Speaker identification and unsupervised speaker adaptation techniques

  • US 10,127,911 B2
  • Filed: 08/25/2015
  • Issued: 11/13/2018
  • Est. Priority Date: 09/30/2014
  • Status: Active Grant
  • ×
    • Pin Icon | RPX Insight
    • Pin
First Claim
Patent Images

1. A method for operating a virtual assistant, the method comprising:

  • at an electronic device;

    receiving, at the electronic device, an audio input comprising user speech, wherein the audio input is associated with a contextual data;

    determining whether the user speech contains one or more predetermined words;

    in response to determining that the user speech contains one or more predetermined words;

    determining whether a speaker of the user speech is a predetermined user based at least in part on a speaker profile for the predetermined user; and

    in accordance with a determination that the speaker of the user speech is the predetermined user, adding the audio input comprising user speech to the speaker profile for the predetermined user, wherein adding the audio input comprising user speech to the speaker profile includes annotating the audio input in the speaker profile with the contextual data;

    receiving a second audio input comprising a second user speech;

    determining whether a second contextual data associated with the second audio input matches the contextual data;

    in accordance with a determination that the second contextual data associated with the second audio input matches the contextual data;

    determining whether a speaker of the second user speech is the predetermined user based at least in part on the audio input added to the speaker profile; and

    in accordance with a determination that the speaker of the second user speech is the predetermined user, activating the virtual assistant and processing a spoken command received subsequent to the second user speech.

View all claims