Voice Command Response Control Using Relative Receipt Time
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In environments with multiple voice-capable devices in close proximity, a voice command intended for one device can inadvertently trigger actions in other devices due to overlapping reception, leading to unintended operational changes.
Innovation Solution
Implementing tightly time-synchronized clocks among voice-capable devices to determine which device received a voice command first, allowing only the initial recipient to trigger a response and preventing other devices from doing so.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If multiple voice-capable devices are deployed in close proximity to provide comprehensive voice control coverage, then the accessibility and ease of operation of the system is improved, but the reliability deteriorates because voice commands intended for one device can inadvertently trigger actions in other devices
Solution Approach 1:
The system performs preliminary actions by having devices continuously monitor for wake phrases and prepare to execute commands before the user actually speaks. When a wake phrase is detected, the system pre-positions the response mechanism so that when the voice command follows, the device is ready to execute immediately. This preliminary preparation allows multiple devices to be active simultaneously without causing unintended actions, as each device waits for its designated turn based on the wake phrase timing.
Solution Approach 2:
The system implements feedback mechanisms where devices broadcast their wake phrase detection status and command execution state to other devices in the network. When Device A detects a wake phrase and begins processing a command, it sends feedback signals to Device B and Device C, causing them to suppress their own response mechanisms. This feedback loop ensures that only the device that detected the wake phrase first will execute the command, preventing unintended actions while maintaining the accessibility of multiple devices.
2Speed
If voice-capable devices continuously monitor for commands to respond immediately, then the responsiveness and speed of the system is improved, but the device complexity increases due to the need for time-synchronization mechanisms
Solution Approach 1:
The time-synchronization mechanism serves multiple functions simultaneously: it coordinates wake phrase detection timing, manages command execution priority, and prevents unintended device responses. Rather than implementing separate systems for each function, the patent makes the time-synchronization mechanism multi-functional, reducing overall system complexity while maintaining fast response speeds. The same timing infrastructure that enables immediate command response also manages device communication protocols and priority arbitration.
3Reliability
If only one device can execute commands at a time to prevent unintended actions, then the reliability is improved, but the productivity decreases because commands may be delayed until the correct device is ready
Solution Approach 1:
Devices perform preliminary actions by continuously monitoring for wake phrases and pre-positioning their response mechanisms. When a wake phrase is detected, the system immediately begins the command execution process without delay. This preliminary preparation eliminates the need for devices to wait idly, as they are already in a ready state waiting for the actual voice command. The wake phrase detection and preparation occurs in parallel across all devices, maintaining high productivity while ensuring only the correct device executes the command.
Data Source
AI summary
A method and system for controlling response to a voice-command utterance. An example method includes a computing system that is associated with the first device carrying out operations upon the first device receiving the voice-command utterance. The operations include (a) making a determination of whether any of one or more second devices received the voice-command utterance before the first device received the voice-command utterance and (b) controlling whether the computing system will trigger an action in response to the first device receiving the voice-command utterance, with the controlling being based on the determination of whether any of the one or more second devices received the voice-command utterance before the first device received the voice-command utterance. In an example implementation, the action could be controlling operation of a control target such as one or more lights.