Automated demographic analysis by analyzing voice activity
AssigneeAT&T Intellectual Property I, L.P.
InventorsMichael Johnston, Hisao M. Chang, Harry E. Blanchard, Bernard S. Renger, Linda Roberts
Life of this patent
Estimating the term…
Abstract
A method of generating demographic information relating to an individual is provided. The method includes monitoring an environment for a voice activity of an individual and detecting the voice activity of the individual. The method further includes analyzing the detected voice activity of the individual and determining, based on the detected voice activity of the individual, a demographic descriptor of the individual.
Claims17
A method of generating demographic information relating to a plurality of individuals, comprising:
- monitoring an environment for a plurality of voice activities;
- detecting the plurality of voice activities, each belonging to one of the plurality of individuals;
- recognizing speech in the plurality of voice activities;
- analyzing, with a processor, the plurality of voice activities of the plurality of individuals;
- determining, with the processor and based on the plurality of voice activities of the plurality of individuals, a demographic descriptor for each of the plurality of individuals;
- correlating, with the processor, the speech in the plurality of voice activities and known information of the environment to determine content descriptors of the plurality of voice activities, the known information of the environment comprising audiovisual content, the content descriptors of the plurality of voice activities relating to the audiovisual content;
- and
- correlating, with the processor, the demographic descriptor of each of the plurality of individuals and the content descriptors of the plurality of voice activities to determine responses to be generated for the plurality of individuals, the responses comprising altering at least a portion of the audiovisual content.
A system for generating demographic information relating to a plurality of individuals, comprising:
- an audio capturer disposed in an environment for detecting a plurality of voice activities, each belonging to one of the plurality of individuals;
- a speech recognizer that recognizes speech in the plurality of voice activities;
- and
- a processor that:
- analyzes the plurality of voice activities of the plurality of individuals to determine, based on the plurality of voice activities of the plurality of individuals, a demographic descriptor for each of the plurality of individuals;
- correlates the speech in the plurality of voice activities and known information of the environment to determine content descriptors of the plurality of voice activities, the known information of the environment comprising audiovisual content, the content descriptors of the plurality of voice activities relating to the audiovisual content;
- and
- correlates the demographic descriptor of each of the plurality of individuals and the content descriptors of the plurality of voice activities to determine responses to be generated for the plurality of individuals, the responses comprising altering at least a portion of the audiovisual content.
A non-transitory computer readable medium for storing a computer program for generating demographic information relating to a plurality of individuals, the non-transitory computer readable medium comprising:
- an executable monitoring code segment that monitors an environment for a plurality of voice activities;
- an executable detecting code segment that detects the plurality of voice activities, each belonging to one of the plurality of individuals;
- an executable recognizing code segment that recognizes speech in the plurality of voice activities;
- an executable analyzing code segment that analyzes the plurality of voice activities of the plurality of individuals;
- an executable determining code segment that determines, based on the plurality of voice activities of the plurality of individuals, a demographic descriptor for each of the plurality of individuals;
- an executable first correlating code segment that correlates the speech in the plurality of voice activities and known information of the environment to determine content descriptors of the plurality of voice activities, the known information of the environment comprising audiovisual content, the content descriptors of the plurality of voice activities relating to the audiovisual content;
- and
- an executable second correlating code segment that correlates the demographic descriptor of each of the plurality of individuals and the content descriptors of the plurality of voice activities to determine responses to be generated for the plurality of individuals, the responses comprising altering at least a portion of the audiovisual content.
Dependencies are inferred from the claim text.