Navigation Apparatus Speech Recognition Error Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation apparatuses face difficulties in correcting speech recognition misrecognition efficiently, as they require cumbersome user operations on software keyboards or remote controls, which compromise hands-free convenience and increase processing burden.
Innovation Solution
A navigation apparatus that utilizes storage of keywords and phonetic symbols, speech recognition, word display, candidate presentation for one-symbol corrections, and geographical point search, allowing users to correct misrecognized words with fewer operations and reduced processing burden by displaying candidates with different first phonetic symbols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a software keyboard on a touch panel or remote control is operated to correct misrecognition, then the correction can be made, but many operations must be repeatedly carried out which is troublesome and loses hands-free convenience
Solution Approach 1:
The system pre-generates and displays candidate words with different first phonetic symbols before the user needs to correct misrecognition. This preliminary preparation of correction candidates eliminates the need for users to navigate through lengthy software keyboards or perform multiple manual operations, directly resolving the contradiction between hands-free convenience and the number of operations required.
2Ease of operation
If misrecognition is corrected by speech, then the user operation is easy, but the burden at the apparatus side becomes large
Solution Approach 1:
The correction process is segmented by focusing only on words with different first phonetic symbols rather than requiring complete speech recognition re-processing. This segmentation approach maintains user operation simplicity while significantly reducing the processing burden on the apparatus, as only specific candidate words need to be generated and displayed rather than performing comprehensive speech analysis.
3Reliability
If all possible word corrections are presented, then the user can find the correct word, but the processing burden and display complexity increase significantly
Solution Approach 1:
Instead of presenting all possible word corrections uniformly, the system applies local quality by selectively generating and displaying only words with different first phonetic symbols. This localized approach to correction candidates maintains reliable correct word identification while significantly reducing data processing burden and display complexity, as the system focuses on the most likely error patterns rather than exhaustively checking all possibilities.
Data Source
AI summary
In this navigation apparatus, when speech recognition of inputted speech is carried out, keywords included in the content of the recognized speech are searched from a dictionary DB, and then these words are displayed as keywords of a POI search. When a correction of a keyword is required by the user, because most errors occur in the first phonetic symbol of the misrecognized word, a search of words each having phonetic symbols in which the first phonetic symbol of the misrecognized word is changed from the phonetic symbols of the word to be corrected (i.e., a search of words having one different first phonetic symbol) is carried out to present candidates for correction. In this navigation apparatus, because the displayed candidates for correction are limited to words having a different first phonetic symbol which has a high possibility of being the cause of misrecognition, the user can correct the misrecognized keyword by a simple operation. Further, it is possible to reduce the process burden as compared to the conventional misrecognition correction processes.