Host Device Voice Trigger Segmentation for Personalized Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional home automation systems inadequately support a wide range of users and devices, failing to tailor control operations to individual user lifestyles due to variability in device types and frequent network changes.
Innovation Solution
An electronic device with a host device that recognizes reserved voice expressions to control connected devices, allowing for personalized control based on user inputs, including the ability to register, recognize, and manage these expressions for tailored operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional speech recognition methods are used to control devices, then device operation is achieved, but the control does not sufficiently correspond to individual user lifestyles
Solution Approach 1:
The speech input is segmented into multiple components: a predetermined expression (trigger word) and a subsequent utterance. This segmentation allows the system to first identify user intent through the trigger word, then process specific commands in the subsequent utterance, enabling personalized control while maintaining operational simplicity.
Solution Approach 2:
The system performs preliminary recognition of predetermined expressions before processing the full speech input. By预先 identifying trigger words that indicate specific user intentions or lifestyles, the system can prepare appropriate response patterns in advance, making the overall interaction simpler and more adaptive to individual users.
2Adaptability or versatility
If multiple devices are connected via network for comprehensive control, then device functionality increases, but network stability decreases due to frequent device changes
Solution Approach 1:
The host device is designed with universal functionality to manage multiple different types of devices through a standardized speech recognition interface. By using a common predetermined expression recognition mechanism for all devices, the system achieves broad device compatibility while maintaining stable control operations despite frequent device additions or removals.
3Measurement precision
If speech analysis is performed continuously to recognize user intent, then control accuracy improves, but processing time increases
Solution Approach 1:
The system performs preliminary matching of predetermined expressions against the speech input stream. This preliminary action quickly identifies whether the speech contains recognized trigger words, allowing the system to either immediately execute known commands or initiate more detailed analysis only when necessary, thereby reducing overall processing time while maintaining recognition accuracy.
Solution Approach 2:
The system applies partial speech analysis by focusing primarily on recognizing predetermined expressions rather than analyzing every aspect of the speech input in detail. This partial analysis approach achieves sufficient recognition accuracy for control purposes while significantly reducing processing time compared to comprehensive speech analysis.
Data Source
AI summary
According to one embodiment, an electronic device determines whether one or more devices should be controlled based on a second utterance input subsequent to a first utterance input from outside in accordance with the first utterance. The electronic device includes a management unit and a controller. The management unit prepares and manages a determination audio data item for determining whether the first utterance is a desired utterance by utterances input from outside at a plurality of times, and determines whether the first utterance is the desired utterance using the prepared and managed determination audio data item. The controller controls the one or more devices based on the second utterance.