Trigger Word Recognition Accuracy in Electronic Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electronic devices often misrecognize ambient noise as a trigger word, activating the speech recognition mode unintentionally, or fail to recognize the trigger word due to noise, leading to inconvenient repeated utterances.
Innovation Solution
An electronic device and control method that improve trigger word recognition by using a processor to identify and update recognition and misrecognition information based on characteristic speech information, activating the speech recognition mode when a similarity threshold is met, and deactivating it when the similarity is below a certain threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the electronic device uses simple trigger word detection, then the device complexity is low, but the trigger word recognition accuracy deteriorates due to misrecognition of ambient noise
Solution Approach 1:
The system performs preliminary actions by collecting and storing characteristic information of trigger words and misrecognized words before actual recognition. This pre-prepared data is then used during recognition to compare and identify the trigger word, improving accuracy without adding real-time processing complexity.
Solution Approach 2:
The system implements feedback by using the collected characteristic information from previous trigger word utterances and misrecognition cases to improve future recognition decisions. The stored information serves as reference feedback that guides the recognition process, enabling the device to learn from past performance.
2Ease of operation
If the electronic device activates speech recognition mode frequently, then the ease of operation improves, but the loss of time increases due to unnecessary mode activations from misrecognition
Solution Approach 1:
The system replaces simple mechanical trigger detection with a more sophisticated information-based recognition mechanism. By substituting the basic detection approach with characteristic information comparison, the system maintains ease of operation while eliminating unnecessary activations through smarter recognition logic.
3Measurement precision
If the electronic device uses advanced recognition algorithms, then the trigger word recognition accuracy improves, but the processing time and energy consumption increase
Solution Approach 1:
The system uses copying by creating a database of characteristic information copies from previous trigger word utterances and misrecognition cases. During recognition, the system compares new input against these pre-created copies rather than performing complex analysis from scratch, reducing real-time energy consumption while maintaining high accuracy.
Data Source
AI summary
An electronic apparatus is provided. The electronic device includes: a storage configured to store recognition related information and misrecognition related information of a trigger word for entering a speech recognition mode; and a processor configured to identify whether or not the speech recognition mode is activated on the basis of characteristic information of a received uttered speech and the recognition related information, identify a similarity between text information of the received uttered speech and text information of the trigger word, and update at least one of the recognition related information or the misrecognition related information on the basis of whether or not the speech recognition mode is activated and the similarity.