# US 10,504,554 B2 · Information processing device, information processing system, and information processing method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,504,554 B2 - Document ID: US10504554B2 - Status: Granted - Kind: B2 - Application number: 15/544,128 - Filed: 2015-11-12 - Published: 2018-09-20 - Granted: 2019-12-10 - Earliest claimed: 2015-02-03 - Assignees: Sony Corporation - Applicants: Sony Corporation - Inventors: Naoya Takahashi - Web page: https://patentgrep.com/patent/US10504554B2 ## CPC - G11B 27/005: {Reproducing at a different information rate from the information rate of recording (for television signals H04N5/783)} - G11B 27/031: Electronic editing of digitised analogue information signals, e.g. audio or video signals - H04N 5/783: Adaptations for reproducing at a rate different from the recording rate - H04N 9/802: involving processing of the sound signal (H04N9/806, H04N9/835 take precedence) - H04N 21/439: Processing of audio elementary streams - H04N 21/8549: Creating video summaries, e.g. movie trailer {(retrieval in video databases by using presentations in form of a video summary G06F16/739)} - G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R) - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract An information processing device including a video generation unit that generates a fast reproduction video from a video part of an input moving image, a sound generation unit that generates a shortened sound using a portion of a sound part of the moving image, and a synthesizing unit that synthesizes the fast reproduction video generated by the video generation unit and the shortened sound generated by the sound generation unit and generate a fast reproduction moving image. ## Claims ### Claim 1 An information processing device, comprising: a central processing unit (CPU) configured to: generate a fast reproduction video from a video part of a moving image; extract a plurality of sound segments from a portion of a sound part of the moving image; dispose the plurality of sound segments at a position corresponding to the fast reproduction video; connect a first sound segment of the plurality of sound segments and a second sound segment of the plurality of sound segments in an overlapping manner; generate a shortened sound based on the connection of the first sound segment and the second sound segment; and synthesize the generated fast reproduction video and the generated shortened sound to generate a fast reproduction moving image. ### Claim 2 (depends on 1) The information processing device according to claim 1, wherein the CPU is further configured to dispose a reproduction start position of a third sound segment of the plurality of sound segments at a position of the fast reproduction video corresponding to a starting point of the third sound segment. ### Claim 3 (depends on 1) The information processing device according to claim 1, wherein the CPU is further configured to: divide the sound part of the moving image into sections of respective scenes of the moving image, and extract at least one sound segment of the plurality of sound segments from each of the sections of the respective scenes. ### Claim 4 (depends on 3) The information processing device according to claim 3, wherein the CPU is further configured to dispose the extracted at least one sound segment at positions of the fast reproduction video corresponding to scenes of the moving image to which the extracted at least one sound segment belongs. ### Claim 5 (depends on 1) The information processing device according to claim 1, wherein the CPU is further configured to: divide the sound part of the moving image into an utterance section and a non-utterance section, and connect the first sound segment and the second sound segment that are extracted from the non-utterance section. ### Claim 6 (depends on 5) The information processing device according to claim 5, wherein the CPU is further configured to overlap an event sound on the connected first sound segment and the connected second sound segment. ### Claim 7 (depends on 1) The information processing device according to claim 1, wherein the CPU is further configured to apply cross-fade to overlapping parts of the first sound segment and the second sound segment. ### Claim 8 (depends on 1) The information processing device according to claim 1, wherein the CPU is further configured to generate the shortened sound based on a video analysis result of the video part of the moving image. ### Claim 9 (depends on 8) The information processing device according to claim 8, wherein the CPU is further configured to dispose the plurality of sound segments at positions at which a time-series change of volume of the plurality of sound segments matches a time-series change of a subject appearing in the fast reproduction video. ### Claim 10 (depends on 1) The information processing device according to claim 1, wherein the CPU is further configured to control a reproduction speed of the fast reproduction video based on a sound analysis result of the sound part of the moving image. ### Claim 11 An information processing system, comprising: a central processing unit (CPU) configured to: generate a fast reproduction video from a video part of a moving image; extract a plurality of sound segments from a portion of a sound part of the moving image; dispose the plurality of sound segments at a position corresponding to the fast reproduction video; connect a first sound segment of the plurality of sound segments and a second sound segment of the plurality of sound segments in an overlapping manner; generate a shortened sound based on the connection of the first sound segment and the second sound segment; and synthesize the generated fast reproduction video and the generated shortened sound to generate a fast reproduction moving image. ### Claim 12 An information processing method, comprising: in an information processing device comprising a central processing unit (CPU): generating, by the CPU, a fast reproduction video from a video part of a moving image; extracting, by the CPU, a plurality of sound segments from a portion of a sound part of the moving image; disposing, by the CPU, the plurality of sound segments at a position corresponding to the fast reproduction video; connecting, by the CPU, a first sound segment of the plurality of sound segments and a second sound segment of the plurality of sound segments in an overlapping manner; generating, by the CPU, a shortened sound based on the connection of the first sound segment and the second sound segment; and synthesizing, by the CPU, the generated fast reproduction video and the shortened sound for generating a fast reproduction moving image. ### Claim 13 A non-transitory computer-readable medium having stored thereon computer-executable instructions which, when executed by an information processing device, cause the information processing device to execute operations, the operations comprising: generating a fast reproduction video from a video part of a moving image; extracting a plurality of sound segments from a portion of a sound part of the moving image; disposing the plurality of sound segments at a position corresponding to the fast reproduction video; connecting a first sound segment of the plurality of sound segments and a second sound segment of the plurality of sound segments in an overlapping manner; generating a shortened sound based on the connection of the first sound segment and the second sound segment; and synthesizing the generated fast reproduction video and the generated shortened sound to generate a fast reproduction moving image.