US 11,989,232 B2
Generating realistic representations of locations by emulating audio for images based on contextual information
Saraswathi Sailaja Perumalla, Visakhapatnam (IN); Shanthan Chamala, Malvern, PA (US); Venkata Vara Prasad Karri, Visakhapatnam (IN); Sairam Telukuntla, Westford, MA (US); and Sarbajit K. Rakshit, Kolkata (IN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Nov. 6, 2020, as Appl. No. 17/090,939.
Prior Publication US 2022/0147563 A1, May 12, 2022
Int. Cl. G06F 16/00 (2019.01); G06F 7/00 (2006.01); G06F 16/638 (2019.01); G06F 16/687 (2019.01); G06T 19/00 (2011.01); H04R 23/00 (2006.01)
CPC G06F 16/687 (2019.01) [G06F 16/638 (2019.01); G06T 19/006 (2013.01); H04R 23/008 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a request to emulate audio for a location having unknown acoustic properties:
in response to receiving the request to emulate audio for a location having unknown acoustic properties, dynamically generating audio for one or more images associated with the location, based on contextual information that satisfies the request;
embedding the generated audio into the one or more images;
emulating audio in a generated user interface that provides a realistic representation of the location using the embedded audio to simulate interactions of generated noises with materials associated with the one more images at different points in time and in varying weather conditions in response to user interactions with the one or more images;
implementing a feedback mechanism that solicits feedback indicating perceived accuracy for the one or more images associated with the emulated audio that simulates interactions of generated noises with materials associated with the one or more images and interactions of users;
receiving solicited feedback indicating a perceived accuracy for the one or more images associated with the emulated audio;
in response to receiving the solicited feedback indicating the perceived accuracy for the one or more images associated with the emulated audio, altering a depiction of the one or more images to increase an accuracy of depictions of the one or more images and corresponding emulated audio;
considering health parameters of a user by altering the location to be within a threshold score for tolerance prior to the user entering the location, based on the health parameters of the user;
generating one or more recommendations that alter the location to be within a threshold score of audio level; and
alerting the user of alternate locations that meet the threshold score for tolerance.