligned captions and translated audio.
• Efficient localization: Content creators can easily generate localized versions of videos by aligning translated audio with the original video.

Original Abstract Submitted

one or more computing devices, systems, and/or methods for generating a video in a target language are provided. in an example, a first video, in which a first speaker speaks in a first language, is identified. a translated transcript in a second language is determined. the translated transcript is indicative of a translation of speech spoken by the first speaker in the first video. based upon the translated transcript and a speaker profile associated with a second speaker, first audio, including an auditory representation of the translated transcript being spoken in a voice of the second speaker, is generated. based upon the first video and the first audio, a second video, in which mouth movements of the first speaker are aligned with speech of the auditory representation of the first audio, is generated.