Patent information
IP India · live recordAbstract
Disclosed subject matter relates to digital media including a method and system for generating a contextual audio related to an image. An audio generating system may determine scene-theme and viewer theme of scene in the image. Further, audio files matching scene-objects and the contextual data may be retrieved in real-time and relevant audio files from audio files may be identified based on relationship between scene-theme, scene-objects, viewer theme, contextual data and metadata of audio files. A contribution weightage may be assigned to the relevant and substitute audio files based on contextual data and may be correlated based on contribution weightage, thereby generating the contextual audio related to the image. The present disclosure provides a feature wherein the contextual audio generated for an image may provide a holistic audio effect in accordance with context of the image, thus recreating the audio that might have been present when the image was captured. FIG.2
Applicants
1Inventors
4Claims
16Specification
Show full textCollapse
Claims:We claim: 1. A method of generating a contextual audio related to an image, the method comprising: determining, by an audio generating system (107), scene-theme of a scene in the image by analysing the image received from an image repository (103), wherein the scene-theme is determined based on key image features in the image and one or more scene-objects, corresponding to the key image features, in the image; determining, by the audio generating system (107), a viewer theme of the image based on contextual data (213) associated with the image; retrieving, by the audio generating system (107), one or more audio files matching the one or more scene-objects and the contextual data (213) in real-time by performing a real-time search using textual descriptions of the one or more scene-objects and the contextual data (213); identifying, by the audio generating system (107), one or more relevant audio files from the one or more audio files based on relationship between the scene-theme, the one or more scene-objects, the viewer theme, the contextual data (213) and metadata of the one or more audio files; assigning, by the audio generating system (107), a contribution weightage to each of the one or more relevant audio files and one or more substitute audio files based on the contextual data (213); and correlating, by the audio generating system (107), the one or more relevant audio files and the one or more substitute audio files based on the contribution weightage, thereby generating the contextual audio related to the image. 2. The method as claimed in claim 1, wherein the one or more scene-objects comprises information related to at least one of objects present in the scene, actions of the objects present in the scene and background of the objects present in the scene.
3. The method as claimed in claim 1, wherein the contextual data (213) comprises at least one of location, date, time and weather condition when the image is viewed, user profile data from social networking websites, user preferences and user inputs. 4. The method as claimed in claim 1, wherein the one or more substitute audio files are generated by the audio generating system (107) in real-time for the one or more relevant audio files when the metadata of the one or more audio files matches with metadata of the one or more relevant audio files.
5. The method as claimed in claim 1, wherein the one or more substitute audio files are generated to provide additional sound effects related to one or more unseen objects in the scene, wherein the one or more unseen objects are related to the scene.
6. The method as claimed in claim 1, wherein the contribution weightage is assigned based on level of contribution of each of the one or more relevant audio files and the one or more substitute audio files required for generating the contextual audio.
7. The method as claimed in claim 1 further comprises playing, by the audio generating system (107), the corresponding contextual audio when the image is viewed.
8. The method as claimed in claim 1 further comprises logging, by the audio generating system (107), the one or more relevant audio files and the one or more substitute audio files for self-learning of the audio generating system (107).
9. An audio generating system (107) for generating a contextual audio related to an image, the audio generating system (107) comprising:
a processor (109); and a memory (113) communicatively coupled to the processor (109), wherein the memory (113) stores the processor-executable instructions, which, on execution, causes the processor (109) to: determine scene-theme of a scene in the image by analysing the image received from an image repository (103), wherein the scene-theme is determined based on key image features in the image and one or more scene-objects, corresponding to the key image features in the image; determine a viewer theme of the image based on contextual data (213) associated with the image; retrieve one or more audio files matching the one or more scene-objects and the contextual data (213) in real-time by performing a real-time search using textual descriptions of the one or more scene-objects and the contextual data (213); identify one or more relevant audio files from the one or more audio files based on relationship between the scene-theme, the one or more scene-objects, the viewer theme, the contextual data (213) and metadata of the one or more audio files; assign a contribution weightage to each of the one or more relevant audio files and one or more substitute audio files based on the contextual data (213); and correlate the one or more relevant audio files and the one or more substitute audio files based on the contribution weightage, thereby generating the contextual audio related to the image. 10. The audio generating system (107) as claimed in claim 9, wherein the one or more scene-objects comprises information related to at least one of objects present in the scene, actions of the objects present in the scene and background of the objects present in the scene.
11. The audio generating system (107) as claimed in claim 9, wherein the contextual data (213) comprises at least one of location, date, time and weather condition when the image is viewed, user profile data from social networking websites, user preferences and user inputs.
12. The audio generating system (107) as claimed in claim 9, wherein the processor (109) generates the one or more substitute audio files in real-time for the one or more relevant audio files when the metadata of the one or more audio files matches with metadata of the one or more relevant audio files.
13. The audio generating system (107) as claimed in claim 9, wherein the processor (109) generates the one or more substitute audio files to provide additional sound effects related to one or more unseen objects in the scene, wherein the one or more unseen objects are related to the scene. 14. The audio generating system (107) as claimed in claim 9, wherein the processor (109) assigns the contribution weightage based on level of contribution of each of the one or more relevant audio files and the one or more substitute audio files required for generating the contextual audio.
15. The audio generating system (107) as claimed in claim 9, wherein the processor (109) is further configured to play the corresponding contextual audio when the image is viewed.
16. The audio generating system (107) as claimed in claim 9 self-learns by logging the one or more relevant audio files and the one or more substitute audio files.
Dated this 30th day of June 2017
SWETHA S N OF K & S PARTNERS AGENT FOR THE APPLICANT , Description:TECHNICAL FIELD The present subject matter relates generally to digital media, and more particularly, but not exclusively to a method and a system for generating a contextual audio related to an image.