Secondary Microphone Wakeword Detection During Primary Device Occupancy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Speech recognition systems face challenges when a primary device is unable to capture spoken user inputs, such as during phone calls or music playback, as its microphone is diverted for other purposes, leading to a need for an alternative method to capture and process voice commands.
Innovation Solution
A secondary device, connected via Bluetooth or other techniques, is enabled to capture spoken user inputs when the primary device is disabled, allowing it to detect wake words and send audio data to the speech processing system until the primary device is re-enabled.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the primary device's microphone is used for other purposes (phone calls, music playback), then those functions are improved, but the ability to capture spoken user inputs for speech recognition deteriorates
Solution Approach 1:
The patent introduces a secondary device as an intermediary to capture spoken user inputs when the primary device's microphone is occupied. The secondary device acts as a mediator that receives audio data from the environment and forwards it to the speech processing system, ensuring voice command capture functionality is maintained even when the primary device is engaged in other activities like phone calls or music playback.
2Productivity
If the primary device is occupied with other tasks, then task completion efficiency is improved, but continuous voice command processing capability deteriorates
Solution Approach 1:
The patent ensures continuous voice command processing availability by implementing a fallback mechanism where the secondary device takes over audio capture when the primary device is occupied. This maintains the continuity of the speech recognition function across different device states, allowing users to interact with the system regardless of whether the primary device is available for audio input.
3Reliability
If a secondary device is introduced to capture voice inputs, then voice command processing reliability is improved, but device complexity increases
Solution Approach 1:
The patent leverages the secondary device's existing microphone and processing capabilities for multiple purposes - both its original function and voice command capture. By reusing the secondary device's hardware resources rather than adding dedicated components, the system achieves improved voice command reliability while minimizing the increase in overall system complexity.
Data Source
AI summary
Techniques for capturing spoken user inputs while a device is prevented from capturing such spoken user inputs are described. When a first device has a status representing it is unbeneficial for the first device to perform wakeword detection, a second device (e.g. a vehicle) may perform wakeword detection on behalf of the first device. The second device may be unable to send audio data, representing a spoken user input, to a speech processing system. In such an example, the second device may send the audio data to a third device, which may send the audio data to the speech processing system.