Autonomous Mobile Body Voice Recognition Noise Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous mobile body technologies face challenges in improving voice recognition accuracy due to the lack of consideration for non-target sounds, leading to increased noise levels and decreased Signal-to-Noise Ratio (SNR), which results in reduced recognition accuracy and user annoyance.
Innovation Solution
An information processor and method that enable an autonomous mobile body to execute motions that optimize sound recognition by creating and utilizing a noise map to avoid non-target sounds, thereby improving the SNR and enhancing voice recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the autonomous mobile body moves toward the estimated direction of the user, then the signal strength of the user's voice increases, but the input level of noise also increases
Solution Approach 1:
The system performs preliminary noise mapping before voice recognition to identify noise-prone areas in advance. By pre-characterizing the acoustic environment and marking noise sources, the mobile body can plan movement trajectories that avoid noise regions while still approaching the user, thus improving voice recognition accuracy without increasing noise exposure
Solution Approach 2:
The system continuously monitors the acoustic environment and provides feedback to adjust movement decisions. By real-time detection of noise levels and user position, the system dynamically modifies its approach strategy to maintain optimal signal-to-noise ratio, ensuring high voice recognition accuracy while minimizing noise input
2Speed
If the autonomous mobile body simply approaches the estimated direction of the user, then the response speed increases, but the voice recognition accuracy decreases due to increased noise
Solution Approach 1:
The system performs preliminary noise mapping to pre-identify safe approach paths. By having noise environment information available before movement, the system can calculate optimal trajectories that balance speed and recognition accuracy, avoiding noise regions while maintaining efficient response time
Solution Approach 2:
The system dynamically adjusts the approach strategy based on real-time noise conditions and user position. Rather than following a fixed path, the mobile body continuously adapts its trajectory to maintain optimal signal-to-noise ratio, achieving both fast response and high recognition accuracy through dynamic path optimization
Data Source
Figure 1
Figure 2
Figure 3
AI summary
[Object] To cause an autonomous mobile body to execute a motion for further improving accuracy of voice recognition. [Solution] There is provided an information processor including: an operation control unit that controls a motion of an autonomous mobile body acting on the basis of recognition processing, in a case where a target sound that is a target voice for voice recognition processing is detected, the operation control unit moving the autonomous mobile body to a position, around an approach target, where an input level of a non-target sound that is not the target voice becomes lower, the approach target being determined on the basis of the target sound. In addition, there is provided an information processing method including causing a processor to: control a motion of an autonomous mobile body acting on the basis of recognition processing, the controlling further including, in a case where a target sound that is a target voice for voice recognition processing is detected, moving the autonomous mobile body to a position, around an approach target, where an input level of a non-target sound that is not the target voice becomes lower, the approach target being determined on the basis of the target sound.