Multi-Channel Acoustic Echo Cancellation for CPU-Limited Voice Commands

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Multi-channel acoustic echo cancellation in playback devices requires substantial computational resources, exceeding the capabilities of typical CPUs, especially when handling vocal commands alongside media output, leading to obscured voice commands and inefficient resource utilization.

Innovation Solution

Implement methods and systems for multi-channel acoustic echo cancellation that reduce computational requirements, allowing existing CPUs to efficiently process voice commands by filtering media output from captured audio signals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multi-channel acoustic echo cancellation is implemented to filter media output from captured audio signals, then the signal-to-noise ratio of voice commands is enhanced, but the computational resource requirements exceed typical CPU capabilities

Engineering Contradiction:
Improvesignal-to-noise ratio of voice commandsVSAvoidcomputational resource requirements
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the multi-channel acoustic echo cancellation process into multiple parallel filter banks, where each filter bank processes a specific frequency range or channel independently. This segmentation divides the computationally intensive task into smaller, more manageable units that can be processed in parallel, reducing the overall computational burden on the CPU while maintaining the signal-to-noise ratio enhancement.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by implementing acoustic echo cancellation only for specific frequency ranges or channels where it is most needed, rather than processing the entire audio spectrum uniformly. This selective approach reduces computational requirements while still achieving effective voice command enhancement in the critical frequency ranges.

Inventive Principle:
Principle #16Partial or excessive action

2Reliability

If computational resources are allocated to process multi-channel acoustic echo cancellation, then voice command clarity is improved, but other system functions may suffer from resource constraints

Engineering Contradiction:
Improvevoice command recognition accuracyVSAvoidsystem throughput for other functions
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent implements periodic action by processing audio signals in discrete frames or time windows, where acoustic echo cancellation is applied periodically rather than continuously in real-time. This approach allows the system to allocate computational resources in bursts, ensuring voice command recognition accuracy while providing opportunities for other system functions to execute between processing intervals.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The patent applies partial action by focusing computational resources only on the specific audio channels or frequency ranges containing voice commands, rather than processing all audio streams equally. This selective processing improves voice command recognition accuracy while minimizing the impact on system throughput for other functions.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS20250267218A1Multi-Channel Acoustic Echo Cancellation
Publication Date: 2025.08.21 SONOS INC
  • US20250267218A1 patent drawing
  • US20250267218A1 patent drawing
  • US20250267218A1 patent drawing

AI summary

A playback device is configured to: produce a first channel audio output of a first channel of audio content; produce a second channel audio output of a second channel of the audio content; receive captured audio content comprising (i) a first portion corresponding to the first channel audio output, (ii) a second portion corresponding to the second channel audio output, and (iii) a third portion corresponding to a voice command, wherein the captured audio content has a first signal-to-noise ratio; determine a set of signal components from at least one of the first channel or the second channel of the audio content; perform acoustic echo cancellation on a subset of signal components; determine an acoustic echo cancellation output; and apply the acoustic echo cancellation output to the captured audio content and thereby increase the first signal-to-noise ratio to a second signal-to-noise ratio that is greater than the first signal-to-noise ratio.