Arbitration-Based Voice Recognition Bandwidth Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing media playback systems face challenges in efficiently managing voice inputs from multiple networked devices, leading to potential bandwidth waste and latency issues when multiple devices attempt to send the same voice command to a cloud-based computing device.
Innovation Solution
An arbitration process is implemented among networked microphone devices to determine which device should send voice inputs to the cloud-based computing device, based on confidence measures and time intervals, ensuring efficient voice recognition and minimizing bandwidth usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple networked devices send voice inputs to the cloud-based computing device, then voice recognition coverage is improved, but bandwidth waste and latency increase
Solution Approach 1:
The system performs preliminary arbitration among networked devices before sending voice inputs to the cloud. Each device determines a confidence value for detecting the wake word and shares this information with other devices. Based on this preliminary assessment, only the device with the highest confidence value proceeds to send the voice input, preventing redundant transmissions and optimizing bandwidth usage while maintaining reliable voice recognition coverage.
2Reliability
If multiple networked devices send voice inputs to the cloud-based computing device, then voice recognition coverage is improved, but latency increases
Solution Approach 1:
The arbitration process determines which device should send the voice input before transmission begins. By pre-establishing confidence values and identifying the most suitable device in advance, the system avoids the latency that would result from multiple devices simultaneously attempting to send voice inputs or from the cloud processing multiple redundant inputs.
3Loss of energy
If an arbitration process is implemented among networked devices, then bandwidth efficiency is improved, but device complexity increases
Solution Approach 1:
The arbitration process is segmented into distinct functional components: wake word detection, confidence value determination, confidence value sharing among devices, and send decision-making. Each networked device independently performs detection and determination, then shares results with others. This segmentation distributes the complexity across multiple simple device-level functions rather than requiring one complex centralized arbitration system, making the overall solution more manageable and scalable.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
A first voice input is detected and a first measure of confidence associated with the first voice input is determined. A message is received comprising a second measure of confidence associated with detection of the first voice input by a network device. A determination is made whether the first measure of confidence is greater than the second measure of confidence. Based on the determination that the first measure of confidence is greater than the second measure of confidence, a second voice input is sent to a server.