Audio Transmission System Using Attention-Based Noise Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing electronic devices fail to effectively help users in noisy or quiet environments by inadequately managing sound transmission and reception, leading to difficulties in hearing specific sound sources and ensuring voices are heard by intended recipients, particularly due to the 'cocktail party effect' where background noise interferes with conversations.

Innovation Solution

The implementation of devices and methods that use user attention to selectively transmit audio and adjust noise cancellation or transparency based on contextual factors such as object locations, eye tracking, and physiological data, utilizing low-latency multi-user wireless networking to enhance audio transmission and reception, allowing users to focus on specific sound sources while minimizing background noise.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If noise cancellation is used to block background noise, then audio clarity is improved, but user awareness of ambient environment is reduced

Engineering Contradiction:
Improveaudio clarityVSAvoidenvironmental awareness
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system dynamically switches between noise cancellation mode and ambient sound passthrough mode based on detected user attention state. When the user is determined to be attentively listening to a specific audio source, noise cancellation is activated to improve audio clarity. When the user shifts attention to the ambient environment, the system transitions to passthrough mode to restore environmental awareness, thus resolving the contradiction between audio clarity and environmental awareness.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system uses sensors to continuously monitor user attention state and provides feedback to control the noise cancellation algorithm. This closed-loop feedback mechanism allows the system to adaptively adjust the balance between noise cancellation and ambient sound transmission based on real-time user behavior, optimizing both audio clarity and environmental awareness according to actual usage conditions.

Inventive Principle:
Principle #23Feedback

2Speed

If audio is transmitted wirelessly in real-time, then communication responsiveness is improved, but transmission latency increases

Engineering Contradiction:
Improvecommunication responsivenessVSAvoidtransmission latency
Core Design Contradiction:
SpeedVSLoss of time

Solution Approach 1:

The system performs preliminary actions by capturing and buffering audio data before actual transmission is needed. By pre-processing and preparing audio streams in advance, the system reduces the time required for real-time wireless transmission, thereby improving communication responsiveness while minimizing perceived latency to acceptable levels.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If multiple sensors are used to detect user attention, then detection accuracy is improved, but device complexity increases

Engineering Contradiction:
Improveuser attention detection accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system merges multiple sensor types (cameras for eye tracking, microphones for audio analysis, accelerometers for head movement detection) into an integrated attention detection system. By combining these sensors and processing their data through a unified algorithm, the system achieves high detection accuracy while managing device complexity through integrated design and shared processing resources.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS20240211200A1Live peer-to-peer voice communication systems and methods using machine intelligence
Publication Date: 2024.06.27 APPLE INC
  • US20240211200A1 patent drawing
  • US20240211200A1 patent drawing
  • US20240211200A1 patent drawing

AI summary

Various implementations disclosed herein include devices, systems, and methods that sense, assess, measure, or otherwise determine user attention to selectively transmit or deliver audio from an audio source (e.g., a talking user's voice captured by their device, a TV, etc.) to one or more listening users' devices and/or adjusts audio cancellation/transparency of environmental noise on the one or more listening users' devices in a multi-person setting.