Ambient Sound Cleaning via Audio Stream Subtraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing devices struggle to accurately detect voice commands when ambient sound includes audio output from nearby devices, leading to incorrect or missed voice command detection.
Innovation Solution
A method is implemented at a first electronic device to generate a cleaned version of ambient sound by receiving timing and offset information from a second device, aligning an audio stream with the ambient sound, and performing a subtraction operation to remove the audio stream from the ambient sound.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If media content is played back at a second device located close to a first device, then the user experience of media playback is improved, but the accuracy of voice command detection at the first device deteriorates due to ambient sound interference
Solution Approach 1:
The patent extracts and removes the media content audio signal from the ambient sound captured by the first device's microphone. By identifying and subtracting the known media content audio stream from the captured ambient sound, the system isolates and eliminates the interfering audio component, thereby improving voice command detection accuracy without reducing media playback intensity.
Solution Approach 2:
The patent introduces an intermediary processing step that receives both the ambient sound capture and the media content audio stream, then performs audio signal processing to generate a cleaned version of the ambient sound. This intermediary audio processing mechanism mediates between the media playback function and the voice command detection function, allowing both to operate effectively simultaneously.
2Adaptability or versatility
If the first device attempts to detect voice commands in ambient sound including media content audio, then voice command detection capability is maintained, but processing power requirements increase due to the need to filter and analyze noisy audio signals
Solution Approach 1:
The patent performs preliminary action by pre-processing the ambient sound to remove media content audio interference before voice command detection begins. By cleaning the audio signal in advance through subtraction of the known media content stream, the system reduces the computational burden on subsequent voice recognition algorithms, thereby lowering overall processing power consumption while maintaining detection capability.
3Measurement precision
If audio signals from media content playing on a second device are subtracted from sound detected at a first device, then voice command detection accuracy is improved, but device complexity increases due to the need for audio tracking and synchronization
Solution Approach 1:
The patent implements feedback by continuously tracking the playback position and timing of media content on the second device, then using this information to dynamically adjust and update the audio subtraction process. The system receives feedback about media content playback status and uses it to maintain accurate synchronization between the subtracted audio signal and the captured ambient sound, ensuring sustained detection accuracy despite the added complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
While a media content item is emitted by a second electronic device that is remote from the first electronic device, the first electronic device receives data that includes: timing information, offset information that indicates a difference between an initial position of the media content item and a current playback position of the media content item, and an audio stream that corresponds to the media content item. The first electronic device detects ambient sound that includes sound corresponding to the media content item emitted by the second electronic device. The first electronic device generates a cleaned version of the ambient sound by using the timing information and the offset information to align the audio stream with the ambient sound and performing a subtraction operation to substantially subtract the audio stream from the ambient sound.