Vehicle Sound Crosstalk Suppression via Adaptive Filter Reset
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sound crosstalk suppression devices, like those described in Patent Literature 1, fail to effectively suppress crosstalk components in voice signals collected by a driver's microphone when multiple occupants are present in a vehicle cabin, as they lack microphones to capture clear voices from other occupants, making it difficult to learn and filter out crosstalk.
Innovation Solution
A sound crosstalk suppression device with multiple microphones that analyzes the speaker situation using voice signals from multiple microphones, updates a filter to generate a suppression signal for crosstalk components, and resets the filter parameters when the speaker situation changes, allowing adaptive suppression of crosstalk in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If only one microphone is disposed in front of the driver to collect the driver's voice, then the device complexity is reduced, but the crosstalk suppression capability deteriorates because the microphone cannot clearly collect other occupants' voices for filter learning
Solution Approach 1:
The patent divides the voice collection task into multiple segments by placing microphones at different positions (driver's microphone and passenger's microphone). Each microphone is responsible for collecting voices from its respective position, enabling the system to separately capture the driver's voice and the passenger's crosstalk voice for effective filter learning and suppression.
2Adaptability or versatility
If the filter parameter is continuously updated without resetting, then the adaptability to changing speaker situations improves, but the measurement precision deteriorates because the filter learns incorrect crosstalk characteristics when speaker configuration changes
Solution Approach 1:
The patent implements dynamic filter parameter management by detecting speaker situations and selectively resetting filter parameters. When a speaker situation change is detected (e.g., passenger speaking vs. silent), the system resets the filter parameters to prevent learning incorrect crosstalk characteristics, while maintaining continuous adaptation within each stable speaker situation.
Solution Approach 2:
The system uses feedback from speaker situation detection to control filter parameter resetting. By monitoring whether the passenger is speaking or silent and comparing with previous states, the system determines when to reset filter parameters, ensuring accurate crosstalk suppression adapts to changing conditions.
3Measurement precision
If the filter parameter is reset every time speaker situation changes, then the crosstalk suppression accuracy improves by preventing incorrect learning, but the response time deteriorates due to the need to relearn filter parameters
Solution Approach 1:
The system performs preliminary detection of speaker situations before filter parameter updates. By detecting whether the passenger is speaking or silent in advance and comparing with the previous state, the system determines the appropriate timing for filter parameter resetting, avoiding unnecessary resets and reducing relearning time while maintaining suppression accuracy.
Data Source
AI summary
A sound crosstalk suppression device includes: a speaker analysis unit configured to analyze a speaker situation in a closed space based on voice signals respectively collected by a plurality of microphones arranged in the closed space; a filter update unit that includes a filter configured to generate a suppression signal of a crosstalk component included in a voice signal of a main speaker, that is configured to update a parameter of the filter, and that is configured to store the updated parameter in a memory; a reset unit configured to reset the parameter of the filter in a case where it is determined that an analysis result of the speaker situation is switched; and a crosstalk suppression unit configured to suppress a crosstalk component by using a suppression signal.