Adaptive Beamforming Control for Voice Interference Suppression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional adaptive beamforming technologies do not dynamically adjust beam width and dead zone formation intensity based on the situation, leading to suboptimal performance when the angle between masking sound and the voice of interest changes, affecting the suppression of noise and voice interference.
Innovation Solution
An information processing device that acquires voice and noise signals from multiple microphones, using noise level and obstruction information to dynamically adjust beam width and dead zone formation intensity, employing adaptive beamforming techniques to optimize sound suppression.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If the beam width is narrowed and dead zone formation intensity is increased to suppress masking sound, then the suppression effect of masking sound improves, but the beam width becomes excessively narrow making slight deviations impermissible and decreasing the adaptive beamforming effect
Solution Approach 1:
The patent applies dynamics by making the beam width and dead zone formation intensity adjustable and changeable based on situational conditions. The control unit dynamically modifies these parameters according to the angular relationship between masking sound and object person voice, allowing the system to adapt to different acoustic environments rather than using fixed parameters.
Solution Approach 2:
The patent implements parameter changes by modifying the beam width and dead zone formation intensity as controllable parameters. The control unit changes these parameters based on measured angular relationships, transitioning between different parameter settings to optimize performance for wide-angle and narrow-angle masking scenarios.
2Object-affected harmful factors
If the beam width is narrowed to acquire sound in a narrow angular range, then the masking sound suppression improves, but the beam width becomes excessively narrow making slight deviations impermissible
Solution Approach 1:
The system dynamically adjusts beam width based on the angular separation between masking sound and object person voice. When masking sound comes from a wide angle, the beam width is narrowed for strong suppression. When masking sound is close to the object person direction, the beam width is widened to maintain reliability and accommodate slight deviations in speaking direction.
Solution Approach 2:
The control unit changes the beam width parameter according to the measured angular relationship. This parameter adjustment allows the system to optimize masking suppression when conditions permit, while maintaining reliability when the angular separation is small and narrow beams would be too sensitive to directional deviations.
3Device complexity
If fixed beam width and dead zone formation intensity are used, then the system complexity is reduced, but the effectiveness of sound suppression decreases when the angle between masking sound and object person voice varies
Solution Approach 1:
The patent implements feedback by measuring the angular relationship between masking sound and object person voice, then using this information to adjust beam width and dead zone formation intensity. The control unit continuously monitors acoustic conditions and modifies parameters accordingly, creating a closed-loop system that adapts to varying scenarios.
Solution Approach 2:
The patent achieves universality by creating a beamforming system that can handle multiple scenarios effectively. By making parameters adjustable based on angular relationships, the same system can optimally suppress masking sound whether it comes from wide angles or narrow angles, rather than requiring different fixed configurations for different situations.
Data Source
AI summary
An information processing device includes a signal acquisition unit that acquires a voice signal of an object person outputted from a mic array and a control unit that acquires at least one of noise level information indicating a noise level of noise and first information as information indicating whether or not an obstructor is speaking while obstructing speech of the object person and changes a beam width as a width of a beam corresponding to an angular range of acquired sound, centering at the beam representing a direction in which voice of the object person is inputted to the mic array, and dead zone formation intensity as a degree of suppressing at least one of the noise and voice of the obstructor inputted to the mic array based on at least one of the noise level information and the first information.