In-Vehicle Voice Recognition with Device-Specific Detection Modes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition devices in vehicles face challenges in accurately identifying control requests from unclear user instructions, particularly when controlling devices with high operational importance, due to limitations in detection modes and environmental noise interference.
Innovation Solution
A voice recognition system that dynamically sets detection modes based on the control target device, using either natural language recognition or rule-based recognition, to improve accuracy and flexibility in interpreting user commands, and adjusts these modes based on the sound collection environment to minimize misrecognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single detection mode is used for all control target devices, then the system complexity is reduced, but the accuracy of control request identification deteriorates for devices with high operational importance
Solution Approach 1:
The patent applies local quality by configuring different detection modes for different control target devices based on their operational importance. Devices with high operational importance (e.g., steering, braking) use a first detection mode with stricter recognition rules, while devices with lower importance use a second detection mode with more flexible recognition. This resolves the contradiction by optimizing accuracy locally for critical devices without unnecessarily complicating the entire system.
2Adaptability or versatility
If natural language recognition is used to handle unclear instructions, then the flexibility in interpreting user commands is improved, but the reliability of control request identification deteriorates due to potential misrecognition
Solution Approach 1:
The patent changes the recognition parameters dynamically based on the control target device. For devices with high operational importance, the system uses stricter recognition parameters (first detection mode) that require clearer matching, reducing misrecognition. For devices with lower importance, more flexible parameters (second detection mode) are used to accommodate unclear instructions. This resolves the contradiction by adapting the recognition strictness parameter to the specific device context.
3Ease of operation
If ambiguous words are detected and recognized based on user intentions, then the ease of operation is improved, but the measurement precision of voice recognition deteriorates
Solution Approach 1:
The patent applies local quality by allowing ambiguous word recognition only for specific control target devices with lower operational importance. For critical devices like steering or braking, the system does not permit ambiguous interpretations even if it reduces convenience. For non-critical devices, ambiguous word recognition is enabled to improve ease of operation. This resolves the contradiction by localizing the tolerance for ambiguity to appropriate device contexts.
Data Source
AI summary
A voice recognition device receives requests to control devices installed in a moving body based on instructions voiced by a user. The voice recognition device includes a speech acquisition unit, a speech data conversion unit, a control target device identification unit, a detection mode setting unit and a control request identification unit. The speech acquisition unit acquires speech. The speech data conversion unit converts the acquired speech into speech data. The control target device identification unit that analyzes the speech data to identify the control target device. The detection mode setting unit that sets a detection mode for identifying the control request corresponding to the speech data in accordance with the control target device. The control request identification unit that analyzes the speech data to identify the control request with respect to the control target device, based on the set detection mode.