False trigger correction for a voice-activated intelligent device
AssigneeHarman International Industries, Incorporated
InventorKevin Hague
Life of this patent
Estimating the term…
Abstract
A method for confirming a trigger in an audio input detected by a voice-activated intelligent device that listens for and detects a trigger in the audio input, confirms whether the trigger in the audio input is intended to wake the device, and if confirmed, the device is instructed to activate. If the trigger cannot be confirmed, the device is instructed to ignore the trigger. The step of confirming whether the trigger is intended to activate the device may include determining whether the audio input is human generated speech, which may also include detecting a fingerprint in the audio input.
Claims18
A method for confirming a trigger for a voice-activated intelligent device, the method carried out on a device having a processing unit, including a non-transitory computer-readable storage medium, capable of executing instructions of a software program, the method comprising the steps of:
- listening for a trigger in an audio input;
- upon hearing the trigger, performing a wake confirmation by detecting a fingerprint in the audio input, performing a wake confirmation further comprises;
- monitoring, in a cloud-based environment, occurrences of a user canceling a command at the voice-activated intelligent device that was the result of a false trigger;
- generating a fingerprint to associate the trigger in the audio input with a false trigger for each occurrence of a user canceling a command that was the result of the false trigger;
- performing a statistical analysis on the generated fingerprints;
- upon identification of a statistically viable quantity of generated fingerprints, generating a final fingerprint that defines the trigger as a false trigger;
- synchronizing the final fingerprint to the voice-activated intelligent device to detect and identify the trigger as false in subsequent audio inputs that contain the trigger;
- and
- upon confirmation that the audio input contains a trigger and a final fingerprint, instructing the voice-activated intelligent device to ignore the audio input.
A method for detecting a false trigger in an audio signal detected by a voice-activated intelligent device, the method carried out on a device having a processing unit, including a non-transitory computer-readable storage medium, capable of executing instructions of a software program, the method comprising the steps of:
- receiving an audio input signal at an audio source;
- prior to broadcasting the audio input signal, performing a wake confirmation in a processing unit associated with the audio source by detecting a false trigger in the audio input, performing a wake confirmation further comprises;
- monitoring, in a cloud-based environment, occurrences of a user canceling a command at the voice-activated intelligent device that was the result of a false trigger;
- generating a fingerprint to associate the trigger in the audio input with a false trigger for each occurrence of a user canceling a command that was the result of the false trigger;
- performing a statistical analysis on the generated fingerprints;
- upon identification of a statistically viable quantity of generated fingerprints, generating a final fingerprint that defines the trigger as a false trigger;
- synchronizing the final fingerprint to the voice-activated intelligent device to detect and identify the trigger as false in subsequent audio inputs that contain the trigger;
- upon detecting a false trigger in the audio input, the audio source communicates a fingerprint to the voice-activated intelligent device;
- detecting the fingerprint at the voice-activated intelligent device;
- and
- ignoring the audio input at the voice-activated intelligent device.
A method for confirming a trigger for a voice-activated intelligent device, the method carried out on a device having a processing unit, including a non-transitory computer-readable storage medium, capable of executing instructions of a software program, the method comprising the steps of:
- listening for an audio input;
- performing distortion analysis of the audio input to determine if the source of the audio input is human generated speech;
- upon determining the source of the audio input is human generated speech, listening for a trigger in the audio input;
- upon determining that the source of the audio input is human generated speech and contains the trigger, activating the voice-activated intelligent device;
- and
- upon determining the source of the audio input is not human generated speech and contains the trigger, ignoring the trigger at the voice-activated intelligent device.
Dependencies are inferred from the claim text.