Emotion recognition system
AssigneeUniversity of Southern California
InventorShrikanth S. Narayanan
Life of this patent
Estimating the term…
Abstract
An emotion recognition system for assessing human emotional behavior from communication by a speaker includes a processing system configured to receive signals representative of the verbal and/or non-verbal communication. The processing system derives signal features from the received signals. The processing system is further configured to implement at least one intermediate mapping between the signal features and one or more elements of an emotional ontology in order to perform an emotion recognition decision. The emotional ontology provides a gradient representation of the human emotional behavior.
Claims19
An emotion recognition system for automatically assessing human emotional behavior from physical phenomena indicative of the human emotional behavior, the system comprising:
- one or more a sensors configured to sense, the physical phenomena;
- and
- a computer processing system configured to:
- receive a time series of signals from the one or more sensors;
- identify features, in the time series of signals that are indicative of the human emotional behavior;
- and
- output a gradient, multiple-perspective assessment of the human, emotional behavior based on the identified features that includes a gradient representation of each of multiple emotional states indicated by the human emotional behavior.
A method of automatically assessing human emotional behavior from physical phenomena indicative of the human emotional behavior, the method comprising:
- sensing the physical phenomena using one or more sensors;
- receiving a time series of signals from the one or more sensors using a computer processing system;
- identifying features in, the time series of signals that are indicative of the human emotional behavior using a computer processing system;
- and
- outputting a gradient, multiple-perspective assessment of the human emotional behavior based on the identified features that includes a gradient representation of each of multiple emotional states indicated by the emotional behavior using a computer processing system.
Dependencies are inferred from the claim text.