Word Extraction Device Using Utterance Timing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing word extraction devices rely solely on appearance frequency, which can lead to inaccurate extraction of important words, as they do not consider the timing and context of utterances.
Innovation Solution
A word extraction device and method that converts speech information into text, calculates importance levels based on the timing of keyword utterances, and uses a keyword database to weight the importance of words, incorporating appearance frequencies and utterance timing to improve extraction precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If only appearance frequency is used to extract important words, then the extraction process is simple, but the extraction precision deteriorates
Solution Approach 1:
The patent changes the parameters used for word importance evaluation from only appearance frequency to a composite parameter that includes appearance frequency, timing information, and keyword co-occurrence relationships. This allows the system to capture contextual nuances while maintaining a systematic evaluation framework.
Solution Approach 2:
The patent introduces timing information and keyword databases as intermediary elements that mediate between raw speech data and final word extraction. These intermediaries provide contextual framework that enhances precision without requiring direct complex analysis of every word occurrence.
2Measurement precision
If timing information is incorporated into word extraction, then extraction precision is improved, but computational complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-processing speech into text data and pre-identifying keywords from a keyword database before conducting the main importance calculation. This staged approach breaks down complex computation into manageable steps that can be executed efficiently.
Solution Approach 2:
The patent segments the word extraction process into distinct stages: speech-to-text conversion, keyword extraction from database, timing information capture, and importance level calculation. Each segment handles a specific aspect, reducing overall computational complexity through modular processing.
3Measurement precision
If keyword databases are used to weight words, then extraction accuracy is improved, but the system requires more resources
Solution Approach 1:
The system uses pre-existing keyword databases that contain curated information about important terms and concepts. By leveraging these pre-processed resources, the system avoids the need to build and maintain its own extensive knowledge base, thus reducing resource requirements while maintaining high accuracy.
Data Source
AI summary
A word extraction method according to at least one embodiment of the present disclosure includes: converting, with at least one processor operating with a memory device in a device, received speech information into text data; converting the text data into a string of words including a plurality of words; extracting, with the at least one processor operating with the memory device in the device, a keyword included in a keyword database from the plurality of words; and calculating, with the at least one processor operating with the memory device in the device, importance levels of the plurality of words based on timing of utterance of the keyword and timing of utterance of each of the plurality of words.