Mobile Audio Input Routing With Voice-Validated Call Placement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Speech recognition systems in mobile devices often fail to accurately distinguish command phrases due to background noise or obstructions, leading to unintended calls, which can have negative consequences.
Innovation Solution
A mobile device validates command phrases by analyzing a trigger phrase followed by a call command and parameter, using voice recognition engines to confirm the accuracy of the command and contact information, and employs a validation threshold to ensure accurate call placement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If speech recognition systems are made more sensitive to trigger phrases, then the system becomes more responsive to user commands, but the system becomes more prone to false activation from background noise
Solution Approach 1:
The system performs preliminary analysis of the audio environment by capturing background noise samples before triggering speech recognition. This preliminary action allows the system to establish a baseline of ambient sounds, enabling more accurate distinction between genuine trigger phrases and background noise later in the process
Solution Approach 2:
The system uses feedback mechanisms where the output of one speech recognition pass informs subsequent processing. Validation phrases are used to confirm initial trigger detection, and the system continuously refines its understanding of the audio environment based on incoming signals, adjusting its sensitivity dynamically
2Reliability
If the system validates command phrases more thoroughly, then the accuracy of call placement improves, but the time required to process the command increases
Solution Approach 1:
The system performs preliminary validation by checking if the detected trigger phrase matches known command patterns before initiating full processing. Contact information is pre-validated and stored in accessible formats, so that when a command is issued, the system can quickly match the intent with pre-verified contact data rather than processing everything from scratch
Solution Approach 2:
The validation process is segmented into multiple stages: initial trigger detection, command phrase validation, and final confirmation. Each stage has specific validation criteria and can terminate early if confidence thresholds are met, preventing unnecessary processing time while maintaining accuracy
Data Source
AI summary
A method on a mobile device for a wireless network is described. An audio input is monitored for a trigger phrase spoken by a user of the mobile device. A command phrase spoken by the user after the trigger phrase is buffered. The command phrase corresponds to a call command and a call parameter. A set of target contacts associated with the mobile device is selected based on respective voice validation scores and respective contact confidence scores. The respective voice validation scores are based on the call parameter. The respective contact confidence scores are based on a user context associated with the user. A call to a priority contact of the set of target contacts is automatically placed if the voice validation score of the priority contact meets a validation threshold and the contact confidence score of the priority contact meets a confidence threshold.