Asynchronous Sound Source Separation via Reference Signal Time Shift
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sound signal processing methods fail to effectively separate sound sources when recorded asynchronously by multiple devices, leading to deteriorated separation and voice recognition performance due to timing and sampling frequency differences.
Innovation Solution
A method involving the output of reference signals of different frequencies by each device, calculation of time shift amounts based on received reference and sound signals, and subsequent separation of sound signals to synchronize and separate sound sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If sound signals are recorded asynchronously by multiple devices, then the system can operate with flexible timing and sampling frequencies, but the sound source separation performance deteriorates due to phase difference changes
Solution Approach 1:
The system performs preliminary time shift calculation using reference signals before the actual sound source separation process. By calculating the time shift amount between asynchronous devices in advance and storing it, the system prepares the necessary synchronization information before processing the main sound signals, thereby resolving the phase difference issue without affecting the separation performance
Solution Approach 2:
Reference signals serve as an intermediary between asynchronous devices to establish timing relationships. These reference signals are used to calculate time shift amounts that act as mediators, allowing the system to compensate for asynchronous recording without directly processing the mismatched sound signals
2Measurement precision
If time shift calculation is performed using reference signals, then accurate synchronization can be achieved, but the system complexity increases due to additional signaling requirements
Solution Approach 1:
Each device generates and uses its own reference signals to calculate its own time shift amount relative to other devices. The system performs self-synchronization by having devices independently calculate and store their own time shift values, reducing the need for complex centralized control mechanisms
Data Source
AI summary
A sound signal processing method and device are provided for separating sounds of the respective sound sources even when sounds are recorded asynchronously by a plurality of devices. Specifically, the present invention comprises the steps of instructing each of the plurality of devices to output a reference signal of a different frequency, receiving each of the reference signals output from the speaker of the plurality of devices according to the instruction, receiving sound signals in which each of the reference signals output from the speaker of the plurality of devices is input into the microphone of the plurality of devices, calculating a time shift amount of each of the devices based on each of the received reference signals output from the speaker and the received sound signals, and separating the plurality of signal signals input into the microphone of the plurality of devices based on the calculated time shift amount.