Voice Output Device Compound Word Pronunciation Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice output devices, such as electronic dictionaries, struggle to accurately reproduce the pronunciation of compound words, leading to a feeling of incorrectness in voice output.
Innovation Solution
A voice output device with a compound word voice data storage unit, text display unit, word designation unit, compound word detection unit, and voice output unit, which detects and outputs voice data for compound words by associating voice data with each compound word and allowing users to designate words for accurate voice output.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If voice data is synthesized based on phonetic symbol information of individual words, then voice output can be generated, but connection between words cannot be reproduced accurately causing wrong pronunciation feeling
Solution Approach 1:
The patent segments voice data storage into two distinct parts: individual word voice data and compound word voice data. This segmentation allows the system to store and reproduce compound words with their correct connected pronunciation separately from individual words, thereby resolving the pronunciation accuracy issue while maintaining manageable data structure complexity.
Solution Approach 2:
The patent adds a new dimension to the voice data storage structure by introducing compound word voice data that operates at a different level than individual word data. This dimensional addition enables the system to handle compound word pronunciation as a distinct entity, achieving accurate connection reproduction without overwhelming complexity in the base word-level storage system.
2Reliability
If compound word voice data is stored separately for each compound word, then accurate voice output is achieved, but data storage complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-storing compound word voice data in the database during system setup. This allows the system to quickly retrieve and output accurate compound word pronunciation without performing complex real-time synthesis, thereby achieving high reliability while avoiding the need for extensive computational resources during operation.
Solution Approach 2:
The patent changes the parameter of voice data organization by storing compound words as complete phonetic sequences rather than as assemblies of individual word phonemes. This parameter change enables accurate compound word reproduction while actually reducing data volume compared to storing multiple individual word recordings for each compound word combination.
3Reliability
If the system detects compound words and outputs stored voice data, then pronunciation accuracy improves, but processing time increases
Solution Approach 1:
The patent uses copying by storing complete compound word voice recordings in the database rather than synthesizing them from individual words during operation. This copying approach allows instant retrieval of pre-recorded accurate compound word pronunciation, significantly reducing processing time while maintaining high accuracy.
Solution Approach 2:
The system performs preliminary action by pre-processing and storing compound word voice data during database setup. This preliminary preparation eliminates the need for complex real-time detection and synthesis operations, thereby reducing processing time during actual voice output operations while ensuring accurate pronunciation.
Data Source
AI summary
A voice output device, includes: a compound word voice data storage unit that stores voice data in association with each of compound words which is formed of a plurality of words; a text display unit that displays text containing a plurality of words; a word designation unit that designates any of the words in the text displayed by the text display unit as a designated word based on a user's operation; a compound word detection unit that detects a compound word in which voice data is stored in the compound word voice data storage unit, from among the plurality of words in the text containing the designated word; and a voice output unit that outputs voice data corresponding to the compound word detected by the compound word detection unit as a voice.