Wake-Word Engine Suppression for Networked Audio Playback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network microphone devices (NMDs) are prone to false positives due to false wake word triggers, leading to inefficient operation, resource consumption, and disruption of audio playback.
Innovation Solution
Implementing a playback device with a primary wake-word engine and a secondary wake-word engine suppressor that identifies false wake words, temporarily deactivating the primary engine and other NMDs to prevent false triggers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the primary wake-word engine continuously monitors for wake words, then voice activation capability is maintained, but false positives occur causing resource consumption and audio interruptions
Solution Approach 1:
The secondary wake-word engine suppressor performs preliminary analysis of audio content before the primary wake-word engine processes it. By pre-identifying false wake words in the audio stream, the system prevents unnecessary activation of the primary engine and other NMDs, thereby conserving compute resources while maintaining reliable voice activation capability.
2Speed
If the primary wake-word engine remains active to detect wake words, then responsiveness to user commands is ensured, but false triggers cause unexpected chimes and disruptions
Solution Approach 1:
The secondary wake-word engine suppressor applies preliminary anti-action by identifying and neutralizing false wake words in the audio stream before they can trigger the primary wake-word engine. This prevents harmful false positive triggers and unexpected chimes while keeping the primary engine active and responsive to legitimate user commands.
3Adaptability or versatility
If multiple network microphone devices operate simultaneously, then voice control coverage is enhanced, but false positives propagate across the network causing widespread interruptions
Solution Approach 1:
The secondary wake-word engine suppressor acts as an intermediary between the audio stream and multiple network microphone devices. By pre-identifying false wake words and transmitting suppression indicators to other NMDs over the network, it prevents false positive propagation while maintaining enhanced voice control coverage across multiple devices.
Data Source
AI summary
In one aspect, a playback deice is configured to identify in an audio stream, via a second wake-word engine, a false wake word for a first wake-word engine that is configured to receive as input sound data based on sound detected by a microphone. The first and second wake-word engines are configured according to different sensitivity levels for false positives of a particular wake word. Based on identifying the false wake word, the playback device is configured to (i) deactivate the first wake-word engine and (ii) cause at least one network microphone device to deactivate a wake-word engine for a particular amount of time. While the first wake-word engine is deactivated, the playback device is configured to cause at least one speaker to output audio based on the audio stream. After a predetermined amount of time has elapsed, the playback device is configured to reactivate the first wake-word engine.


