Gaze-Controlled Directional Sound Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Directional microphones capture sound in a fixed direction, which may not align with the user's interest, especially when the direction of interest changes frequently, such as when tracking a moving object, requiring manual adjustment or additional methods like gaze or body positioning.
Innovation Solution
A sound recording device comprising a sound recording unit, an image recording unit to determine the user's primary gaze direction, and a control unit to amplify sounds arriving in that direction while attenuating or not amplifying sounds from other directions, using a cluster of sound recording devices and image processing to adjust sound levels based on gaze direction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a directional microphone is used to capture sound from a particular direction, then sound from that direction is amplified, but the direction is fixed and cannot adapt to changing user interest
Solution Approach 1:
The patent applies dynamics by making the microphone array's beamforming direction dynamic rather than fixed. The system continuously adjusts the directional sensitivity pattern based on real-time gaze direction detection from the camera, allowing the amplified sound direction to adapt as the user looks at different objects or people.
Solution Approach 2:
The system uses feedback by detecting the user's gaze direction through camera-based eye tracking and using this information to adjust the microphone array's beamforming in real-time. The detected gaze direction feeds back to the signal processing unit, which then modifies the directional sound capture accordingly.
2Adaptability or versatility
If the directional microphone is attached to a movable object to change direction, then direction flexibility is improved, but the system becomes more complex and requires manual adjustment
Solution Approach 1:
The patent replaces the mechanical approach of physically moving the microphone with an electronic beamforming system. Instead of mechanically repositioning sensors, the system uses signal processing to electronically steer the directional sensitivity pattern, significantly reducing mechanical complexity while maintaining directional flexibility.
Solution Approach 2:
The system introduces an intermediary element - the camera-based gaze detection system - that mediates between the user's natural behavior and the microphone array's directional capture. This intermediary translates gaze direction into beamforming control parameters, simplifying the overall system architecture.
3Measurement precision
If the user turns their head to align with the direction of interest, then sound capture direction matches user interest, but this is inconvenient when the user needs to perform other tasks
Solution Approach 1:
The system applies self-service by automatically adjusting the sound capture direction based on the user's gaze without requiring the user to manually reposition their head or the microphone. The gaze detection and beamforming adjustment happen automatically, allowing the user to maintain natural head position while performing other tasks.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This disclosure is directed to a sound recording arrangement comprising a sound recording arrangement and a method in the sound recording arrangement for amplifying sounds in a primary gaze direction of the user of the sound recording arrangement. The method comprises the actions of recording sounds arriving at a sound recording unit from objects in the field of view of the user, and recording a first set of images of the head and/or the eyes of the user, and determining a primary gaze direction of the user based on the first set of images, and amplifying sounds arriving in the primary gaze direction compared to sounds arriving from other directions.