Voice Recognition via Multi-Device Clock Synchronization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current voice recognition systems in vehicles struggle to effectively separate mixed voices or noise without increasing the number of microphones, leading to reduced recognition rates, especially when there are multiple speakers or noise present.
Innovation Solution
The method involves connecting multiple devices with voice collection capabilities, such as smartphones and a car host system, to collect and synchronize voice information using clock synchronization, allowing for voice separation and recognition without adding more fixed microphones, by leveraging existing devices like smartphones with microphones to enhance voice recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a microphone array or extended algorithms (ICA, FDICA) are used to separate mixed voices, then voice recognition rate is improved, but the number of microphones must be at least equal to the number of voice sources, leading to cost increase
Solution Approach 1:
The patent makes existing devices (smartphones, tablets, laptops) serve multiple functions: they act as both communication devices and voice collection devices. By utilizing the microphones already present in these ubiquitous devices, the system achieves voice separation capability without requiring additional dedicated microphones in the vehicle, thus resolving the contradiction between recognition rate and microphone quantity
Solution Approach 2:
The system leverages the existing voice collection capabilities of user devices that people already carry and use. These devices self-serve as additional microphones by utilizing their built-in microphones, eliminating the need for the vehicle system to provide additional hardware while still achieving improved voice recognition in multi-speaker environments
2Measurement precision
If multiple devices are connected to collect voice information, then voice separation capability is improved, but clock synchronization between devices must be achieved
Solution Approach 1:
The system establishes a master-slave relationship where one device acts as master and others as slaves. The master device provides reference timing information, and slave devices adjust their local clocks based on feedback from the master, achieving synchronization through continuous timing feedback without requiring complex inter-device coordination protocols
Solution Approach 2:
Instead of having each device independently synchronize with every other device (which would create N*(N-1)/2 synchronization relationships), the patent inverts the approach by designating one device as the central time reference. All other devices synchronize to this single master, reducing the complexity from quadratic to linear relationships
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
A method and device for voice recognition are provided. The method for voice recognition includes: receiving a voice information collected by a plurality of voice collection devices configured on a plurality of devices connected together, wherein the plurality of devices comprises at least one mobile device； and conducting a voice separation and recognition process on the voice information collected by the plurality of voice collection devices. The device for voice recognition includes: a processor, configured to: obtain a clock difference among a plurality of devices connected together, where each of the plurality of devices is configured with a voice collection device； obtain a voice information collected by the voice collection device configured on the each of the plurality of voice collection devices； and conduct a voice separation and recognition process on voice information collected by the voice collection device based on the clock difference among the among a plurality of devices.