Audio Output Synchronization for Voice Recognition Interference

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Voice recognition systems face degradation due to interference from nearby audio sources, such as televisions, and local audio outputs, which can hinder the accurate processing of voice commands if the interference signals are not synchronized and cancelled effectively.

Innovation Solution

Implementing a method to synchronize interference signals from local and remote audio sources by delaying the output of local audio to align it with the audio input, allowing for simultaneous capture and cancellation of these signals, thereby improving the accuracy of voice command processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If local audio output is used for voice recognition feedback, then user experience is improved, but interference with voice command capture deteriorates

Engineering Contradiction:
Improveuser experienceVSAvoidinterference with voice command capture
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary synchronization by delaying the local audio output signal to match the timing of remote audio signals before they are captured by the microphone. This preliminary alignment ensures that when the audio signals are played through local speakers, they arrive at the microphone at the same time as remote audio, enabling effective cancellation without degrading voice command capture quality

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system converts the harmful local audio interference into a beneficial cancellation opportunity by capturing the local audio signal, synchronizing it with remote audio timing, and using it as a reference signal to actively cancel both local and remote audio interference from the voice command capture channel

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

2Object-generated harmful factors

If audio signals are cancelled without synchronization, then noise cancellation is attempted, but cancellation accuracy deteriorates

Engineering Contradiction:
Improvenoise cancellationVSAvoidcancellation accuracy
Core Design Contradiction:
Object-generated harmful factorsVSMeasurement precision

Solution Approach 1:

The system performs preliminary timing alignment by delaying the local audio output signal to synchronize with remote audio signals before cancellation processing. This ensures that all audio interference signals (local and remote) are time-aligned when captured by the microphone, allowing the cancellation algorithm to effectively subtract them from the voice command signal with high accuracy

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses feedback by capturing the local audio output signal, synchronizing it with remote audio timing, and using this synchronized signal as a reference for the cancellation algorithm. The cancellation system continuously adjusts based on the synchronized reference signal to maintain accurate noise cancellation

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20240094984A1Synchronization of audio output for noise cancellation
Publication Date: 2024.03.21 COMCAST CABLE COMM LLC
  • US20240094984A1 patent drawing
  • US20240094984A1 patent drawing
  • US20240094984A1 patent drawing

AI summary

A first computing device may comprise at least one audio output and at least one audio input. The first computing device may determine a first delay associated with output of first audio from a second computing device located remote to the first computing device. Output of second audio may be caused via the at least one audio output based on the first delay. An audio input signal comprising the first audio, the second audio, and third audio indicative of a voice command may be received via the at least one audio input. At least one action may be caused to be performed based on the voice command. The at least one action may be caused to be performed based on removal of the first audio and the second audio from the audio input signal.