3 results about "Upper Case Letter" patented technology

The invention discloses an auxiliary reading system for language learning. The auxiliary reading system comprises a font generation module, a pronunciation labeling module, an output adaptation module and a learning auxiliary module, through Len3 / Len4 length limitation and capital letter design, traditional Pinyin character size limitation is broken through, the letter space is enlarged by 2.25-9 times, the readability of numbers and printing scenes is remarkably improved, and through actual measurement, the identification efficiency under a No.10 font is improved by more than 7.4 times. An HZ-IPA, HZ-EN and HZ-ES composite labeling mode is created for the first time, adaptive pronunciation rules are provided for English and Spanish native language persons, the problems of "ng" pronunciation divergence and the like are solved, the negative migration influence of the native language is reduced, and the pronunciation accuracy of non-native language persons is improved by 60%.

This invention discloses a text pronunciation optimization method and system for speech synthesis, belonging to the field of speech synthesis management technology. In this method, after emotional processing, long sentences are split into segments based on a triple rule system of semantic blocks, classical Chinese function words, and character length. The English portion of the text undergoes layered processing, distinguishing between pure uppercase letter combinations and regular English words, adding splitting and prosodic markers to pure uppercase letter combinations, and generating optimized text pronunciation information. This invention breaks through the limitations of existing single-rule adaptation in speech synthesis text processing, pioneering a multi-dimensional layered optimization framework that integrates technologies such as semantic parsing of numbers and operators, scene-based matching of polyphonic characters, emotional markers for literary texts, and semantic long sentence splitting. It designs multiple exclusive optimization rules for the speech synthesis and reading needs of literary and everyday spoken texts, solving the core pain point of existing technologies that emphasize generality but neglect specific scenarios.

To enable capital letters and small letters in a character string inputted by handwriting to be discriminated with high accuracy by considering the size of an input field displayed on a screen.SOLUTION: A handwriting input device includes conversion means for converting a handwritten character into character data by performing character recognition, display control means for displaying the converted character data in a prescribed input field instead of a handwritten character, first determination means for determining whether a prescribed character in which a capital letter and a small letter are stored in advance as similar letters is included in the character data, and second determination means for determining whether a handwritten character is a capital letter or a small letter on the basis of a size in the height direction of the prescribed input field and a size of the height direction of the handwritten character in the case that the prescribed character with the capital letter and the small letter stored in advance as similar letters is included in the character data. The display control means displays a handwritten character as character data of a capital letter or a small letter in the prescribed input field in accordance with a determination result of the second determination means.SELECTED DRAWING: Figure 9