Systems and methods for automated speech-to-text captioning
AssigneeMetal Platforms Technologies, LLC
InventorsAayush Bhutani, Dipro Ray
Life of this patent
Estimating the term…
Abstract
The disclosed systems and methods may include (1) generating a caption for a spoken phrase in a video, (2) determining an accuracy rating for the caption, and (3) in response to determining that the accuracy rating is below an accuracy threshold, prompting a user to manually review the caption prior to publishing the caption. Various other methods, systems, and computer-readable media are also disclosed.
Claims16
A computer-implemented method comprising:
- generating a caption for a spoken phrase in a video;
- determining an accuracy rating for the caption;
- and
- in response to determining that the accuracy rating is below an accuracy threshold, prompting a user to manually review the caption prior to publishing the caption, wherein the accuracy threshold is based on a number of phrases in at least one of the video or a segment of the video corresponding to the spoken phrase, and wherein an accuracy threshold for a video or video segment that includes more than a specified number of phrases is lower than an accuracy threshold for a video or video segment that has fewer than the specified number of phrases.
A system comprising:
- at least one physical processor;
- and
- physical memory comprising computer-executable instructions that, when executed by the physical processor, cause the physical processor to:
- generate a caption for a spoken phrase in a video;
- determine an accuracy rating for the caption;
- and
- in response to determining that the accuracy rating is below an accuracy threshold, prompt a user to manually review the caption prior to publishing the caption, wherein the accuracy threshold is based on a number of phrases in at least one of the video or a segment of the video corresponding to the spoken phrase, and wherein an accuracy threshold for a video or video segment that includes more than a specified number of phrases is lower than an accuracy threshold for a video or video segment that has fewer than the specified number of phrases.
A non-transitory computer-readable medium comprising one or more computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to:
- generate a caption for a spoken phrase in a video;
- determine an accuracy rating for the caption;
- and
- in response to determining that the accuracy rating is below an accuracy threshold, prompt a user to manually review the caption prior to publishing the caption, wherein the accuracy threshold is based on a number of phrases in at least one of the video or a segment of the video corresponding to the spoken phrase, and wherein an accuracy threshold for a video or video segment that includes more than a specified number of phrases is lower than an accuracy threshold for a video or video segment that has fewer than the specified number of phrases.
Dependencies are inferred from the claim text.