18242860. METHODS AND DEVICES FOR SELECTIVELY IGNORING CAPTURED AUDIO DATA simplified abstract (Amazon Technologies, Inc.)

From WikiPatents
Jump to navigation Jump to search

METHODS AND DEVICES FOR SELECTIVELY IGNORING CAPTURED AUDIO DATA

Organization Name

Amazon Technologies, Inc.

Inventor(s)

James David Meyers of San Jose CA (US)

Kurt Wesley Piersol of San Jose CA (US)

METHODS AND DEVICES FOR SELECTIVELY IGNORING CAPTURED AUDIO DATA - A simplified explanation of the abstract

This abstract first appeared for US patent application 18242860 titled 'METHODS AND DEVICES FOR SELECTIVELY IGNORING CAPTURED AUDIO DATA

Simplified Explanation

The patent application describes systems and methods for selectively ignoring an occurrence of a wakeword within audio input data. Here are some key points to explain the innovation:

  • Detection of a wakeword uttered by an individual within a modified time window.
  • Accounting for hardware delays and echoing offsets in detecting the wakeword.
  • The detected wakeword may correspond to a word in the audio output of a voice-activated electronic device.
  • Selective determination of when to ignore the wakeword based on the occurrence within the outputted audio.
      1. Potential Applications

This technology could be applied in voice-activated electronic devices such as smart speakers, virtual assistants, and other devices that respond to voice commands.

      1. Problems Solved

This technology helps prevent accidental activations of voice-activated devices by selectively ignoring occurrences of the wakeword within the audio input data.

      1. Benefits

- Improved user experience by reducing unintended activations of voice-activated devices. - Enhanced privacy by preventing devices from activating at unwanted times. - Increased efficiency by accurately detecting and responding to voice commands.

      1. Potential Commercial Applications

This technology could be valuable for companies developing voice-activated products, smart home devices, and other applications where voice recognition is essential.

      1. Possible Prior Art

One potential prior art could be existing voice recognition systems that may not have the capability to selectively ignore occurrences of a wakeword within audio input data.

        1. Unanswered Questions
        2. How does this technology differentiate between intentional and unintentional utterances of the wakeword?

This information is not explicitly provided in the abstract, but the system may use contextual cues or user behavior patterns to make this determination.

        1. What measures are in place to ensure the accuracy and reliability of ignoring the wakeword in the audio input data?

The abstract does not detail specific measures, but the system may incorporate machine learning algorithms or user feedback mechanisms to improve accuracy over time.


Original Abstract Submitted

Systems and methods for selectively ignoring an occurrence of a wakeword within audio input data is provided herein. In some embodiments, a wakeword may be detected to have been uttered by an individual within a modified time window, which may account for hardware delays and echoing offsets. The detected wakeword that occurs during this modified time window may, in some embodiments, correspond to a word included within audio that is outputted by a voice activated electronic device. This may cause the voice activated electronic device to activate itself, stopping the audio from being outputted. By identifying when these occurrences of the wakeword within outputted audio are going to happen, the voice activated electronic device may selectively determine when to ignore the wakeword, and furthermore, when not to ignore the wakeword.

Retrieved from "http://wikipatents.org/index.php?title=18242860._METHODS_AND_DEVICES_FOR_SELECTIVELY_IGNORING_CAPTURED_AUDIO_DATA_simplified_abstract_(Amazon_Technologies,_Inc.)&oldid=52455"