Abstract: Systems, methods, and computer-readable storage media are provided for recognizing emotion in audio signals in real-time. An audio signal is detected and a rapid audio fingerprint is computed on a user's computing device. One or more features is extracted from the audio fingerprint and compared with features associated with defined emotions to determine relative degrees of similarity. Confidence scores are computed for the defined emotions based on the relative degrees of similarity and it is determined whether a confidence score for one or more particular emotions exceeds a threshold confidence score. If it is determined that a threshold confidence score for one or more particular emotions is exceeded, the particular emotion or emotions are associated with the audio signal. As desired, various action then may be initiated based upon the emotion/emotions associated with the audio signal.

Abstract: Devices are often configurable to perform actions automatically in response to a condition, such as an alarm presented at a time or date of a meeting; a message associated with a location specified by a geofence; or an automated response to a received message. Such conditions may be tangentially applied to actions involving an individual (e.g., a reminder presented during an anticipated meeting or a geofence associated with the individual's office), but may result in false positives when the individual is not actually present, and false negatives when an unanticipated presence of the individual arises. Instead, a device may be configured to detect the presence of the individual with the user (e.g., capturing a photo of the environment of the user, and identifying the face of the individual in the photo), and to perform an action for the user during the detected presence of the individual with the user.