Vehicle Speech Command Disambiguation via Contextual Attributes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice recognition systems in vehicles often misinterpret general voice commands, leading to incorrect execution of actions, such as calling a contact at an unintended location, due to ambiguity in instructions.
Innovation Solution
The system receives voice commands, performs speech recognition, and uses secondary characteristics like date, time, proximity, and user affiliation to disambiguate the intended action, selecting the appropriate vehicle command based on these attributes to provide a clear recognition result.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech recognition is performed on general voice commands, then the system can execute actions based on user instructions, but the system may misinterpret the intended action due to ambiguity in the commands
Solution Approach 1:
The system performs preliminary actions by obtaining contextual information (date, time, user affiliation) before executing the voice command. This allows the system to pre-filter and evaluate multiple potential commands against available context, selecting the most probable intended command before execution, thereby resolving ambiguity without requiring additional user input.
Solution Approach 2:
The system introduces contextual information as an intermediary element between the voice command and the executed action. This intermediary layer (comprising date, time, and user affiliation data) mediates the interpretation process by providing additional criteria for disambiguation, allowing the system to select the correct command from multiple possibilities without directly modifying the voice recognition process itself.
2Measurement precision
If the system selects from multiple available commands based on contextual information, then the accuracy of command recognition improves, but the complexity of the system increases
Solution Approach 1:
The system segments the disambiguation process into distinct components: obtaining contextual information (date, time, user affiliation), evaluating multiple available commands against this context, and selecting the most probable command. This segmentation allows each component to be handled independently using simple, well-defined operations, reducing overall system complexity while maintaining high recognition accuracy.
Solution Approach 2:
The system changes parameters by incorporating additional contextual variables (date, time, user affiliation) into the command selection process. Rather than complicating the voice recognition algorithm itself, the system modifies the selection criteria by evaluating commands against these contextual parameters, thereby improving accuracy through parameter expansion rather than algorithmic complexity.
3Reliability
If contextual information such as date and time is used to determine the intended command, then misinterpretation of voice commands is reduced, but the amount of processing required increases
Solution Approach 1:
The system obtains contextual information (date, time, user affiliation) as a preliminary step before command execution. By gathering this information in advance and organizing it for quick access, the system enables rapid comparison against available commands during the selection process, minimizing additional processing time while improving reliability through comprehensive contextual evaluation.
Data Source
AI summary
A system and method of recognizing speech in a vehicle. The method includes receiving a voice command at the vehicle via a microphone in the vehicle, and obtaining a recognition result from speech recognition performed on the received voice command. The recognition result may represent the voice command and be indicative of any of two or more available vehicle commands. The method may further include selecting one of the two or more available vehicle commands based on a secondary characteristic and an attribute of the selected one of the vehicle commands. The system may be implemented as vehicle electronics that include a microphone located within the vehicle and configured to receive a voice command from a user located within the vehicle, and a controller in communication with the microphone. The controller may be configured to perform speech recognition on the voice command and obtain a disambiguated recognition result.