Voice Device Wake Word Detection Timing Window
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice-activated electronic devices often inadvertently activate due to audio output containing the wake word, leading to disruptions in audio playback and user experience, as they mistakenly interpret the wake word within the outputted audio as a command.
Innovation Solution
The device calculates a modified time window considering hardware delays and echoing offsets to determine when the wake word is likely to be detected, allowing it to ignore instances of the wake word within this window and prevent erroneous activation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the device continuously monitors audio input for wake word detection, then the device can respond to user commands, but the device may inadvertently activate when the wake word is present in outputted audio
Solution Approach 1:
The system pre-calculates a time window before audio output that accounts for hardware delays and echoing offsets. This preliminary determination of when the wake word might appear in audio input allows the system to ignore detections within this window, preventing erroneous activation while maintaining reliable wake word detection for actual user commands.
2Object-generated harmful factors
If the device ignores all wake word detections during audio output, then erroneous activation is prevented, but legitimate user commands during audio playback cannot be detected
Solution Approach 1:
The system applies different detection behaviors to different time periods: during the calculated time window when the wake word is expected to appear in audio input, detections are ignored; outside this window, normal wake word detection operates. This localized approach prevents erroneous activation while preserving the ability to detect legitimate user commands.
3Measurement precision
If the device accounts for hardware delays and echoing offsets, then accurate identification of erroneous wake word detections is achieved, but the system complexity increases
Solution Approach 1:
The system determines a specific time window parameter based on hardware delay characteristics and echoing offset measurements. By converting complex physical phenomena into a single time window parameter, the system achieves precise wake word detection timing while maintaining relatively simple implementation through parameter-based control rather than complex real-time analysis.
Data Source
AI summary
Systems and methods for selectively ignoring an occurrence of a wakeword within audio input data is provided herein. In some embodiments, a wakeword may be detected to have been uttered by an individual within a modified time window, which may account for hardware delays and echoing offsets. The detected wakeword that occurs during this modified time window may, in some embodiments, correspond to a word included within audio that is outputted by a voice activated electronic device. This may cause the voice activated electronic device to activate itself, stopping the audio from being outputted. By identifying when these occurrences of the wakeword within outputted audio are going to happen, the voice activated electronic device may selectively determine when to ignore the wakeword, and furthermore, when not to ignore the wakeword.