In-Vehicle Conferencing With Speaker Tracking and Source Prioritization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In-vehicle conferencing systems face challenges in determining who is speaking due to obstructed camera views and poor audio capture, especially in vehicles with multiple occupants, leading to noisy and unclear communication.
Innovation Solution
A vehicle controller system uses sensors and processors to identify speakers through mouth movement, audio signal strength, and triangulation, prioritizing video and audio feeds from the best image and audio sources, and enhancing them to provide clear communication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single camera is used to serve multiple occupants, then device complexity is reduced, but measurement precision of speaker identification deteriorates due to obstructed views
Solution Approach 1:
The patent combines video data from a single camera with audio data from multiple microphones to achieve accurate speaker identification. The system merges multiple data sources (video feeds, audio signals, mouth movement detection) to compensate for the limitations of using only one camera, thereby maintaining low device complexity while improving measurement precision.
Solution Approach 2:
The system uses audio signals as an intermediary to identify speakers when visual identification is obstructed. By detecting mouth movements and correlating them with audio sources, the system can identify speakers even when the camera view is blocked by headrests or other cabin features.
2Measurement precision
If multiple microphones are used to capture audio from all occupants, then measurement precision of audio capture is improved, but noise levels increase
Solution Approach 1:
The patent applies local quality by processing audio signals differently based on their source and characteristics. The system identifies specific audio sources (speakers) and enhances their signals while suppressing or filtering out background noise and non-speaker audio, thereby maintaining high measurement precision without overwhelming noise levels.
Solution Approach 2:
The system dynamically changes audio parameters such as gain, filtering, and signal enhancement based on real-time detection of speaker activity. When a speaker is identified through video analysis, the corresponding audio channel is enhanced while others are attenuated, allowing precise audio capture without constant high noise levels from all microphones.
3Ease of manufacture
If microphones are positioned in the front of the vehicle, then ease of manufacture is improved, but measurement precision of audio capture deteriorates for rear occupants
Solution Approach 1:
The patent segments the audio capture function by using multiple microphones positioned at different locations in the vehicle cabin. This segmentation allows each microphone to optimally capture audio from its nearest occupants, with the system then combining these segmented audio sources to achieve comprehensive and precise audio capture throughout the vehicle.
Solution Approach 2:
The system adds spatial dimensionality to audio processing by using multiple microphones distributed throughout the cabin space. This multi-dimensional audio array allows the system to capture and identify speakers from various positions, including rear occupants, by analyzing sound arrival times and intensities from different spatial locations.
Data Source
AI summary
Systems and methods for implementing smart in-vehicle conferencing with user tracking and speaker prioritization. A controller system of a vehicle may determine, based at least in part on one or more cameras, a plurality of candidate best image sources, determine, from the plurality of candidate best image sources, a best image source for a speaker in the vehicle, determine, based at least in part on the best image source, a video feed, determine, based at least in part on one or more microphones, a plurality of candidate best audio sources, determine, from the plurality of candidate best audio sources, a best audio source for the speaker, determine, based at least in part on the best audio source, an audio feed, and provide, to a conference call line, the video feed and the audio feed.