Voice Command Processing with Wake-Free Follow-Up Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice command systems in devices like smart speakers and smartphones require a wake word for every command, which can be inconvenient, especially when users have dirty hands or are engaged in activities that make button pressing difficult.
Innovation Solution
The system allows for voice commands to be accepted without a wake word for a predetermined period after the initial command, utilizing multithreading to execute applications and recognizing subsequent commands based on parameters extracted from previous speech or user actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a wake word is required for every voice command, then the system can reliably distinguish user commands from background speech, but the ease of operation deteriorates when users have dirty hands or are engaged in activities that make button pressing difficult
Solution Approach 1:
The system performs preliminary action by detecting a wake word once to activate a temporary command acceptance state. During this activated state, subsequent voice commands can be processed without requiring repeated wake word detection, thereby improving ease of operation while maintaining reliability through the initial wake word trigger.
2Ease of operation
If the system accepts voice commands without wake word for a predetermined period, then the ease of operation improves for continuous commands, but the reliability deteriorates due to potential misrecognition of background speech
Solution Approach 1:
The system applies dynamics by implementing a time-based dynamic state transition. After wake word detection, the system enters a temporary high-sensitivity state for a predetermined period during which commands are accepted without wake word. The system dynamically adjusts its recognition threshold and state based on elapsed time, thereby balancing ease of operation for continuous commands with reliability through automatic state expiration.
3Productivity
If multithreading is used to execute applications during voice command processing, then the productivity improves by handling multiple commands simultaneously, but the device complexity increases
Solution Approach 1:
The system applies segmentation by dividing command processing into separate thread modules. Each voice command is handled by dedicated processing threads that can execute simultaneously, improving productivity. The segmentation separates wake word detection, command recognition, and application execution into distinct functional threads, managing complexity through modular organization.
Data Source
AI summary
An information processing device includes a microphone that acquires a speech signal, and at least one processor. In a case in which the processor determines a wake word is included in first recognition data derived from the speech signal, when the processor determines that control information, that is information related to a control processing, is included in second recognition data derived from the speech signal after the wake word, the processor executes a first control processing corresponding to the control information. When the processor determines that the control information is included in third recognition data derived from the speech signal acquired by the microphone during a first period after a predetermined condition related to an event that occurs after the wake word is satisfied or during execution of the first control processing, the processor executes a second control processing corresponding to the control information included in the third recognition data.