Abstract: A plurality of attribute scores are calculated for data including audio based on a plurality of acoustic attributes. Each of the attribute scores relate to a detection of one of the acoustic attributes in the data including audio. A suitability score is output based on the plurality of attribute scores. The suitability score relates to an accuracy of a speech recognition system to transcribe the data including audio.

Abstract: Examples disclosed herein involve obfuscating training data. An example method includes computing a sequence of acoustic features from audio data of training data, the training data comprising the audio data and a corresponding text transcript; mapping the acoustic features to acoustic model states to generate annotated feature vectors, the annotated feature vectors comprising the acoustic features and corresponding context from the text transcript; and providing a randomized sequence of the annotated feature vectors as obfuscated training data to an audio analysis system.

Abstract: Techniques associated with identifying stories in media content are described in various implementations. In one example implementation, a method may include receiving media content, and segmenting the media content into a plurality of media segments based on auditory indicators included in the media content. The method may also include analyzing a first media segment to determine a first set of concepts associated with the first media segment, and analyzing a second media segment to determine a second set of concepts associated with the second media segment. The method may further include comparing the first set of concepts to the second set of concepts to determine a conceptual similarity between the first set of concepts and the second set of concepts, and in response to the conceptual similarity exceeding a similarity threshold, identifying a story that includes the first media segment and the second media segment.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for expiration of social media posts. An example method includes analyzing a social media post on a social media profile, determining a characteristic of the social media post, and setting an expiration time at which the social media post is to be removed from the social network interface based on the characteristic.

Abstract: Techniques associated with identifying stories in media content are described in various implementations. In one example implementation, a method may include receiving media content, and segmenting the media content into a plurality of media segments based on auditory indicators included in the media content. The method may also include analyzing a first media segment to determine a first set of concepts associated with the first media segment, and analyzing a second media segment to determine a second set of concepts associated with the second media segment. The method may further include comparing the first set of concepts to the second set of concepts to determine a conceptual similarity between the first set of concepts and the second set of concepts, and in response to the conceptual similarity exceeding a similarity threshold, identifying a story that includes the first media segment and the second media segment.