A feature correction system is used to remove undesirable audio and video features from a media stream. The system determines an undesirable audio feature in the media stream by detecting a region that is relatively silent or has a predetermined speech disfluency, e.g., umms, y’knows, or ahhs. Further, the system establishes a start time and an end time for the undesirable audio feature. The system then detects video frames in the media stream that include the undesirable audio feature. The system finally performs feature correction for the undesirable audio feature and/or the video frames according to one or more predetermined techniques, e.g., muting the undesirable audio feature and/or compressing related video frames.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Macpherson, Luke, "REMOVING UNDESIRABLE AUDIO FEATURES FROM A MEDIA STREAM", Technical Disclosure Commons, (November 23, 2016)