Multi-language mixed language text processing method and system
A text processing and multilingual technology, applied in speech synthesis, speech analysis, instruments, etc., can solve problems such as lack of primary language and lack of phoneme pronunciation in secondary language, and achieve the effect of improving application effect
Active Publication Date: 2017-01-04
IFLYTEK CO LTD
View PDF4 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The embodiment of the present invention provides a multilingual mixed-language text processing method and system to solve the lack of phoneme pronunciation in the secondary language that is likely to cause the absence of the main language when the corresponding phonetic structure of the multilingual mixed-language text is greatly different in the prior art The problem
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0051] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and implementation manners.
[0052] Word-to-sound conversion refers to the process of using a sequence of phonetic symbols to represent the pronunciation content after converting a text sequence into a corresponding pronunciation content. For a single-language text, the corresponding phonetic conversion can be realized according to the pronunciation characteristics of the language. For multilingual mixed-language texts, traditional methods use the main language and sub-language pronunciation symbols to describe the pronunciation of the corresponding main and sub-language in the mixed text, and then map the sub-language phonetic symbols in the mixed text to the corresponding pronunciation symbols. The corresponding position of...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a multi-language mixed language text processing method and system. The multi-language mixed-language text processing method comprises the steps of determining a hyperphoneme set used for describing pronunciation conditions of a mixed language text according to a pronunciation principle, wherein the hyperphoneme set comprises a vowel phoneme set and a consonant phoneme set; collecting a mixed language text containing a primary language and a secondary language; extracting grammar units from the mixed language text; building a general dictionary of the mixed language text according to the grammar units and the hyperphoneme set, wherein the general dictionary contains the grammar units in the primary language and the secondary language and pronunciation information of the grammar units; and carrying out grapheme-to-phoneme conversion on the mixed language text according to the general dictionary to acquire a phonetic symbol sequence corresponding to the mixed language text. By using the method provided by the invention, problems of primary language missing and secondary language phoneme pronunciation missing are easily caused when the primary language and the secondary language corresponding to the multi-language mixed language text are greatly different in phonetic structure can be solved, and thus an application effect of a multi-language mixed language phonetic system in text processing is improved.
Description
Technical field [0001] The invention relates to the field of multilingual text information processing, in particular to a multilingual mixed language text processing method and system. Background technique [0002] With the popularization of computers and the Internet, and the need for internationalization, more and more texts are expressed in multiple languages, and a text often contains characters of multiple languages at the same time, that is, mixed-language text. Since the pronunciation and prosody of characters in different languages are different, it is difficult to process the mixed-language text using a unified method. For example, speech synthesis and speech recognition require unified processing of characters in different languages. [0003] The existing multilingual mixed-language text processing method generally uses the phoneme set corresponding to the main language to indicate the pronunciation of the text in the main language, and the sub-language uses the phone...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G10L13/08G10L25/48
Inventor 祖漪清闫润强王影胡国平胡郁刘庆峰
Owner IFLYTEK CO LTD