×

Method and apparatus for automatically determining speaker characteristics for speech-directed advertising or other enhancement of speech-controlled devices or services

  • US 8,793,127 B2
  • Filed: 10/31/2007
  • Issued: 07/29/2014
  • Est. Priority Date: 10/31/2002
  • Status: Expired due to Term
First Claim
Patent Images

1. An apparatus for automatically determining desired speaker characteristics, configured to operate in an application mode or a learning mode or in both an application mode and a learning mode, comprising:

  • a speech input device comprising a mobile device having an input and output, wherein said input comprises a means for receiving speech inputs in the form of one or more utterances and for receiving non-speech inputs, wherein said mobile device is configured for transmitting and receiving data over a network;

    a primary information extraction module for receiving one or more utterances from said speech input device, said primary information extraction module comprising an automatic speech recognition module for collecting primary information in the form of;

    transcribed text, symbolic representation of associated meaning, or a combination of transcribed text and symbolic representation of associated meaning;

    a secondary information extraction module for receiving utterances from said speech input device, said secondary information extraction module comprising an automatic speech characteristics module that estimates or extracts secondary information comprising explicit or implicit speech indicators of interest, corresponding to desired speaker characteristics; and

    a controlled system for using primary and secondary information extracted by said automatic speech recognition system module and said automatic speech characteristics module to produce a system action or response as a system output;

    a learning module configured to record both secondary information and user behavior, said learning module configured to analyze said information to determine any of economically valuable relationships between speech and behavior, and economically valuable relationships between speech and speaker'"'"'s personal characteristics, wherein said economically valuable relationships indicate any of a high propensity to purchase and a high socioeconomic status;

    said learning module analyzing either said secondary information and user behavior or said secondary information and speaker personal characteristics, for the discovery of relations between said secondary information and user behavior or said secondary information and speaker personal characteristics, by application of any of;

    multivariate correlation analysis and linear regression;

    mutual information statistics;

    clustering and decision trees; and

    perceptrons, neural networks, support vector machines, and linear classifiers;

    wherein, during said application mode, said controlled system presents one or more advertisements to said user in addition to producing said system action, wherein the content of said advertisement is based on factors selected from among a group of factors consisting of;

    primary information;

    secondary information; and

    a combination of primary information and secondary information;

    wherein, during said learning mode, learning results from a series of queries or interactions, including at least some conducted by speech, followed by user behavior.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×