Distributed Microphone Mobile Objects for Voice Separation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice acquisition systems struggle to accurately separate voices from multiple sound sources when the number of sound sources exceeds the number of microphones, leading to decreased position detection accuracy and ineffective voice extraction in interactive robots.
Innovation Solution
A voice acquisition system comprising movable mobile objects with microphones, a sound source number estimating unit, and a control unit that adjusts the positions of these objects to ensure sufficient microphone coverage, allowing for accurate voice separation from multiple sound sources by estimating the number of sound sources and coordinating the movement of additional microphones to enhance separation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a fixed number of microphones are mounted on a single mobile object, then the device complexity is reduced, but the measurement precision of sound source positions and voice separation accuracy deteriorate when the number of sound sources exceeds the number of microphones
Solution Approach 1:
The system divides the microphone resources across multiple mobile objects (robots) instead of concentrating all microphones on a single device. Each mobile object carries one or more microphones, and the system dynamically coordinates these distributed microphones to collectively capture sounds from multiple sources, thereby maintaining high measurement precision without requiring each individual mobile object to have a large number of microphones.
Solution Approach 2:
The system dynamically adjusts the allocation and coordination of microphones across mobile objects based on the estimated number of sound sources. When multiple sound sources are detected, the control unit activates and coordinates additional microphones from other mobile objects, transforming the static microphone configuration into a dynamic, adaptive system that scales its measurement capability according to the actual acoustic environment.
2Adaptability or versatility
If the number of microphones is increased to handle more sound sources, then the voice separation accuracy improves, but the device complexity and cost increase
Solution Approach 1:
Multiple mobile objects are equipped with microphones that serve dual purposes: each mobile object independently performs its primary function while its microphone contributes to the collective voice acquisition system. This multi-functionality allows the system to adapt to varying numbers of interaction partners without requiring a dedicated large array of microphones, as the same microphones are shared across different functional contexts.
Solution Approach 2:
The system uses the mobile objects themselves (which are already present and performing other functions) to provide the additional microphone resources needed for multi-person interaction. Instead of adding dedicated microphone arrays, the system leverages the existing mobile objects and their integrated microphones, allowing them to serve both their primary functions and the voice acquisition function simultaneously.
3Productivity
If a single mobile object is used for voice acquisition, then the device complexity is minimized, but the productivity of voice separation processing deteriorates when multiple sound sources are present
Solution Approach 1:
The voice acquisition function is segmented across multiple mobile objects, with each object contributing its microphone resources to the overall processing task. This segmentation allows the system to parallelize the voice capture process, improving the productivity of voice separation processing by simultaneously capturing sounds from multiple sources with distributed microphones rather than relying on a single mobile object.
Data Source
AI summary
A voice acquisition system includes a plurality of mobile objects each of which includes one or more microphones and is movable around a sound source; a sound source number estimating unit which estimates the number of sound sources in a vicinity of any of the mobile objects; and a control unit which controls positions of the mobile objects, wherein the control unit controls, based on the number of sound sources in a vicinity of a first mobile object, a position of a second mobile object which differs from the first mobile object, and the voice acquisition system acquires voice using both a microphone included in the first mobile object and a microphone included in the second mobile object.