Patent · US Active

Method and system for mitigating unwanted audio noise in a voice assistant-based communication environment

US12367893B2 · kind B2 · utility

0Cited by
10References
12Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 19, 2022
Grant dateJul 22, 2025
Priority date
Expiry dateMay 4, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L2021/02082
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method for mitigating unwanted audio noise in internet of things (IoT) based communication environment is provided. The method includes identifying and pairing one or more IoT devices with a voice assistant device, and then dividing the one or more paired IoT devices into a plurality of clusters. The method further includes detecting a user's location with respect to a location of the voice assistant device and then determining a cluster among the plurality of clusters corresponding to the user's location based on the detected user's location and thereafter using a recurrent neural networks (RNN) model, predicting an optimal sound output of the voice assistance device that is audible at the detected user's location. The method furthermore includes correcting the predicted optimal sound output of the voice assistance device using a sound parameter value associated with the determined cluster and a phase shift of the predicted optimal sound output.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.