Back to results
US 11,887,598 B2Granted
Voice verification for media playback
AssigneeSonos, Inc.
InventorConnor Kristopher Smith
Life of this patent
Estimating the term…
Abstract
In one aspect, a network microphone device includes a plurality of microphones and is configured to capture a voice input via the one or more microphones, detect a wake word in the voice input, transmit data associated with the voice input to one or more remote computing devices associated with a voice assistant service, and receive a response from the one or more remote computing devices, the response comprising a playback command based on the voice input. The network microphone device may be configured to obtain verification information characterizing the voice input and, based on the verification information indicating that the voice input was spoken by an unverified user, functionally disable the NMD from performing the playback command.
Claims20
A network microphone device (NMD) comprising:
- one or more processors;
- one or more microphones;
- and
- a tangible, non-transitory, computer-readable medium storing instructions executable by the one or more processors to cause the NMD to perform operations comprising:
- capturing a first voice input via the one or more microphones;
- analyzing at least a portion of the first voice input to detect a first wake word;
- based on the analyzed first voice input, detecting the first wake word;
- after detecting the first wake word, transmitting first data associated with the first voice input to one or more remote computing devices associated with a voice assistant service (VAS);
- in parallel with transmitting the first data, deriving, at the NMD, first verification information characterizing the first voice input;
- after transmitting the first data, receiving a first response from the one or more remote computing devices, the first response comprising a first playback command;
- after receiving the first response, and based on the first verification information indicating that the first voice input was spoken by a verified user, performing the first playback command via the NMD;
- capturing a second voice input via the one or more microphones;
- analyzing, via the NMD, at least a portion of the second voice input to detect a second wake word;
- based on the analyzed second voice input, detecting the second wake word;
- after detecting the second wake word, transmitting second data associated with the second voice input to one or more remote computing devices associated with a voice assistant service (VAS);
- in parallel with transmitting the second data, deriving, at the NMD, second verification information characterizing the second voice input;
- after transmitting the second data, receiving a second response from the one or more remote computing devices, the second response comprising a second playback command;
- and
- after receiving the second response, and based on the second verification information indicating that the second voice input was spoken by an unverified user, functionally disabling the NMD from performing the second playback command.
16 more elements
A method comprising:
- capturing a first voice input via one or more microphones of a network microphone device (NMD);
- analyzing, via the NMD, at least a portion of the first voice input to detect a first wake word;
- based on the analyzed first voice input, detecting the first wake word;
- after detecting the first wake word, transmitting first data associated with the first voice input to one or more remote computing devices associated with a voice assistant service (VAS);
- in parallel with transmitting the first data, deriving, at the NMD, first verification information characterizing the first voice input;
- after transmitting the first data, receiving a first response from the one or more remote computing devices, the first response comprising a first playback command;
- after receiving the first response, and based on the first verification information indicating that the first voice input was spoken by a verified user, performing the first playback command via the NMD;
- capturing a second voice input via the one or more microphones of the NMD;
- analyzing, via the NMD, at least a portion of the second voice input to detect a second wake word;
- based on the analyzed second voice input, detecting the second wake word;
- after detecting the second wake word, transmitting second data associated with the second voice input to one or more remote computing devices associated with a voice assistant service (VAS);
- in parallel with transmitting the second data, deriving, at the NMD, second verification information characterizing the second voice input;
- after transmitting the second data, receiving a second response from the one or more remote computing devices, the second response comprising a second playback command;
- and
- after receiving the second response, and based on the second verification information indicating that the second voice input was spoken by an unverified user, functionally disabling the NMD from performing the second playback command.
12 more elements
A tangible, non-transitory, computer-readable medium storing instructions executable by one or more processors to cause a network microphone device (NMD) to perform operations comprising:
- capturing a first voice input via one or more microphones of the NMD;
- analyzing, via the NMD, at least a portion of the first voice input to detect a first wake word;
- based on the analyzed first voice input, detecting the first wake word;
- after detecting the first wake word, transmitting first data associated with the first voice input to one or more remote computing devices associated with a voice assistant service (VAS);
- in parallel with transmitting the first data, deriving, at the NMD, first verification information characterizing the first voice input;
- after transmitting the first data, receiving a first response from the one or more remote computing devices, the first response comprising a first playback command;
- after receiving the first response, and based on the first verification information indicating that the first voice input was spoken by a verified user, performing the first playback command via the NMD;
- capturing a second voice input via the one or more microphones;
- analyzing, via the NMD, at least a portion of the second voice input to detect a second wake word;
- based on the analyzed second voice input, detecting the second wake word;
- after detecting the second wake word, transmitting second data associated with the second voice input to one or more remote computing devices associated with a voice assistant service (VAS);
- in parallel with transmitting the second data, deriving, at the NMD, second verification information characterizing the second voice input;
- after transmitting the second data, receiving a second response from the one or more remote computing devices, the second response comprising a second playback command;
- and
- after receiving the second response, and based on the second verification information indicating that the second voice input was spoken by an unverified user, functionally disabling the NMD from performing the second playback command.
12 more elements
Dependencies are inferred from the claim text.