Voice Transcription Error Correction via Sound Similarity Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for inputting character strings, whether through keyboards or voice recognition, often result in typographical errors and false recognitions, requiring manual correction by users, which is time-consuming and inefficient.
Innovation Solution
A computer-based transcription method that accepts voice input, performs voice recognition, and corrects character strings by specifying portions with similarity to the original sound information, allowing users to easily identify and correct errors using a graphical user interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If voice recognition is used for inputting character strings, then input speed is improved, but accuracy deteriorates due to false recognitions and typographical errors
Solution Approach 1:
The system performs voice recognition to generate character strings, then uses sound information matching to provide feedback by identifying portions that match the original voice input. This feedback mechanism allows automatic correction of recognition errors while preserving the speed advantage of voice input.
Solution Approach 2:
The patent replaces manual mechanical correction (keyboard input) with an automatic sound-based correction system. By substituting the mechanical keyboard correction process with automated sound information comparison, the system maintains high input speed while improving accuracy.
2Measurement precision
If manual correction is performed to improve accuracy, then accuracy is improved, but time consumption increases
Solution Approach 1:
The system performs self-correction by automatically comparing sound information and identifying matching portions without requiring manual user intervention. This self-service mechanism improves accuracy while minimizing the time loss associated with manual correction.
Solution Approach 2:
The system performs preliminary sound information matching and identification of correctable portions before final correction is applied. This preliminary action prepares the correction data in advance, reducing the time needed for actual correction operations.
3Ease of operation
If voice recognition is used, then ease of operation is improved, but reliability deteriorates due to typographical errors and false recognitions
Solution Approach 1:
The system provides automatic feedback by comparing sound information and identifying portions that match the original voice input. This feedback loop enhances reliability by automatically detecting and correcting errors while maintaining the ease of voice-based operation.
4Productivity
If automatic correction is implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent replaces complex manual correction operations with an automated sound information matching system. By substituting manual processes with automated acoustic comparison, the system improves productivity while managing complexity through algorithmic rather than mechanical means.
Data Source
AI summary
A method for transcription is performed by a computer. The method includes: accepting input of a voice after causing a display unit to display a sentence including a plurality of words; acquiring first sound information being information concerning sounds corresponding to the sentence; acquiring second sound information being information concerning sounds of the voice accepted in the accepting; specifying a portion in the first sound information having a prescribed similarity to the second sound information; and correcting a character string in the sentence corresponding to the specified portion based on a character string corresponding to the second sound information.