CN101984489A - Method for realizing numerical pronunciation of Chinese content by using Chinese TTS - Google Patents
Method for realizing numerical pronunciation of Chinese content by using Chinese TTS Download PDFInfo
- Publication number
- CN101984489A CN101984489A CN2010105352691A CN201010535269A CN101984489A CN 101984489 A CN101984489 A CN 101984489A CN 2010105352691 A CN2010105352691 A CN 2010105352691A CN 201010535269 A CN201010535269 A CN 201010535269A CN 101984489 A CN101984489 A CN 101984489A
- Authority
- CN
- China
- Prior art keywords
- chinese
- numeral
- digital
- tts
- bit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Document Processing Apparatus (AREA)
Abstract
The invention relates to a method for realizing numerical pronunciation of Chinese content by using Chinese TTS, which comprises the following steps: (1) converting a number into a Chinese character string corresponding to the number; and (2) realizing Chinese pronunciation of the Chinese character string by calling CTTS. The method for realizing numerical pronunciation of Chinese content by using Chinese TTS, which is provided by the invention, has the advantages of simple and quick conversion algorithm processes, convenient use and wide usability and practicability.
Description
Technical field
The present invention relates to a kind of manner of articulation, relate in particular to a kind of method of utilizing Chinese TTS to realize Chinese content numeric utterance.
Background technology
In the application program of the function that Chinese TTS pronunciation is much arranged, have arabic numeral in the centre of Chinese content, pronunciation but is English, not too appropriate, brings very big puzzlement to the user, reasonably disposal route is allow these numerals send out sound Chinese.Along with the continuous development of voice technology, use the program of Chinese TTS more and more, this inconsistent pronunciation needs perfect, and it is very necessary finding the algorithm that addresses this problem, and product also is one well promotes.
Summary of the invention
In order to solve the above-mentioned technical matters that exists in the background technology, a kind of transfer algorithm process simple and fast provided by the present invention, easy to use, have a method that the utilization Chinese TTS of usability and practicality widely realizes Chinese content numeric utterance.
Technical solution of the present invention is: the invention provides a kind of method of utilizing Chinese TTS to realize Chinese content numeric utterance, its special character is: the Chinese TTS of described utilization realizes that the method for Chinese content numeric utterance may further comprise the steps:
1) numeral is transformed into the pairing Chinese character string of this numeral;
2) realize the Chinese character string is carried out Chinese pronunciations by calling CTTS.
Above-mentioned steps 1) specific implementation is:
1.1) read digital mode according to Chinese and set up the digital conversion corresponding tables;
1.2) according to the digital conversion corresponding tables numeral is carried out the Chinese conversion.
Above-mentioned steps 1.1) in:
Digital mode read in described Chinese: described numeral comprises two parts of basic number word and position; Described basic numeral is 0,1,2,3,4,5,6,7,8 and 9; Institute's rheme is hundred billion, 10,000,000,000,1,000,000,000, hundred million, ten million, 1,000,000,100,000, ten thousand, thousand, hundred, ten and individual;
Described digital conversion corresponding tables is:
Zero in the described basic digital corresponding tables, 0,1,2,3,4,5,6,7,8,9 of one, two, three, four, five, six, seven, eight, nine corresponding respectively numerals substantially;
In the institute rheme conversion corresponding tables hundred billion, 10,000,000,000,1,000,000,000, hundred million, ten million, 1,000,000,100,000, ten thousand, thousand, hundred, ten and individual difference corresponding successively from the most significant digit to the lowest order.
Above-mentioned numeral is decimal or integer.
When above-mentioned numeral is integer, described step 1.2) specific implementation is:
1.2.1) to obtain numeral according to the number of arabic numeral be several figure places;
1.2.2) begin to read one by one from the most significant digit of numeral, earlier basic numeral is converted into corresponding Chinese by basic digital corresponding tables, find the corresponding Chinese in position according to position conversion corresponding tables then.
Above-mentioned steps 1.2.2) when this bit digital that reads was 0, its concrete conversion regime was in:
If this bit digital is hundred million, this bit digital part Chinese does not have, and bit position Chinese is hundred million;
If this bit digital is a myriabit, if three or two or of its front have numeral substantially, this bit digital part Chinese does not have, and bit position Chinese is ten thousand;
If one of the back of this bit digital remains 0, then continue next bit; If the right and wrong 0 in the back of this bit digital, this corresponding Chinese are zero.
If this position is a position, then directly finish.
Above-mentioned steps 1.2.2) when these bit digital right and wrong 0 of reading, its concrete conversion regime is in:
If this bit digital is a position, numeral is converted into corresponding Chinese, do not need bit position;
If this bit digital is ten, and numeral be 1 and also this arabic numeral most significant digit be ten, do not need numerical portion Chinese, only need bit position;
When above-mentioned numeral is decimal, described step 1.2) specific implementation is:
The radix point front is if 0, only one zero of integral part Chinese; If radix point front non-0, fraction part is this digital conversion corresponding Chinese according to basic digital conversion table, integral part is converted into basic numeral corresponding Chinese earlier according to basic digital conversion table, finds the corresponding Chinese in position according to position conversion corresponding tables then.
Advantage of the present invention is:
This method is exactly in order to solve when application call Chinese TTS pronounces, in the middle of the Chinese content of pronunciation arabic numeral are arranged, by this algorithm these arabic numeral are converted into corresponding Chinese character string, call Chinese TTS then, the Chinese pronunciations that makes it send out correct.This algorithm using method is simple, and simple and fast is realized easily, and is easy to use, has usability and practicality widely, program done very little change just can realize.
Description of drawings
Fig. 1 is a manner of articulation schematic flow sheet provided by the present invention.
Embodiment
Referring to Fig. 1, the present invention is a kind of method of utilizing Chinese TTS to realize Chinese content numeric utterance, dominant ideas of the present invention are to run into numeral to convert it into Chinese character string into correspondence when CTTS pronounces, and realize numeral is carried out Chinese pronunciations by calling CTTS again.When solving the arabic numeral Chinese TTS pronunciation in the Chinese content, most important part is that these arabic numeral are converted into corresponding Chinese character string.
This method may further comprise the steps:
1) numeral is transformed into the pairing Chinese character string of this numeral, this numeral can be decimal or integer, and its specific implementation is:
1.1) read digital mode according to Chinese and set up the digital conversion corresponding tables;
Digital mode read in Chinese: numeral comprises two parts of basic number word and position; Basic numeral is 0,1,2,3,4,5,6,7,8 and 9; The position is hundred billion, 10,000,000,000,1,000,000,000, hundred million, ten million, 1,000,000,100,000, ten thousand, thousand, hundred, ten and individual;
The digital conversion corresponding tables is:
Zero in the basic digital corresponding tables, 0,1,2,3,4,5,6,7,8,9 of one, two, three, four, five, six, seven, eight, nine corresponding respectively numerals substantially;
In the position conversion corresponding tables hundred billion, 10,000,000,000,1,000,000,000, hundred million, ten million, 1,000,000,100,000, ten thousand, thousand, hundred, ten and individual difference corresponding successively from the most significant digit to the lowest order.
1.2) according to the digital conversion corresponding tables numeral is carried out the Chinese conversion.
When numeral is integer, step 1.2) specific implementation is:
1.2.1) to obtain numeral according to the number of arabic numeral be several figure places;
1.2.2) begin to read one by one from the most significant digit of numeral, earlier basic numeral is converted into corresponding Chinese by basic digital corresponding tables, find the corresponding Chinese in position according to position conversion corresponding tables then.
When this bit digital that reads was 0, its concrete conversion regime was:
If this bit digital is hundred million, this bit digital part Chinese does not have, and bit position Chinese is hundred million;
If this bit digital is a myriabit, if three or two or of its front have numeral substantially, this bit digital part Chinese does not have, and bit position Chinese is ten thousand;
If one of the back of this bit digital remains 0, then continue next bit; If the right and wrong 0 in the back of this bit digital, this corresponding Chinese are zero.
If this position is a position, then directly finish.
When these bit digital right and wrong 0 of reading, its concrete conversion regime is:
If this bit digital is a position, numeral is converted into corresponding Chinese, do not need bit position;
If this bit digital is ten, and numeral be 1 and also this arabic numeral most significant digit be ten, do not need numerical portion Chinese, only need bit position;
When numeral is decimal, described step 1.2) specific implementation is:
The radix point front is if 0, only one zero of integral part Chinese; If radix point front non-0, fraction part is this digital conversion corresponding Chinese according to basic digital conversion table, integral part is converted into basic numeral corresponding Chinese earlier according to basic digital conversion table, finds the corresponding Chinese in position according to position conversion corresponding tables then.
2) realize the Chinese character string is carried out Chinese pronunciations by calling CTTS.
Divide three ones to describe the present invention in detail with this scope of natural number 1-999999999999 below:
According to the rule of Chinese reading word, a general numeral is made up of two parts, basic numeral and position.For example: 4520 read 4,520, and here the four, five, the 2nd, numeral, the thousand, hundred, the tenth, position.
Set up two corresponding tables according to this rule.
1, digital conversion corresponding tables:
Numeral: [0,1,2,3,4,5,6,7,8,9]
Corresponding Chinese: [zero, one, two, three, four, five, six, seven, eight, nine].
2, position conversion corresponding tables:
(individual position) corresponding table is from most significant digit (hundred billion) to lowest order:
[thousand, hundred, ten, hundred million, thousand, hundred, ten, ten thousand, thousand, hundred, ten, individual].
For example: 234500 can translate into Chinese character string 234,500; 26.458 can translate into Chinese character string 26 458.
Again for example, 150.26 can translate into Chinese character string 150 26.
The present invention is a kind of method of utilizing Chinese TTS to realize Chinese content numeric utterance, promptly is to run into numeral to convert it into Chinese character string into correspondence when CTTS pronounces, and realizes numeral is carried out Chinese pronunciations by calling CTTS again.Call Chinese TTS one section Chinese content is pronounced,, call this algorithm and this digital translation can be become corresponding Chinese character string if run into arabic numeral when (comprising integer, decimal).The present invention can be applicable to the pronunciation that solves arabic numeral in the program of all Chinese TTS pronunciations, transfer algorithm process.
Claims (8)
1. method of utilizing Chinese TTS to realize Chinese content numeric utterance, it is characterized in that: the Chinese TTS of described utilization realizes that the method for Chinese content numeric utterance may further comprise the steps:
1) numeral is transformed into the pairing Chinese character string of this numeral;
2) realize the Chinese character string is carried out Chinese pronunciations by calling CTTS.
2. the Chinese TTS of utilization according to claim 1 realizes the method for Chinese content numeric utterance, and it is characterized in that: the specific implementation of described step 1) is:
1.1) read digital mode according to Chinese and set up the digital conversion corresponding tables;
1.2) according to the digital conversion corresponding tables numeral is carried out the Chinese conversion.
3. the Chinese TTS of utilization according to claim 2 realizes the method for Chinese content numeric utterance, it is characterized in that: described step 1.1):
Digital mode read in described Chinese: described numeral comprises two parts of basic number word and position; Described basic numeral is 0,1,2,3,4,5,6,7,8 and 9; Institute's rheme is hundred billion, 10,000,000,000,1,000,000,000, hundred million, ten million, 1,000,000,100,000, ten thousand, thousand, hundred, ten and individual;
Described digital conversion corresponding tables is:
Zero in the described basic digital corresponding tables, 0,1,2,3,4,5,6,7,8,9 of one, two, three, four, five, six, seven, eight, nine corresponding respectively numerals substantially;
In the institute rheme conversion corresponding tables hundred billion, 10,000,000,000,1,000,000,000, hundred million, ten million, 1,000,000,100,000, ten thousand, thousand, hundred, ten and individual difference corresponding successively from the most significant digit to the lowest order.
4. realize the method for Chinese content numeric utterance according to claim 2 or the Chinese TTS of 3 described utilizations, it is characterized in that: described numeral is decimal or integer.
5. the Chinese TTS of utilization according to claim 4 realizes the method for Chinese content numeric utterance, it is characterized in that: when described numeral is integer, described step 1.2) specific implementation be:
1.2.1) to obtain numeral according to the number of arabic numeral be several figure places;
1.2.2) begin to read one by one from the most significant digit of numeral, earlier basic numeral is converted into corresponding Chinese by basic digital corresponding tables, find the corresponding Chinese in position according to position conversion corresponding tables then.
6. the Chinese TTS of utilization according to claim 5 realizes the method for Chinese content numeric utterance, it is characterized in that: when this bit digital that reads was 0, its concrete conversion regime was described step 1.2.2):
If this bit digital is hundred million, this bit digital part Chinese does not have, and bit position Chinese is hundred million;
If this bit digital is a myriabit, if three or two or of its front have numeral substantially, this bit digital part Chinese does not have, and bit position Chinese is ten thousand;
If one of the back of this bit digital remains 0, then continue next bit; If the right and wrong 0 in the back of this bit digital, this corresponding Chinese are zero.
If this position is a position, then directly finish.
7. the Chinese TTS of utilization according to claim 5 realizes the method for Chinese content numeric utterance, it is characterized in that: when these bit digital right and wrong 0 of reading, its concrete conversion regime is described step 1.2.2):
If this bit digital is a position, numeral is converted into corresponding Chinese, do not need bit position;
If this bit digital is ten, and numeral be 1 and also this arabic numeral most significant digit be ten, do not need numerical portion Chinese, only need bit position;
8. the Chinese TTS of utilization according to claim 4 realizes the method for Chinese content numeric utterance, it is characterized in that: when described numeral is decimal, described step 1.2) specific implementation be:
The radix point front is if 0, only one zero of integral part Chinese; If radix point front non-0, fraction part is this digital conversion corresponding Chinese according to basic digital conversion table, integral part is converted into basic numeral corresponding Chinese earlier according to basic digital conversion table, finds the corresponding Chinese in position according to position conversion corresponding tables then.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105352691A CN101984489A (en) | 2010-11-08 | 2010-11-08 | Method for realizing numerical pronunciation of Chinese content by using Chinese TTS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105352691A CN101984489A (en) | 2010-11-08 | 2010-11-08 | Method for realizing numerical pronunciation of Chinese content by using Chinese TTS |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101984489A true CN101984489A (en) | 2011-03-09 |
Family
ID=43641659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010105352691A Pending CN101984489A (en) | 2010-11-08 | 2010-11-08 | Method for realizing numerical pronunciation of Chinese content by using Chinese TTS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101984489A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086026A (en) * | 2018-07-17 | 2018-12-25 | 阿里巴巴集团控股有限公司 | Broadcast the determination method, apparatus and equipment of voice |
| CN110119495A (en) * | 2018-02-05 | 2019-08-13 | 北大方正集团有限公司 | Conversion method, system, computer equipment and the medium of digit strings |
| CN111145720A (en) * | 2020-02-04 | 2020-05-12 | 清华珠三角研究院 | Method, system, device and storage medium for converting text into voice |
-
2010
- 2010-11-08 CN CN2010105352691A patent/CN101984489A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110119495A (en) * | 2018-02-05 | 2019-08-13 | 北大方正集团有限公司 | Conversion method, system, computer equipment and the medium of digit strings |
| CN109086026A (en) * | 2018-07-17 | 2018-12-25 | 阿里巴巴集团控股有限公司 | Broadcast the determination method, apparatus and equipment of voice |
| WO2020015479A1 (en) * | 2018-07-17 | 2020-01-23 | 阿里巴巴集团控股有限公司 | Broadcast voice determination method, device and apparatus |
| CN109086026B (en) * | 2018-07-17 | 2020-07-03 | 阿里巴巴集团控股有限公司 | Broadcast voice determination method, device and equipment |
| TWI711967B (en) * | 2018-07-17 | 2020-12-01 | 開曼群島商創新先進技術有限公司 | Method, device and equipment for determining broadcast voice |
| CN111145720A (en) * | 2020-02-04 | 2020-05-12 | 清华珠三角研究院 | Method, system, device and storage medium for converting text into voice |
| CN111145720B (en) * | 2020-02-04 | 2022-06-21 | 清华珠三角研究院 | Method, system, device and storage medium for converting text into voice |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102023716A (en) | 26, 27, 29 or 30 letter key element-containing numeric key Chinese input method | |
| CN101984489A (en) | Method for realizing numerical pronunciation of Chinese content by using Chinese TTS | |
| CN100504733C (en) | Sound-shape encoding Chinese characters input method | |
| CN100403239C (en) | Tibetan input method based on English keyboard | |
| CN101882006A (en) | Zero-memory simple sub-character splitting input method | |
| CN101661335A (en) | Chinese character input method applicable to embedded type platform and system | |
| CN1805009A (en) | Multi-language speech switching apparatus | |
| CN103778110A (en) | Method and system for converting simplified Chinese characters into traditional Chinese characters | |
| CN102368177B (en) | New Chinese character initial and final input method and input keyboard | |
| CN100458668C (en) | Input method for Chinese character of first pronunciation | |
| CN101741945A (en) | Numeric keyboard arrangement method and spelling Chinese character input method thereof of mobilephone | |
| CN100354804C (en) | Intelligent cell-phone Mongol inputting method | |
| CN101493731A (en) | Method for inputting Chinese by english lexical | |
| CN1196057C (en) | One-code two-form quick Chinese digital coding input method | |
| CN107145478B (en) | Method for converting Chinese sentence into braille | |
| CN106055122A (en) | Method, system and device for inputting Sanscrit based on English keyboard and device | |
| CN104007833A (en) | Ternary basic code input method | |
| CN106325540A (en) | Simplified input method of northeast Yunnan sub-dialect Miao language and application of simplified input method | |
| CN101833377B (en) | Novel keyboard input short pinyin codes | |
| CN1288187B (en) | Computer Chinese character input method and its keyboard | |
| CN101408808A (en) | Method for inputting difficult Chinese characters | |
| CN102279653A (en) | Keyboard used for inputting Chinese | |
| CN110956017A (en) | Chinese mandarin information ASCII natural language understanding code | |
| CN101419505A (en) | Free code input method | |
| CN1786943A (en) | Apparatus for Chinese and English phonetic exchange |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110309 |