Irrelevant Voice Cancellation via Decibel-Based Coefficients
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing audio signal processing technologies fail to effectively cancel out irrelevant voice interference between multiple users in close proximity, leading to audio signal interference during web conferences or meetings, as traditional noise cancellation methods require exclusive microphones or multiple microphones for each user.
Innovation Solution
A computer-implemented method using multiple microprocessors to detect user utterances from multiple microphones, determine cancelling coefficients based on decibel measures, and apply these coefficients to generate output audio data that cancels out interfering voices, ensuring only the intended user's voice is heard.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If traditional noise cancellation methods are used, then ambient noise can be reduced, but irrelevant voice interference between multiple users cannot be effectively cancelled
Solution Approach 1:
The patent segments the audio signal processing by creating separate processing paths for each user's audio data. Each computing device processes its own local audio data independently while exchanging remote audio data with other devices, allowing individualized interference cancellation for each user without affecting others' audio quality
Solution Approach 2:
The patent changes the processing parameter from simple noise cancellation to coefficient-based signal combination. By calculating cancelling coefficients based on decibel measures and combining local audio data with processed remote audio data using these coefficients, the system effectively separates and cancels irrelevant voices while preserving the intended user's voice
2Object-affected harmful factors
If exclusive microphones are used for each user, then voice interference is eliminated, but device complexity and cost increase
Solution Approach 1:
The patent makes the microphone system universal by allowing each computing device to use its own microphone for multiple purposes: capturing both the intended user's voice and irrelevant voices from other users. The processed audio data from multiple devices is then combined to achieve interference cancellation, eliminating the need for exclusive microphones
Solution Approach 2:
The patent introduces audio data exchange as an intermediary mechanism. Each device sends its audio data to other devices, which then process this remote audio data to extract and cancel irrelevant voices. This intermediary data exchange enables interference cancellation without requiring additional physical microphones for each user
3Reliability
If multiple microphones are deployed for each user, then audio signal quality improves, but loss of substance and system complexity increase
Solution Approach 1:
The patent extracts only the relevant audio components from the mixed audio data. By calculating cancelling coefficients based on decibel measures and applying them to the remote audio data, the system extracts and removes only the irrelevant voice portions while preserving the intended user's voice, minimizing loss of useful audio data
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Effectively cancels out interfering audio signals from nearby users, improving the audio experience by isolating the primary user's voice in multi-user environments, such as web conferences or meetings, without the need for exclusive microphones or additional noise cancellation equipment.
Implementation Method 1
detecting a first user utterance having a first user utterance local decibel measure in the first audio data and the first user utterance having a first user utterance remote decibel measure in the second audio data
Implementation Method 2
Such active noise control measures are employed for reducing unwanted sound by the addition of a second sound specifically designed to cancel the first
Data Source
AI summary
Computer-implemented methods, computer program products, and computer systems configured for receiving first audio data from a first computing device via a first microphone, receiving second audio data from a second computing device via a second microphone, detecting a first user utterance having a first user utterance local decibel measure in the first audio data and a first user utterance remote decibel measure in the second audio data, detecting a second user utterance having a second user utterance local decibel measure in the second audio data and a second user utterance remote decibel measure in the first audio data, determining a first cancelling coefficient based on the second user utterance detected at the first microphone and the second user utterance detected at the second microphone, applying the first cancelling coefficient to the first audio data, and generating first output audio data comprising the first user utterance at the first computing device.