Directional Keyword Verification Using Vowel Pattern Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current keyword detection methods in electronic devices face challenges such as inaccurate automatic speech recognition, interference from undesired directions, background noise, and echo issues, which affect the quality and accuracy of keyword detection, particularly in real-time applications.
Innovation Solution
A directional keyword verification method using multiple microphones, which involves analyzing audio streams, determining vowel patterns, and employing beamforming and echo cancellation techniques to filter out undesired noise and verify keywords based on vowel onset locations and phonetic patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ASR engine is used for keyword detection, then speech recognition capability is provided, but detection accuracy is insufficient
Solution Approach 1:
The patent introduces vowel pattern matching as an intermediary verification step between ASR recognition and final keyword detection. The system first uses ASR to recognize words, then verifies the vowel patterns of recognized words against predefined vowel patterns of target keywords. This intermediary verification mechanism resolves the contradiction by maintaining ASR's speech recognition capability while adding a reliable verification layer that significantly improves detection accuracy and reduces false positives.
Solution Approach 2:
The patent segments the keyword detection process into distinct stages: ASR-based word recognition, vowel pattern extraction, vowel pattern matching, and final verification. By dividing the detection process into separable stages with specific functions, the system can optimize each stage independently - using ASR for broad speech recognition while applying precise vowel pattern matching for accurate keyword verification, thereby resolving the accuracy-reliability contradiction.
2Object-affected harmful factors
If multiple microphones are used for directional audio capture, then noise from undesired directions is reduced, but device complexity increases
Solution Approach 1:
The patent replaces complex mechanical acoustic beamforming systems with a simpler signal processing approach. Instead of using multiple microphones with complex spatial filtering hardware, the system uses single or dual microphones combined with software-based vowel pattern recognition and directional verification. This substitution of mechanical complexity with algorithmic simplicity resolves the contradiction by achieving noise rejection through signal processing rather than hardware complexity.
3Speed
If real-time processing is implemented for keyword verification, then response speed is improved, but computation time increases
Solution Approach 1:
The patent applies partial verification by focusing only on vowel patterns rather than analyzing complete phonetic structures or semantic meanings. The system extracts and verifies only the critical vowel portions of recognized words against predefined vowel templates, performing just enough verification to achieve accurate keyword detection without unnecessary computational overhead. This partial action approach resolves the real-time processing contradiction by achieving sufficient verification speed for practical applications.
Data Source
AI summary
The disclosure is directed to a directional keyword verification method and an electronic device using the same method. According to an exemplary embodiment, the proposed keyword verification method would include receiving an audio stream; analyzing the audio stream to obtain at least a word; determining whether the word matches a key word from a keyword database; assigning the word as a filler if the word does not match the keyword from the keyword database; determining whether a vowel pattern of the word matches the vowel pattern of the keyword if the word matches the key word from the keyword database; assigning the first word as a trigger or command word if the vowel pattern of the word matches the vowel pattern of the key word; and otherwise assigning the word as a filler if the vowel pattern of the word does not match the vowel pattern of the key word.