Wake-Word Suppression During Audio Playback to Prevent False Triggers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Playback of audio content containing wake words can falsely trigger networked microphone devices, leading to undesirable interference with the audio content and surges in voice service requests.
Innovation Solution
Processing audio content before playback to detect wake words and instructing networked microphone devices to disregard them during playback, using various techniques such as disabling the microphone, creating listening NULLs, or inserting audio markers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If networked microphone devices continuously monitor for wake words to enable voice control, then voice command responsiveness is improved, but false triggering during audio playback increases
Solution Approach 1:
The system performs preliminary detection of wake words in the audio content before playback occurs. By analyzing the audio content in advance and identifying segments that contain wake words, the system can prepare suppression instructions to be sent to networked microphone devices during playback, preventing false triggers while maintaining voice control functionality.
Solution Approach 2:
The playback device acts as an intermediary between the audio content source and the networked microphone devices. It receives audio content, detects wake words within it, and sends suppression instructions to networked microphone devices during playback, thereby mediating between the need for continuous wake word monitoring and the need to prevent false triggering.
2Adaptability or versatility
If wake word detection is enabled during audio playback, then voice service requests are processed, but interference with audio content increases
Solution Approach 1:
The system extracts and identifies wake word segments from the audio content before playback. By separating and marking these specific segments, the system can then instruct networked microphone devices to ignore only these extracted portions during playback, allowing voice service processing to occur without interfering with the audio content.
Solution Approach 2:
The suppression of wake word detection is applied locally and selectively only during the specific time segments when wake words are detected in the audio content. The networked microphone devices continue to monitor for wake words at all times, but the suppression instructions target specific temporal regions, allowing differentiated behavior based on local conditions.
3Reliability
If audio content is processed to detect and suppress wake words, then false triggering is reduced, but processing complexity increases
Solution Approach 1:
The playback device utilizes its existing wake word detection capabilities and audio processing functions to serve multiple purposes: normal audio playback, wake word detection for voice control, and now additionally, detection of wake words within audio content for suppression purposes. This multi-functionality approach reduces the need for separate dedicated systems.
Solution Approach 2:
The system employs the playback device's own wake word detection algorithms and processing resources to identify wake words in the audio content and generate suppression instructions. Rather than requiring an external complex system, the playback device serves itself by using its existing capabilities to solve the false triggering problem.
Data Source
AI summary
Example techniques involve suppressing a wake word response to a local wake word. An example implementation involves a playback device receiving audio content for playback by the playback device and providing a sound data stream representing the received audio content to a voice assistant service (VAS) wake-word engine and a local keyword engine. The playback device plays back a first portion of the audio content and detects, via the local keyword engine, that a second portion of the received audio content includes sound data matching one or more particular local keywords. Before the second portion of the received audio content is played back, the playback device disables a local keyword response of the local keyword engine to the one or more particular local keywords and then plays back the second portion of the audio content via one or more speakers.