Dual Earbud Audio Capture with Quality-Based Source Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech-recognition systems face challenges in accurately detecting user voice inputs in noisy environments and when users' hands are occupied, leading to difficulties in interacting with devices effectively.
Innovation Solution
A system comprising dual earbuds that monitor ambient audio and compare quality metrics to determine the better audio source, switching to improve audio quality and entering power-saving modes to conserve resources, while also utilizing voice-activity detection and wakeword detection for efficient speech processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single device is used for audio capture, then device complexity is reduced, but audio quality and reliability in noisy environments deteriorate
Solution Approach 1:
The audio capture function is segmented across multiple independent earbud devices, each with its own microphone and processing capabilities. This allows distributed audio collection from different spatial locations, improving noise rejection and voice detection reliability without requiring a single complex device.
Solution Approach 2:
Multiple audio streams from different earbud devices are merged and processed together by a centralized processor. The system combines audio data from multiple sources, applies noise filtering algorithms, and integrates voice activity detection results to achieve higher detection reliability than a single device could provide.
2Reliability
If multiple devices are used for audio capture, then audio quality improves, but power consumption increases
Solution Approach 1:
The earbud devices perform voice activity detection and wakeword detection periodically rather than continuously at full capacity. When no speech is detected, the devices enter low-power modes, reducing overall energy consumption while maintaining the ability to capture audio quality when needed.
Solution Approach 2:
The system uses feedback from voice activity detection and wakeword detection to dynamically adjust processing intensity. When speech is detected, full audio processing is activated; when silence is detected, power consumption is reduced. This feedback mechanism allows multiple devices to maintain high audio quality when necessary while minimizing average power consumption.
3Speed
If continuous audio monitoring is performed, then detection responsiveness improves, but power consumption increases
Solution Approach 1:
Instead of continuous full-capacity monitoring, the system uses periodic sampling with adaptive intervals. The monitoring frequency increases when voice activity is detected and decreases when silence is detected, maintaining responsive detection while reducing average power consumption through periodic low-power states.
Solution Approach 2:
The system performs partial audio analysis continuously at low intensity, then performs more intensive analysis only when necessary (when voice activity or wakewords are detected). This partial action approach maintains basic responsiveness while significantly reducing power consumption compared to continuous full analysis.
Data Source
AI summary
A system and method includes a first device (e.g., a primary or primary earbud) that detects first audio corresponding to an utterance and a second device (e.g., a secondary or secondary earbud) that detects second audio corresponding to the utterance. The first device determines first audio data corresponding to the first audio and the second device determines second audio data corresponding to the second audio. The first device determines a first quality metric corresponding to the first audio data, and the second device determines a second quality metric corresponding to the second audio data. The second device transmits the second quality metric to first device, which compares it to the first quality metric. If the first device determines the second quality metric is better, it transmits the second audio data to a third device (e.g., a smartphone) and enters a power-saving state.