Voice GUI Browse Mode for Wakeword-Free Command Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice-based interaction systems require repeated use of a wakeword for each command, leading to increased latency and reduced responsiveness in controlling graphical user interfaces.
Innovation Solution
Implementing a local language model on the computing device to process audio data without a wakeword for a predetermined time period, restricting commands to a set of predefined actions, and enabling continuous voice-based interactions within a browse mode.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a wakeword is required for each voice command, then the system can reliably distinguish valid commands from background noise, but the latency increases and responsiveness decreases
Solution Approach 1:
The system performs preliminary action by detecting the wakeword in advance and transitioning to a browse mode where subsequent voice commands can be processed without requiring the wakeword again. This preliminary detection enables a temporary state where the system is more responsive to follow-up commands, thus reducing latency while maintaining reliable command distinction through the initial wakeword trigger.
2Productivity
If voice-based interactions are enabled without wakeword for extended periods, then responsiveness improves, but false activations from background noise increase
Solution Approach 1:
The system implements periodic action by enabling wakeword-free voice processing only for a predetermined time period after initial wakeword detection. Once this time period expires, the system automatically returns to requiring wakeword for each command. This periodic switching between modes allows the system to maintain high productivity during active voice sessions while preventing false activations during inactive periods.
Data Source
AI summary
Techniques for voice-based interactions are described. In an example, a device presents a user interface on a display. The device starts an operational mode of the device. The operational mode restricts voice-based interactions with the user interface to a set of commands. The set of commands is defined in a language model that is stored on the device. Further, the device receives, at a microphone of the device, audio data corresponding to a natural language utterance and generates, from the audio data, text data that corresponds to the natural language utterance. The device determines, based at least in part on the language model, that semantics of the text data correspond to a command from the set of commands and presents, on the display, an outcome of performing the command.