Conditional Wake Word Engine for Playback Devices

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional wake-word engines in voice-assisted media playback systems are prone to false positives due to misidentification of wake words in ambient audio, leading to resource consumption and interruptions.

Innovation Solution

Implementing a command keyword engine that detects specific command keywords only when certain playback conditions are met, allowing for local natural language processing and reducing false positives by integrating a local natural language unit (NLU) to recognize a limited library of keywords.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a traditional wake-word engine is used to detect wake words in ambient audio, then voice-assisted control functionality is provided, but false positives occur due to misidentification leading to resource consumption and interruptions

Engineering Contradiction:

Improvevoice-assisted control functionalityVSAvoidfalse positive rate

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent divides the wake-word detection system into two independent segments: a traditional wake-word engine that continuously monitors for wake words, and a new command keyword engine that activates only when specific playback conditions are met. This segmentation allows the command keyword engine to process ambient audio locally without triggering false positives from music or speech, thereby improving reliability while maintaining voice-assisted control functionality.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system dynamically adjusts the activation state of the command keyword engine based on playback conditions. When music or other audio is playing, the command keyword engine remains inactive to avoid false positives. When no audio is playing, the engine becomes active to capture voice commands. This dynamic behavior reduces false positives while preserving ease of operation.

Inventive Principle:

Principle #15Dynamics

2Adaptability or versatility

If cloud-based processing is used for wake-word detection, then comprehensive voice recognition is achieved, but user privacy is compromised and response time increases

Engineering Contradiction:

Improvevoice recognition capabilityVSAvoiduser privacy

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent implements local processing capability through the command keyword engine that runs on-device using a local natural language unit. This local quality allows the system to process command keywords privately without transmitting audio to the cloud, preserving user privacy while maintaining versatile voice recognition for supported commands.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The command keyword engine acts as an intermediary between the microphone and cloud-based voice recognition services. It filters and pre-processes audio locally, handling simple commands before they reach cloud services, thereby reducing privacy risks and response times while maintaining comprehensive recognition capability through the combination of local and cloud processing.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If cloud-based processing is used for all voice inputs, then comprehensive language understanding is achieved, but response time increases and interruptions occur

Engineering Contradiction:

Improvelanguage understanding capabilityVSAvoidresponse time

Core Design Contradiction:

Adaptability or versatilityVSSpeed

Solution Approach 1:

The patent segments voice processing into two pathways: simple command keywords processed instantly by the local command keyword engine, and complex natural language queries routed to cloud-based services. This segmentation enables fast local responses for supported commands while maintaining comprehensive language understanding for more complex requests, thereby improving response speed without sacrificing versatility.

Inventive Principle:

Principle #1Segmentation

4Ease of operation

If the wake-word engine continuously monitors ambient audio, then voice commands can be captured at any time, but false positives from music or speech cause interruptions

Engineering Contradiction:

Improvecontinuous voice command captureVSAvoidinterruptions from false positives

Core Design Contradiction:

Ease of operationVSObject-generated harmful factors

Solution Approach 1:

The command keyword engine dynamically changes its operational state based on ambient audio conditions. It remains inactive when music or speech is detected to avoid false positives, and activates only when the environment is suitable for voice commands. This dynamic approach allows continuous monitoring capability while eliminating harmful interruptions from false positives.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system applies preliminary anti-action by detecting the presence of music or speech before the command keyword engine can misinterpret them as wake words. When such audio is detected, the engine is prevented from activating, thereby counteracting the potential harmful effect of false positives before they occur.

Inventive Principle:

Principle #9Preliminary anti-action

Data Source

PatentUS11361756B2Conditional wake word eventing based on environment

Publication Date: 2022.06.14 SONOS INC

AI summary

In one aspect, a playback device includes at least one microphone configured to detect sound. The playback detects sound via the one or more microphones and determines whether (i) the detected sound includes a voice input, (ii) the detected sound excludes background speech, and (iii) the voice input includes a command keyword. In response to the determining, the playback device performs a playback function corresponding to the command keyword.