Voice-Based Video Tagging

A system for identifying an event of interest in a video, the system comprising:

• one or more processors configured by instructions to:
• access a captured speech pattern, the captured speech pattern captured from a user at a moment during capture of the video;
• match the captured speech pattern to a given stored speech pattern of multiple stored speech patterns, the multiple stored speech patterns corresponding to a command for identifying the event of interest within the video, individual ones of the multiple stored speech patterns stored based on a number of times the individual ones of the multiple stored speech patterns are captured by the camera from a user while the camera is operating in a training mode, wherein the individual ones of the multiple stored speech patterns correspond to an identification of the event of interest as occurring before, during, or after the moment;
• and
• in response a match of the captured speech pattern to the given stored speech pattern, store event of interest information associated with the video, the event of interest information identifying an event moment during the capture of the video at which the event of interest occurs, the event moment being determined to occur before, during, or after the moment based on the matching of the captured speech pattern to the given stored speech pattern.

A non-transitory computer-readable storage medium storing instructions for identifying an event of interest in a video, the instructions, when executed, causing one or more processors to:

• access a captured speech pattern, the captured speech pattern captured from a user at a moment during capture of the video;
• match the captured speech pattern to a given stored speech pattern of multiple stored speech patterns, the multiple stored speech patterns corresponding to a command for identifying the event of interest within the video, individual ones of the multiple stored speech patterns stored based on a number of times the individual ones of the multiple stored speech patterns are captured by the camera from a user while the camera is operating in a training mode, wherein the individual ones of the multiple stored speech patterns correspond to an identification of the event of interest as occurring before, during, or after the moment;
• and
• in response a match of the captured speech pattern to the given stored speech pattern, store event of interest information associated with the video, the event of interest information identifying an event moment during the capture of the video at which the event of interest occurs, the event moment being determined to occur before, during, or after the moment based on the matching of the captured speech pattern to the given stored speech pattern.