CN1983387A - System and method for sending out different-effect character speech by parameter related to character features - Google Patents

System and method for sending out different-effect character speech by parameter related to character features Download PDF

Info

Publication number
CN1983387A
CN1983387A CNA2005101295928A CN200510129592A CN1983387A CN 1983387 A CN1983387 A CN 1983387A CN A2005101295928 A CNA2005101295928 A CN A2005101295928A CN 200510129592 A CN200510129592 A CN 200510129592A CN 1983387 A CN1983387 A CN 1983387A
Authority
CN
China
Prior art keywords
character
file
described character
feature
parameter
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
Application number
CNA2005101295928A
Other languages
Chinese (zh)
Inventor
吴耀宗
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inventec Corp
Original Assignee
Inventec Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Inventec Corp filed Critical Inventec Corp
Priority to CNA2005101295928A priority Critical patent/CN1983387A/en
Publication of CN1983387A publication Critical patent/CN1983387A/en
Pending legal-status Critical Current

Links

Images

Abstract

A system using parameter corresponding to character feature to launch out different character sound is prepared as using fetch module to fetch out character string containing at least one character, using treatment module to fetch out corresponding character sounding file and character feature sounding file according to character sounding parameter and character feature parameter of each character then using voice synthesizing module to synthesize said sounding file and said feature sounding file to be playing character-sound file being used to be played by playing module.

Description

Send the word system for electrical teaching and the method for different-effect with the character feature corresponding parameters
Technical field
The present invention relates to a kind of system and method thereof of sending the word sound, particularly a kind of system and method thereof of sending the word sound of different-effect according to the character feature corresponding parameters.
Background technology
Because science and technology is showing improvement or progress day by day, wherein, speech synthesis technique and speech recognition technology are gradually ripe, applicable scope is quite extensive, for example, can be used for the sound pronunciation of translation machine, in addition, also can make it to become " sound note " in conjunction with the SMS of mobile phone, this function will be a future trend, by " sound note ", the user needn't remove to see the word that shows on the screen with eyes, just can learn the information content with listening, and this is for looking the barrier compatriot, quite convenient, sound word the earliest is applied to electronic translator, as long as after the user presses pronunciation button on/off, just system can send statement shown on the screen.
Yet, after the user has pressed the sounding key, often have only dull pronunciation, seem quite barren, and, between the lines, sometimes can indicate bottom line especially, or be labeled as different colours, different big or small font, with the emphasis in the expression article, if having only the pronunciation of single tone, the user just can't experience the special feature in the article especially, or ben statement, thus, whole section article sounds and will seem quite flat and barren.
Summary of the invention
Fundamental purpose of the present invention is to provide a kind of system and method thereof of sending the word sound of different-effect according to the character feature corresponding parameters, the user can utilize the editor of literal, control the voice output of different-effect, solve the existing in prior technology problem.
Therefore, for reaching above-mentioned purpose, disclosed in this inventionly a kind ofly send the system of the word sound of different-effect, include word sound data storehouse, character feature database, read module, processing module, phonetic synthesis module and playing module according to the character feature corresponding parameters.
There are a plurality of character pronunciation files in word sound data storehouse wherein storage inside, and each character pronunciation file has its corresponding characters voice parameter respectively.
Character feature database wherein storage inside has a plurality of character feature pronunciation files, and each character feature pronunciation file has its corresponding characters characteristic parameter respectively.
Read module its in order to read a character string, in character string, include at least one character, each character includes character voice parameter and character feature parameter respectively.
It distinguishes corresponding characters voice parameter and character feature parameter according to each character processing module, in order to read out corresponding characters pronunciation file and character feature pronunciation file from word sound data storehouse and character feature database.
The phonetic synthesis module its in order to synthetic each character corresponding characters pronunciation file and character feature pronunciation file respectively, word sound file is play to form in synthetic back.
It plays word sound file in order to play each playing module.
Above-mentionedly send the system of the word sound of different-effect, wherein also include an analysis module, the character voice parameter and the character feature parameter that have respectively in order to the character of analyzing character string according to the character feature corresponding parameters.
Said system wherein also includes a memory module, plays word sound file in order to storage.
Said system, wherein each character feature parameter is the parameter that the feature of font, color or font size according to each character is edited.
Said system, wherein the file layout of each character pronunciation file and character feature pronunciation file is respectively a kind of file layout among " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", " .iff " or " .mat ".
On the other hand, of the present inventionly a kind ofly send the method for the word sound of different-effect, include the following step according to the character feature corresponding parameters:
(A) set up a plurality of character pronunciation files, each character pronunciation file is respectively to there being a character voice parameter;
(B) set up a plurality of character feature pronunciation files, each character feature pronunciation file is respectively to there being a character feature parameter;
(C) read a character string, this character string comprises at least one character, and each character has corresponding characters voice parameter and character feature parameter respectively;
(D), read corresponding characters pronunciation file and character feature pronunciation file according to each character difference corresponding characters voice parameter and character feature parameter;
(E) synthetic each character difference corresponding characters pronunciation file and character feature pronunciation file are to form at least one broadcast word sound file; And
(F) play each and play word sound file.
Above-mentionedly send the method for the word sound of different-effect according to the character feature corresponding parameters, wherein the file layout of each character pronunciation file and character feature pronunciation file is respectively a kind of file layout among " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", " .iff " or " .mat ".
Said method, wherein each character feature parameter is the parameter that the feature of font, color or font size according to each character is edited.
Said method wherein after the step that reads a character string, also includes the character voice parameter that each character of analyzing character string has respectively and the step of character feature parameter.
Said method wherein at composite characters difference corresponding characters pronunciation file and character feature pronunciation file, after the step that forms at least one broadcast word sound file, also includes the step that word sound file is play in a storage.
Below in embodiment, describe detailed features of the present invention and advantage in detail; its content is enough to make any those skilled in the art to understand technology contents of the present invention and implements according to this; and according to the disclosed content of this instructions, claim protection domain and accompanying drawing, any those skilled in the art can understand purpose and the advantage that the present invention is correlated with easily.
Description of drawings
Fig. 1 sends the system chart of the word sound of different-effect according to the character feature corresponding parameters for the present invention;
Fig. 2 A sends the method flow diagram of the word sound of different-effect according to the character feature corresponding parameters for the present invention;
Fig. 2 B sends the partial approach process flow diagram of the word sound of different-effect according to the character feature corresponding parameters for the present invention;
Fig. 2 C sends the partial approach process flow diagram of the word sound of different-effect according to the character feature corresponding parameters for the present invention;
Fig. 3 A is the embodiment character voice parameter table of comparisons;
Fig. 3 B is the embodiment character feature parameter table of comparisons; And
Fig. 3 C is an embodiment of the invention synoptic diagram.
Main description of reference numerals:
110 read modules
120 analysis modules
130 processing modules
140 word sound data storehouses
150 character feature databases
160 memory modules
170 phonetic synthesis modules
180 playing modules
Embodiment
For making purpose of the present invention, structure, feature and function thereof there are further understanding, now cooperate embodiment to be described in detail as follows.More than be in order to for example and explain principle of the present invention about the explanation of the explanation of content of the present invention and following embodiment, and provide patented claim protection domain of the present invention further to explain.
See also Fig. 1, it sends the system chart of the word sound of different-effect for the present invention according to the character feature corresponding parameters, includes word sound data storehouse 140, character feature database 150, read module 110, processing module 130, phonetic synthesis module 170 and playing module 180.
Word sound data storehouse 140, can be ROM (read-only memory) (ROM), the memory storage of equal function such as hard disk or storage card, there are a plurality of character pronunciation files the inside, the file layout of character pronunciation file can be " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", a kind of file layout in " .iff " or " .mat ", each character pronunciation file all has its corresponding characters voice parameter, for example, the character voice parameter of " the present " is set at " 001 ", and " my god " the character voice parameter be set at " 002 ", have in word sound data storehouse 140 " the present " follow " my god " the pronunciation file.
Character feature database 150, can be ROM (read-only memory) (ROM), the memory storage of equal function such as hard disk or storage card, in order to store a plurality of character feature pronunciation files, the file layout of each character feature pronunciation file can be " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", a kind of file layout in " .iff " or " .mat ", each character feature pronunciation file is respectively to there being a character feature parameter, for example, the pronunciation file corresponding characters characteristic parameter of " the male sound of being grown up " is " 01 ", and the pronunciation file corresponding characters characteristic parameter of " the women sound of being grown up " is " 02 ".
Read module 110, be used for reading a character string, in character string, include a character or a plurality of character, each character has corresponding characters voice parameter and character feature parameter respectively, each character feature parameter is the font according to each character, the parameter that the feature of color or font size is edited, promptly, as user during at the editing character string, the individual character of character itself promptly has one group of corresponding characters voice parameter, in addition, give the words of character editing further feature, character has the corresponding characters characteristic parameter again, for example, " the present ", the character voice parameter of itself was " 001 ", if be set at the words of black for " the present ", this feature of black can give one group of character feature parameter again and be " 01 ", just correspond to 150 li of character feature databases, be set at the pronunciation file of " the male sound of being grown up " of " 01 ", 140 li character pronunciation file is to be common mechanical sound in word sound data storehouse.
Processing module 130, be according to each character difference corresponding characters voice parameter and character feature parameter, in order to from word sound data storehouse 140 and 150 li of character feature databases read out corresponding character pronunciation file and character feature pronunciation file, such as black " the present ", has parameters such as " 00101 ", " 001 " is " the present " character pronunciation file parameters, processing module 130 can grasp out the character pronunciation file of " the present " from 140 li in word sound data storehouse according to " 001 " this parameter, and " 01 " is the character feature parameter that is set at black, and processing module 130 can grasp out the pronunciation file of corresponding parameter for " the male sound of being grown up " of " 01 " from 150 li of character feature databases according to " 01 " these parameters.
Phonetic synthesis module 170, in order to synthetic by processing module 130 from word sound data storehouse 140 and 150 li characters pronunciation files that read out of character feature database and character feature pronunciation file, play word sound file with synthetic formation, for example with the character pronunciation file of mechanical sound " the present ", and the pronunciation file of " the male sound of being grown up " becomes one by the pronounce broadcast word sound file of " the present " this character of the male sound of adult.
Playing module 180 is used for playing via phonetic synthesis module 170 the broadcast word sound file after synthetic.
In addition, this system also can include analysis module 120 and memory module 160.
Analysis module 120 is connected with processing module 130, in order to analyzing character voice parameter and the character feature parameter that each character has respectively in the character string, and analysis result is passed to processing module 130.
Memory module 160 is connected with phonetic synthesis module 170, in order to store the broadcast word sound file after synthesizing.
Please refer to Fig. 2 A again, it sends the method flow diagram of the word sound of different-effect according to the character feature corresponding parameters for the present invention, and Fig. 2 B and Fig. 2 C send the partial approach process flow diagram of the word sound of different-effect according to the character feature corresponding parameters for the present invention.
At first, set up a plurality of character pronunciation files, each character pronunciation file is respectively to there being a character voice parameter (step 210), wherein, the file layout of character pronunciation file can be a kind of file layout among " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", " .iff " or " .mat ".
Then, set up a plurality of character feature pronunciation files, each character feature pronunciation file is respectively to there being a character feature parameter (step 220), wherein, the file layout of character feature pronunciation file can be a kind of file layout among " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", " .iff " or " .mat ".
Then, read character string, character string comprises at least one character, and each character has corresponding characters voice parameter and character feature parameter (step 230) respectively, wherein, the parameter of each character feature parameter for editing according to the feature of font, color or the font size of each character.
And then, character voice parameter and character feature parameter (step 232) that each character of analysis character string has respectively, then, according to each character difference corresponding characters voice parameter and character feature parameter, read each corresponding character pronunciation file and each character feature pronunciation file (step 240), at last, synthetic each character is corresponding characters pronunciation file and character feature pronunciation file respectively, to form at least one broadcast word sound file (step 250), can store each afterwards earlier and play word sound file (step 252), then, play each and play word sound file (step 260).
Please continue to consult Fig. 3 A, it is the embodiment character voice parameter table of comparisons, and Fig. 3 B is the embodiment character feature parameter table of comparisons, and Fig. 3 C is an embodiment of the invention synoptic diagram.
Among this embodiment, the user edits six words such as " today, weather were fine ", wherein, " the present " is compiled as black, " my god " be compiled as redness, next " my god " be compiled as blueness, " gas " is compiled as pink, and " very " word adds bottom line, and " good " word also is to add bottom line.
Thus, black " the present " can produce the parameter of " 00101 ", " 001 " is the character voice parameter, " 01 " is the character feature parameter, by that analogy, red " my god " can produce the parameter of " 00202 ", blue " my god " can produce the parameter of " 00203 ", pink " gas " meeting produces the parameter of " 00304 ", and " very " that add bottom line can produce the parameter of " 00405 ", and the parameter that adds " good " the meeting generation " 00505 " of bottom line.
The character voice parameter and the character feature parameter that have according to each character, grasp out corresponding characters pronunciation file and character feature pronunciation file, again that both are synthetic and become final broadcast word sound file, for example black " the present " sends " the present " sound for the male sound of adult, red " day " for the women sound of being grown up send " my god " sound, blue " day " for the male sound of child send " my god " sound, pink " gas " is sent " gas " sound for child woman sound, and it then is the volume adjustment to be put send after being twice that " very " that adds bottom line follow " good ".
Though the present invention open the foregoing description, itself and non-limiting the present invention.The change of being done without departing from the spirit and scope of the present invention all belongs to scope of patent protection of the present invention.Please refer to claims of the application about the protection domain that the present invention limited.

Claims (12)

1. one kind is sent the system of the word sound of different-effect according to the character feature corresponding parameters, and it includes:
One word sound data storehouse, in order to store a plurality of character pronunciation files, each described character pronunciation file is respectively to there being a character voice parameter;
One character feature database, in order to store a plurality of character feature pronunciation files, each described character feature pronunciation file is respectively to there being a character feature parameter;
One read module, in order to read a character string, described character string comprises at least one character, and each described character has corresponding described character voice parameter and described character feature parameter respectively;
One processing module, described character voice parameter and the described character feature parameter corresponding respectively according to described character, in order to from described word sound data storehouse and described character feature database read corresponding described character pronunciation file and described character feature pronunciation file;
One phonetic synthesis module is in order to synthetic described character corresponding respectively described character pronunciation file and described character feature pronunciation file, to form at least one broadcast word sound file; And
One playing module is in order to play described broadcast word sound file.
2. the system that sends the word sound of different-effect according to the character feature corresponding parameters as claimed in claim 1, wherein also include an analysis module, the described character voice parameter and the described character feature parameter that have respectively in order to the described character of analyzing described character string.
3. as claimed in claim 1ly send the system of the word sound of different-effect, wherein also include a memory module, in order to store described broadcast word sound file according to the character feature corresponding parameters.
4. as claimed in claim 1ly send the system of the word sound of different-effect according to the character feature corresponding parameters, wherein each described character feature parameter is the parameter that the feature of font, color or font size according to each described character is edited.
5. as claimed in claim 1ly send the system of the word sound of different-effect according to the character feature corresponding parameters, wherein the file layout of each described character pronunciation file is the sharp file layout among " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", " .iff " or " .mat ".
6. as claimed in claim 1ly send the system of the word sound of different-effect according to the character feature corresponding parameters, wherein the file layout of each described character feature pronunciation file is a kind of file layout among " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", " .iff " or " .mat ".
7. one kind is sent the method for the word sound of different-effect according to the character feature corresponding parameters, and it includes the following step:
Set up a plurality of character pronunciation files, each described character pronunciation file is respectively to there being a character voice parameter;
Set up a plurality of character feature pronunciation files, each described character feature pronunciation file is respectively to there being a character feature parameter;
Read a character string, described character string comprises at least one character, and each described character has corresponding described character voice parameter and described character feature parameter respectively;
Described character voice parameter and the described character feature parameter corresponding respectively according to described character read corresponding described character pronunciation file and described character feature pronunciation file;
Described character pronunciation file that synthetic described character is corresponding respectively and described character feature pronunciation file are to form at least one broadcast word sound file; And
Play described broadcast word sound file.
8. as claimed in claim 7ly send the method for the word sound of different-effect according to the character feature corresponding parameters, wherein the file layout of each described character pronunciation file is a kind of file layout among " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", " .iff " or " .mat ".
9. as claimed in claim 7ly send the method for the word sound of different-effect according to the character feature corresponding parameters, wherein the file layout of each described character feature pronunciation file is a kind of file layout among " .wav ", " .au ", " .snd ", " .voc ", " .aiff ", " .afc ", " .iff " or " .mat ".
10. as claimed in claim 7ly send the method for the word sound of different-effect according to the character feature corresponding parameters, wherein each described character feature parameter is the parameter that the feature of font, color or font size according to each described character is edited.
11. the method for sending the word sound of different-effect according to the character feature corresponding parameters as claimed in claim 7, wherein after the described step that reads a character string, also include the described character voice parameter that each described character of analyzing described character string has respectively and the step of described character feature parameter.
12. the method for sending the word sound of different-effect according to the character feature corresponding parameters as claimed in claim 7, wherein at described synthetic described character corresponding respectively described character pronunciation file and described character feature pronunciation file, after the step that forms at least one broadcast word sound file, also include the step of the described broadcast word sound file of a storage.
CNA2005101295928A 2005-12-14 2005-12-14 System and method for sending out different-effect character speech by parameter related to character features Pending CN1983387A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CNA2005101295928A CN1983387A (en) 2005-12-14 2005-12-14 System and method for sending out different-effect character speech by parameter related to character features

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CNA2005101295928A CN1983387A (en) 2005-12-14 2005-12-14 System and method for sending out different-effect character speech by parameter related to character features

Publications (1)

Publication Number Publication Date
CN1983387A true CN1983387A (en) 2007-06-20

Family

ID=38165877

Family Applications (1)

Application Number Title Priority Date Filing Date
CNA2005101295928A Pending CN1983387A (en) 2005-12-14 2005-12-14 System and method for sending out different-effect character speech by parameter related to character features

Country Status (1)

Country Link
CN (1) CN1983387A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015172448A1 (en) * 2014-05-14 2015-11-19 中兴通讯股份有限公司 Method and apparatus for broadcasting chinese name

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015172448A1 (en) * 2014-05-14 2015-11-19 中兴通讯股份有限公司 Method and apparatus for broadcasting chinese name

Similar Documents

Publication Publication Date Title
US10229669B2 (en) Apparatus, process, and program for combining speech and audio data
US7483832B2 (en) Method and system for customizing voice translation of text to speech
EP1490861B1 (en) Method, apparatus and computer program for voice synthesis
US8719028B2 (en) Information processing apparatus and text-to-speech method
US7472065B2 (en) Generating paralinguistic phenomena via markup in text-to-speech synthesis
US20060069567A1 (en) Methods, systems, and products for translating text to speech
US7792673B2 (en) Method of generating a prosodic model for adjusting speech style and apparatus and method of synthesizing conversational speech using the same
JPWO2008001500A1 (en) Audio content generation system, information exchange system, program, audio content generation method, and information exchange method
CN101079301A (en) Device and method for text to audio mapping, and animation of the text
CN105280179A (en) Text-to-speech processing method and system
CN102201233A (en) Mixed and matched speech synthesis method and system thereof
US20020169610A1 (en) Method and system for automatically converting text messages into voice messages
CN1945692B (en) Intelligent method for improving prompting voice matching effect in voice synthetic system
RU2011129330A (en) METHOD AND DEVICE FOR SPEECH SYNTHESIS
JPH06161704A (en) Speech interface builder system
CN1983387A (en) System and method for sending out different-effect character speech by parameter related to character features
Vanhanen Virtual sound: examining glitch and production
JPS6073589A (en) Voice synthesization system
JP2000003189A (en) Voice data editing device and voice database
JP2005326811A (en) Voice synthesizer and voice synthesis method
KR101236496B1 (en) E-mail Transmission Terminal and E-mail System
JP2000231396A (en) Speech data making device, speech reproducing device, voice analysis/synthesis device and voice information transferring device
JP2577372B2 (en) Speech synthesis apparatus and method
CN100369107C (en) Musical tone and speech reproducing device and method
JP2003150185A (en) System and method for synthesizing voice and program for realizing the same

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Open date: 20070620