Representation of Attentiveness in Multimodal Smart Audio Device Systems

The system uses multiple microphones to estimate user location and generate spatially varying attentiveness signals, addressing the challenge of inconsistent device selection in multi-device environments by ensuring the most relevant device responds, enhancing user interaction and coherence.

JP7591033B2Active Publication Date: 2024-11-27DOLBY LABORATORIES LICENSING CORP
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2022506122
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-04-01
Filing Date
2020-07-30
Publication Date
2024-11-27
Estimated Expiration
2040-07-30

AI Technical Summary

Technical Problem

Existing systems for controlling smart audio devices lack efficient methods to determine user location and attention within an environment, leading to inconsistent and unnatural interactions, particularly in multi-device setups where noise, echo, and varying user positions complicate the selection of the appropriate device for response.

Method used

A system that utilizes multiple microphones to estimate user location and generate spatially varying attentiveness signals, adjusting device behavior based on relevance metrics such as distance and wake word confidence, allowing coordinated response from multiple smart audio devices.

Benefits of technology

Enhances user interaction by ensuring the most relevant device responds, providing a more natural and cohesive system behavior that adapts to user movement and noise, improving the responsiveness and coherence of multi-device environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007591033000014
    Figure 0007591033000014
  • Figure 0007591033000015
    Figure 0007591033000015
  • Figure 0007591033000016
    Figure 0007591033000016
Patent Text Reader

Abstract

The method may include receiving an output signal from each microphone of a plurality of microphones in an environment, each of the plurality of microphones being at a microphone location in the environment, the output signal corresponding to a human vocalization. The method may include determining a zone in the environment having at least a threshold probability of containing the location of the human based at least in part on the output signal, and generating a plurality of spatially-varying attentiveness signals within the zone. Each attentiveness signal may be generated by a device located within the zone. Each attentiveness signal may indicate that the corresponding device is in an operational mode awaiting a command and may indicate a relevance metric of the corresponding device.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • LED Design Language for Visual Affordance of Voice User Interfaces

    US20170330429A1

  • Voice input processing method and electronic device for supporting the same

    US20180211665A1

  • Systems and Methods of Receiving Voice Input

    US20190179611A1