Adaptive Noise Cancellation for Shared Audio Endpoints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Background noise from multiple audio endpoints in shared spaces is transmitted to remote participants, causing loss of intelligibility and fatigue during telecommunication sessions, as far-end participants cannot filter out unwanted noise using binaural cues.
Innovation Solution
Implementing adaptive noise cancellation techniques across multiple audio endpoints in shared spaces by detecting co-located devices, identifying the target noise source, and using a loudspeaker reference signal to remove background noise from microphone signals before transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple audio endpoints operate in a shared space, then the utility and coverage of the space is improved, but background noise increases causing loss of intelligibility for remote participants
Solution Approach 1:
The patent extracts the harmful loudspeaker reference signal from the microphone signal by obtaining it from co-located audio endpoints and using adaptive filtering to remove it, thereby separating the useful speech signal from the harmful background noise generated by other endpoints in the shared space
Solution Approach 2:
The system uses adaptive noise cancellation with feedback mechanisms where the loudspeaker reference signal is continuously obtained from co-located endpoints and fed into the adaptive filter to dynamically cancel background noise, improving speech intelligibility for remote participants
2Loss of information
If background noise is transmitted to remote participants, then all audio information is captured, but remote participants experience fatigue and loss of intelligibility
Solution Approach 1:
The patent converts the harmful background noise into a useful reference signal by obtaining the loudspeaker reference signal from co-located audio endpoints, which is then used by the adaptive filter to cancel the noise, transforming the problem of shared space noise into a solution that improves speech clarity for remote participants
3Object-affected harmful factors
If adaptive noise cancellation is implemented, then background noise is reduced, but system complexity increases
Solution Approach 1:
The patent implements a universal noise cancellation approach where co-located audio endpoints share their loudspeaker reference signals with each other, allowing any endpoint to cancel noise from any other endpoint in the shared space, thereby reducing the need for complex individual processing at each endpoint while maintaining effective noise cancellation across the network
Data Source
AI summary
Techniques for adaptive noise cancellation for multiple audio endpoints in a shared space are described. According to one example, a method includes detecting, by a first audio endpoint, one or more audio endpoints co-located with the first audio endpoint at a first location. A selected audio endpoint of the one or more audio endpoints is identified as a target noise source. The method includes obtaining, from the selected audio endpoint, a loudspeaker reference signal associated with a loudspeaker of the selected audio endpoint and removing the loudspeaker reference signal from a microphone signal associated with a microphone of the first audio endpoint. The method also includes providing the microphone signal from the first audio endpoint to at least one of a voice user interface (VUI) or a second audio endpoint, wherein the second audio endpoint is located remotely from the first location.