18431829. MULTI-MODE VOICE TRIGGERING FOR AUDIO DEVICES simplified abstract (Apple Inc.)

From WikiPatents
Jump to navigation Jump to search

MULTI-MODE VOICE TRIGGERING FOR AUDIO DEVICES

Organization Name

Apple Inc.

Inventor(s)

Dersheet C. Mehta of Chatsworth CA (US)

Dinesh Garg of San Jose CA (US)

Sham A. Koli of San Jose CA (US)

Kerry J. Kopp of Los Altos Hills CA (US)

Hans Bernhard of Los Angeles CA (US)

MULTI-MODE VOICE TRIGGERING FOR AUDIO DEVICES - A simplified explanation of the abstract

This abstract first appeared for US patent application 18431829 titled 'MULTI-MODE VOICE TRIGGERING FOR AUDIO DEVICES

Simplified Explanation

Implementations of the subject technology provide systems and methods for multi-mode voice triggering for audio devices. An audio device may store multiple voice recognition models, each trained to detect a single corresponding trigger phrase. So that the audio device can detect a specific one of the multiple trigger phrases without consuming the processing and/or power resources to run a voice recognition model that can differentiate between different trigger phrases, the audio device pre-loads a selected one of the voice recognition models for an expected trigger phrase into a processor of the audio device. The audio device may select the one of the voice recognition models for the expected trigger phrase based on a type of a companion device that is communicatively coupled to the audio device.

  • Audio devices have multiple voice recognition models stored.
  • Each model is trained to detect a single trigger phrase.
  • Pre-loading a selected model saves processing and power resources.
  • The selected model is based on the type of companion device connected.

Potential Applications

This technology could be applied in:

  • Smart home devices
  • Automotive systems
  • Wearable technology

Problems Solved

This technology helps in:

  • Efficient voice triggering
  • Saving processing power
  • Enhancing user experience

Benefits

The benefits of this technology include:

  • Faster response times
  • Reduced power consumption
  • Customizable trigger phrases

Potential Commercial Applications

A potential commercial application for this technology could be in:

  • Smart speakers and home assistants

Possible Prior Art

One possible prior art for this technology could be:

  • Voice recognition systems in smartphones

Unanswered Questions

How does the technology handle background noise during voice triggering?

The technology's ability to filter out background noise and accurately detect trigger phrases in noisy environments is not addressed in the abstract.

Can the audio device learn new trigger phrases over time?

Whether the audio device has the capability to learn and adapt to new trigger phrases beyond the pre-loaded models is not mentioned in the abstract.


Original Abstract Submitted

Implementations of the subject technology provide systems and methods for multi-mode voice triggering for audio devices. An audio device may store multiple voice recognition models, each trained to detect a single corresponding trigger phrase. So that the audio device can detect a specific one of the multiple trigger phrases without consuming the processing and/or power resources to run a voice recognition model that can differentiate between different trigger phrases, the audio device pre-loads a selected one of the voice recognition models for an expected trigger phrase into a processor of the audio device. The audio device may select the one of the voice recognition models for the expected trigger phrase based on a type of a companion device that is communicatively coupled to the audio device.