Hotword Model Update via Modified Input Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current voice assistants face challenges in improving hotword detection performance while maintaining consistent user experience without relying on wake-up words and reducing resource consumption such as memory and power.
Innovation Solution
The proposed solution involves an electronic device that identifies modified hotwords from user inputs received after failing to detect a hotword, monitors subsequent user inputs within a specified time, and updates the hotword model based on user feedback to enhance detection performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional hotword detection methods are used, then the voice assistant can operate, but the hotword detection performance is insufficient and resource consumption is high
Solution Approach 1:
The system performs preliminary actions by monitoring user inputs within a specified time window after a failed hotword detection, proactively gathering data to update the hotword model before the next detection attempt, thereby improving future detection accuracy without continuous high resource consumption
Solution Approach 2:
The system implements feedback mechanisms by using monitored user inputs to update the hotword model, creating a closed-loop system where detection failures trigger learning processes that improve subsequent detection performance while optimizing resource usage through selective updating
2Measurement precision
If the hotword model is continuously updated, then the detection performance improves, but the device complexity and resource usage increase
Solution Approach 1:
The system applies periodic action by updating the hotword model only at specific intervals triggered by failed detections followed by successful user inputs within a specified time window, rather than continuously updating, thereby reducing computational overhead and system complexity while maintaining performance improvement
3Ease of operation
If wake-up words are used, then the voice assistant can be activated, but the user experience consistency deteriorates
Solution Approach 1:
The system applies self-service by enabling the hotword model to automatically learn and adapt from user inputs without requiring manual wake-up commands or external intervention, allowing the device to serve itself in improving detection accuracy while providing consistent user experience
Data Source
AI summary
An electronic device may include a user interface, a processor operatively connected to the user interface, and a memory operatively connected to the processor. The memory may store instructions that, when executed, may cause the processor to identify a modified hotword included in the first user input in response to failing to detect a hotword included in a first user input received using the user interface, to monitor a second user input received during a specified time using the user interface, to identify an existing hotword corresponding to the modified hotword using the second user input, to provide response data indicating whether to update the existing hotword using the modified hotword, through the user interface, and to update a hotword model based on a user input to the response data. Moreover, various example embodiments found through the disclosure, as well as other embodiments, are possible.