CN102087799A - System and method thereof for speech broadcasting of Minnan dialect - Google Patents

System and method thereof for speech broadcasting of Minnan dialect Download PDF

Info

Publication number
CN102087799A
CN102087799A CN 201110068963 CN201110068963A CN102087799A CN 102087799 A CN102087799 A CN 102087799A CN 201110068963 CN201110068963 CN 201110068963 CN 201110068963 A CN201110068963 A CN 201110068963A CN 102087799 A CN102087799 A CN 102087799A
Authority
CN
China
Prior art keywords
words
south
module
phrases
fujian province
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
CN 201110068963
Other languages
Chinese (zh)
Inventor
陈淮琰
蒋阳安
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 Besta Xian Co Ltd
Original Assignee
Inventec Besta Xian Co Ltd
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 Besta Xian Co Ltd filed Critical Inventec Besta Xian Co Ltd
Priority to CN 201110068963 priority Critical patent/CN102087799A/en
Publication of CN102087799A publication Critical patent/CN102087799A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Machine Translation (AREA)

Abstract

The invention relates to a system and a method thereof for speech broadcasting of Minnan dialect. The system comprises a database, an input module, a words and expressions division module, a reading module, a display module, a broadcasting module and a judging unit, wherein the input module is respectively connected with the words and expressions division module and the display module, and the words and expressions division module, the display module, the database and the judging unit are respectively connected with the reading module. In the system and the method provided by the invention, the target words and expressions belonging to the Minnan dialect are divided into words, then, a sound file of the words is read according to Minnan dialect pinyin data corresponding to the words, and a short time is delayed for separating each word while broadcasting the sound file, so that the technical effects of increasing the Minnan dialect skills in listening and speaking of the users can be implemented.

Description

The system and the method thereof of the south of Fujian Province language speech play
Technical field
The present invention relates to a kind of language play back system and method thereof, the system and the method thereof of especially a kind of the south of Fujian Province language speech play.
Background technology
Dialect is the variant of language, and Modern Chinese has various dialect, and the zone that they distribute is very wide, the present voice of difference table, vocabulary, grammer various aspects between the seven big dialects of Modern Chinese.In the cultural data that the my late grandfather carried over, there are many language ancient, elegant, wisdom to be write as with dialect.With regard to the Taiwan that the south of Fujian Province of 74 percent language population was once arranged, the south of Fujian Province language that is write down in the cultural data is enough to reflect historical looks, the U.S. that manifests culture.
But because the south of Fujian Province language gets the brush-off for a long time, all there is not formally to learn the pipeline of the south of Fujian Province language all the time, therefore study is difficult for, add the language learning series products that exists in the market and mostly be the foreign language language, and the product of dialect (comprising dialects such as the south of Fujian Province language) exists on the contrary hardly, so the study of the south of Fujian Province language mostly must being imperceptibly influenced by what one constantly sees and hears by relatives and friends, so if there is not to hear the people of the south of Fujian Province language arround the desire learner, there is no the science of law and practise the south of Fujian Province language, even and desire arround the learner people that can hear the south of Fujian Province language to be arranged, but common people are with the south of Fujian Province language talk the time, can't disconnect each words especially pronounces, so have under the many situations of complicated eight tones and polyphone at the south of Fujian Province language, be not easy the pronunciation of the standard of learning.
In sum, prior art has existed study to hear the south of Fujian Province language and very difficult problem always since the midium or long term as can be known, therefore is necessary to propose improved technological means, solves this problem.
Summary of the invention
The present invention solves the above-mentioned technical matters that exists in the background technology, and proposes the system and the method thereof of a kind of the south of Fujian Province language speech play.
Technical solution of the present invention is that the present invention is the system of a kind of the south of Fujian Province language speech play, and its special character is: this system comprises: database is used for storing a plurality of voice files; Load module is used for importing the target words and phrases; Module cut apart in words and phrases, is used for the target words and phrases are divided into words; Read module is used for reading the south of Fujian Province language phonetic data of corresponding words from database, and reads voice files under the words according to the south of Fujian Province language phonetic data from database respectively; Display module is used for being arranged in order in the target words and phrases according to words, arranges to show the south of Fujian Province language phonetic data; Playing module is used for being arranged in order in the target words and phrases according to words, and archives play sound; Judging unit, be used for judging whether the voice files that is played the module broadcast is last affiliated voice files of words, when if the voice files that is played is last voice files under the words, after the voice files that the broadcast of controls playing module is played is finished, postpone special time, load module inserts words and phrases respectively cuts apart module and display module, and words and phrases are cut apart module, display module, database and judging unit and are connected with read module respectively.
Above-mentioned database is used for storing a plurality of phrases, and module cut apart in words and phrases, and to cut apart the target words and phrases according to phrase be words, words be in the target words and phrases number of words maximum match in phrase.
Above-mentioned read module is used for according to the pronunciation mark of words, reads the south of Fujian Province language phonetic data of corresponding pronunciation mark.
Above-mentioned read module is used for judging that the individual character in the words is after polyphone and individual character do not have corresponding pronunciation mark, reads the default corresponding the south of Fujian Province of individual character language phonetic data.
Above-mentioned display module is used for being provided with display area, and shows the south of Fujian Province language phonetic data in display area.
The method of a kind of the south of Fujian Province language speech play, its special character is: this method comprises the following step:
1) input target words and phrases;
2) cutting apart the target words and phrases is words;
3) read the south of Fujian Province language phonetic data of corresponding words respectively;
4) read the voice files that adheres to words separately;
5) be arranged in order in the target words and phrases according to words, arrange and show the south of Fujian Province language phonetic data;
6) be arranged in order in the target words and phrases according to words, archives in regular turn play sound, and when playing, judge when the voice files that is played is last voice files under the words, after the voice files that is played finishes playing, postpone special time and play next voice files again.
Above-mentioned steps 2) be that to cut apart the target words and phrases according to a plurality of phrases of prestoring be words in, words be in the target words and phrases number of words maximum match in phrase.
Above-mentioned steps 3) is according to the pronunciation mark in the words in, reads the south of Fujian Province language phonetic data of corresponding pronunciation mark.
Above-mentioned steps 3) is to judge that the individual character in the words is after polyphone and individual character do not have corresponding pronunciation mark in, reads the default corresponding the south of Fujian Province of individual character language phonetic data.
Above-mentioned steps 5) also comprises in display area is set, and in display area, show the south of Fujian Province language phonetic data.
The system and the method thereof of a kind of the south of Fujian Province provided by the invention language speech play, after being divided into words by the target words and phrases that will belong to the south of Fujian Province language, voice files according to the south of Fujian Province of words correspondence language phonetic data read words, and when playing sound archives, postpone blink and separate each words, can reach the technology effect of the south of Fujian Province language listening and speaking ability that increases the user.
Description of drawings
Fig. 1 is the system architecture diagram of the south of Fujian Province of the present invention language speech play;
Fig. 2 is the phrase table of embodiment of the invention the south of Fujian Province language;
Fig. 3 is the corresponding tables of embodiment of the invention voice files;
Fig. 4 .1 is an embodiment of the invention display frame synoptic diagram;
Fig. 4 .2 is an embodiment of the invention display area synoptic diagram;
Fig. 5 .1 is the method flow diagram of the south of Fujian Province of the present invention language speech play;
Fig. 5 .2 reads the thin portion method flow diagram of the south of Fujian Province language phonetic data for the present invention.
Wherein, the 110-database, the 120-load module, module cut apart in the 130-words and phrases, the 150-read module, the 160-display module, 170-playing module, 171-judging unit, 300-phrase table, 310-phrase field, 320-phonetic field, 400-corresponding tables, 500-display frame, 510-display area;
Embodiment
The syllable structure and the Chinese of the south of Fujian Province, Taiwan language are similar, are divided into " initial consonant ", " simple or compound vowel of a Chinese syllable " and " tone " three parts, are called one " syllable " after one " initial consonant ", one " simple or compound vowel of a Chinese syllable " and one " tone " combination.According to the prior art data, the south of Fujian Province, Taiwan language has 756 " initial consonants " and " simple or compound vowel of a Chinese syllable " simple or compound vowel of a Chinese syllable in theory " combination; and 8 tones are arranged, are respectively " high and level tone ", " on the moon ", " the moon goes ", " the moon is gone into ", " rising tone ", " on the sun ", " sun goes " and " sun is gone into ".
Following elder generation illustrates System Operation of the present invention with Fig. 1.Referring to Fig. 1, system of the present invention contains database 110, load module 120, words and phrases cuts apart module 130, read module 150, display module 160 and playing module 170.
Database 110 is responsible for storing the words of the south of Fujian Province, Taiwan language, and the south of Fujian Province, the Taiwan language phonetic data that can represent each words pronunciation.Referring to Fig. 2, store the phrase table 300 of the south of Fujian Province, Taiwan language, include phrase field 310 and phonetic field 320 in the phrase table 300.The phrase of phrase field 310 record the south of Fujian Province languages, the south of Fujian Province, Taiwan language phonetic data of phonetic field 320 record phrases, generally speaking, the south of Fujian Province, Taiwan language phonetic data are the Taiwan Roman phonetic, but the present invention is not limited to this.The south of Fujian Province, Taiwan of same data language phonetic data are the pronunciation of corresponding phrase in the phrase table 300.
Database 110 also is responsible for storing the voice files of each syllable in the language of the south of Fujian Province, Taiwan.Generally speaking, the voice files of each syllable is that the numeral that replaced of the south of Fujian Province, Taiwan language phonetic data and the syllable it " tone " with " initial consonant " in the syllable and " simple or compound vowel of a Chinese syllable " is as filename, the numeral that aforesaid " tone " replaced can be defined voluntarily by the person for recording, represents " high and level tone ", " on the moon ", " the moon goes ", " the moon is gone into ", " rising tone ", " on the sun ", " sun goes " and eight tones such as " sun are gone into " in regular turn with 1～8 usually.Referring to Fig. 3, write down the voice files of each syllable with corresponding tables 400, that is to say, when the south of Fujian Province, Taiwan language phonetic data are the Taiwan Roman phonetic, the south of Fujian Province, Taiwan language phonetic data of words " I " are " gu á " (tone is " on the moon "), represent that therefore the file name of the voice files of words " I " is " gua2.mp3 ".The archives naming method of the voice files that wherein, the present invention carried is not limited to this.
Load module 120 is responsible for the target words and phrases that input belongs to the south of Fujian Province, Taiwan language, and the target words and phrases are combined by the phrase of a plurality of the south of Fujian Provinces language.Wherein the target words and phrases can be chosen the specific words and phrases in the archives or imported by modes such as the user key in voluntarily by the user, are not limited to this but the present invention puies forward the mode of input target words and phrases.
Words and phrases are cut apart the module 130 responsible target words and phrases that load module 120 is imported and are divided into words.
When database 110 stores the phonetic data of the phrase of the south of Fujian Province, Taiwan language and the south of Fujian Province, Taiwan language with phrase table 300, words and phrases are cut apart module 130 and can be begun by first word of target words and phrases, with the target words and phrases in regular turn with phrase table 300 in each phrase do the coupling of number of words maximum, if the phrase in the phrase table 300 conforms to words in the target words and phrases, then words and phrases are cut apart module 130 and can be split the words that mates.
When for example the target words and phrases are not for " I am a native of this place ", words and phrases cut apart module 130 can with the target words and phrases by first word begin with phrase table 300 in all phrases compare, the phrase of supposing " I " beginning in the phrase table 300 has only " an I " word, after then words and phrases are cut apart module 130 the target words and phrases are carried out the coupling of number of words maximum, can only match " I ", therefore " I " can be split into a words, and the target words and phrases after cutting apart become " not being a native of this place ".Afterwards, target words and phrases after words and phrases are cut apart module 130 and will be cut apart " be not a native of this place " once more with phrase table 300 in phrase when mating, because the phrase that preceding two words of the target words and phrases after comprising and cut apart in the phrase table 300 are complementary " is not ", suppose to include in addition in the phrase table 300 phrase of " not ", but because phrase " is not " and the number of words of target words and phrases coupling is two words, and phrase " not " has only a word with the number of words of target words and phrases coupling, therefore after the coupling of number of words maximum, " not " can be by being split in the target words and phrases, same, " native " also can be by being split in the target words and phrases.Therefore after words and phrases are cut apart module 130 and finished cutting apart of target words and phrases " I am not a native of this place ", can be partitioned into " I ", " not being " and " native " three words.Wherein, institute of the present invention prompter sentence is cut apart module 130 and is cut apart the mode of target words and phrases and be not limited to this.
The pairing the south of Fujian Province of each words language phonetic data that module 130 is partitioned into cut apart in the read module 150 responsible words and phrases that read from database 110, and with the voice files of representing the pronunciation of each words according to the south of Fujian Province language phonetic data read that reads out.
When if database 110 stores the phonetic data of the phrase of the south of Fujian Province, Taiwan language and the south of Fujian Province, Taiwan language with phrase table 300, owing to comprise the phonetic field 320 of record the south of Fujian Province, Taiwan language phonetic data in the phrase table 300, therefore read module 150 cuts apart that module 130 is mated the phrase in target words and phrases and the phrase table 300 and after being partitioned into words at words and phrases, just can be directly according to phrase field 310 pairing phonetic fields 320, read and cut apart the south of Fujian Province, the corresponding Taiwan of words language phonetic data that module 130 is partitioned into by words and phrases, but the present invention is not limited to this, alternate manner for example separates phrase field 310 to be deposited with phonetic field 320, make read module 150 read the south of Fujian Province, corresponding Taiwan language phonetic data etc. to the position that is different from record phrase field to be cut apart words that module 130 is partitioned into by words and phrases as index.
Display module 160 is responsible for according to cut apart each words putting in order in the target words and phrases that module 130 is partitioned into by words and phrases, arrange to show that words and phrases cut apart the south of Fujian Province language phonetic data of the words correspondence that module 130 is partitioned into, that is to say, after target words and phrases " I am not a native of this place " are cut apart module 130 and are divided into " I ", " not being " and " native " three words by words and phrases, display module 160 can be according to " I ", " not being " and " native " natives " put in order, arrange and demonstrate " gu á ", " m s ī " and " p ú n-t ē
Figure BDA0000051672900000051
" three the south of Fujian Province language phonetic data.
When display module 160 in the display frame shown in Fig. 4 .1 500 during the display-object words and phrases, display module 160 is referring to shown in Fig. 4 .2, display area 510 is set in display frame 500, and on display area 510, shows the south of Fujian Province language phonetic data that read module 150 is read.Wherein, the mode that display area 510 can superposition is arranged in the display frame 500.
Display module 160 can also be when the voice files under playing module 170 is play words, and in the south of Fujian Province language phonetic data that show, mark just is being played the corresponding the south of Fujian Province of voice files language phonetic data that module 170 is play.The mode of display module 160 mark the south of Fujian Provinces languages phonetic data including but not limited to anti-white, add bottom line, change Show Color or change background color etc.
Playing module 170 is responsible for according to cut apart each words putting in order in the target words and phrases that module 130 is partitioned into by words and phrases, plays the voice files of each words that belongs to the south of Fujian Province language phonetic data in regular turn.
Also comprise judging unit 171 in the playing module 170, judging unit 171 is responsible for judging that whether be played voice files that module 170 play is in the voice files under each words last, when if judging unit 171 is judged the voice files that is played in the voice files under each words last, playing module 170 can be after in progress voice files finishes playing, postpone the specific time, allow pronunciation between words and the words interval on free.That is to say, between " not " of playing module 170 in words " I " and words " are not ", a little time can be postponed, to be separated out two words, and when playing the voice files of words under " not being ", " " and the time that does not have delay between the "Yes", so the user just can clearly not recognize the pronunciation of " not being ".
Explain orally operation system of the present invention and method with an embodiment below, referring to Fig. 5 .1.
Before the user brought into use the present invention, the database of carrying out in apparatus of the present invention 110 needed elder generation to store the voice files (step 210) of each syllable in the language of the south of Fujian Province, Taiwan.
When the user by display frame 500 in, after choosing literal " I am not a native of this place " in the display frame 500 with mouse, press " pronunciation " button on the lower device, then load module 120 can use the user the selected literal of mouse " I am not a native of this place " input becoming target word sentence (step 220).
Behind load module 120 input target words and phrases (step 220), the processing that module 130 can cut apart target words and phrases " I am not a native of this place " cut apart in words and phrases, and (detailed process of cutting apart as mentioned above, so no longer repeat specification), target words and phrases " I am not a native of this place " can be cut apart module 130 by words and phrases at last and be divided into " I ", " not being " and " native " three words (step 230).
Afterwards, read module 150 can be according to " I ", " not being " and " native " three words, from the stored phrase table 300 of database 110, read the south of Fujian Province language phonetic data of " I ", " not being " and " native " three words, be respectively " gu á ", " m s ī " and " p ú n-t ē
Figure BDA0000051672900000061
" (step 251).Then, read module 150 the south of Fujian Province language phonetic data " gu á ", " m s ī " and " the p ú n-t ē that also can read
Figure BDA0000051672900000062
" in each syllable; search the words " I " of respectively corresponding the south of Fujian Province language phonetic data to the corresponding tables 400; file name of the voice files under " not being " and " native "; and read voice files (step 252); that is to say; the voice files that read module 150 can be read " gua2.mp3 " according to file name, " m7.mp3 ", " si7.mp3 ", " pun2.mp3 ", " te7.mp3 " and " lang5.mp3 ", wherein " gua2.mp3 " is the voice files that belongs to words " I ", " m7.mp3 " and " si7.mp3 " belongs to the voice files that words " is not ", and voice files " pun2.mp3 ", " te7.mp3 " and " lang5.mp3 " then is the voice files that belongs to " native ".
After the corresponding the south of Fujian Province language phonetic data of the words that read module 150 is read and is partitioned into (step 251), display module 160 can be according to each words putting in order in the target words and phrases, show the south of Fujian Province language phonetic data (step 261) that read module 150 is read in regular turn, that is to say that display module 160 can demonstrate " gu á m s ī p ú n-t ē in display frame 500
Figure BDA0000051672900000071
".Wherein, display module 160 can also be shown in Fig. 4 .2, and the mode with superposition in display frame 500 is provided with display area 510, and in display area the south of Fujian Province, Taiwan language phonetic data " the gu á m s ī p ú n-t ē of display-object words and phrases
Figure BDA0000051672900000072
", the user can read out the sound that is expressed as the target words and phrases according to the south of Fujian Province phonetic data of speaking.
After display module 160 demonstrates the south of Fujian Province language phonetic data (step 261) that read module 150 read, playing module 170 equally also can be according to each words putting in order in the target words and phrases, play the voice files under each words of being read by read module 150 in regular turn, just can be with " gua2.mp3 ", " m7.mp3 ", " si7.mp3 ", " pun2.mp3 ", " te7.mp3 ", the played in order voice files of " lang5.mp3 ", wherein, judging unit 171 can be play " gua2.mp3 " at playing module 170, during " si7.mp3 " and " lang5.mp3 " three voice files, judge the archives that playing module 170 play and be respectively words " I ", " be not " and " native " under last voice files, therefore can allow playing module 170 play " gua2.mp3 ", after " si7.mp3 " or " lang5.mp3 " three voice files are finished, postpone blink, play the voice files (step 270) of next words again, just voice files " m7.mp3 " and " pun2.mp3 ", that is to say that playing module 170 is when playing sound archives, voice files under the two-character word (" gua2.mp3 " and " m7.mp3 ", " si7.mp3 " and " pun2.mp3 ") between have at interval, and the voice files under the same words (" m7.mp3 " and " si7.mp3 ", " pun2.mp3 " and " te7.mp3 ", " te7.mp3 " and " lang5.mp3 ") between do not have at interval, so the user just can be clear and definite tells " I ", " be not " and the pronunciation of " native ".
In addition, when playing module 170 plays sound archives, can also transmit and control signal to display module 160, make display module 160 according to control signal mark and the words (step 262) that is played under the voice files that module 170 plays, for example, when playing module 170 begins to play " gua2.mp3 ", transmission controls signal to display module 160, display module 160 will be changed the color that shows the south of Fujian Province, Taiwan language phonetic data " gu á ", and when playing module 170 begins to play " m7.mp3 ", display module 160 will gain the color of the south of Fujian Province, Taiwan language phonetic data " gu á " color of original demonstration, and change the color that shows the south of Fujian Province, Taiwan language phonetic data " m s ī ", begin to play " pun2.mp3 " up to playing module 170.
In sum, after difference between the present invention and the prior art is to have the target words and phrases that will belong to the south of Fujian Province language and is divided into words as can be known, voice files according to the south of Fujian Province of words correspondence language phonetic data read words, and when playing the voice files of the south of Fujian Province language, postpone to separate blink the technological means of each words, can solve the existing study of prior art thus and hear the south of Fujian Province language and very difficult problem, and then reach the effect of the south of Fujian Province language listening and speaking ability that increases the user.
When read module 150 reads the south of Fujian Province language phonetic data (step 251) to phrase table 300, referring to Fig. 5 .2, if judging to be cut apart, read module 150 includes pronunciation mark (step 2511) in the words that module 130 is partitioned into, then read module 150 is when reading the pairing the south of Fujian Province of words language phonetic data, just can read the pairing the south of Fujian Province of words language phonetic data (step 2513) according to the pronunciation mark, wherein, the pronunciation mark can by be not easy to be used in special symbol in the sentence (as “ @@ ", " * * " etc., but be not limited to this) add that the south of Fujian Province language phonetic data form.
For example read module 150 will read the sound shelves of the individual character " weight " of words in " heavily coming ", if include to pronounce mark “ @@ before at " weight "
Figure BDA0000051672900000081
", just cutting apart the words that module 130 is partitioned into is “ @@
Figure BDA0000051672900000082
Heavily come ", so read module 150 just can be according to special symbol “ @@ when reading words and " heavily come " pairing the south of Fujian Province language phonetic data " afterwards the south of Fujian Province phonetic data of speaking Read words and " heavily come " pairing the south of Fujian Province language phonetic data
Figure BDA0000051672900000084
(step 2513) is subsequently and according to the south of Fujian Province language phonetic data
Figure BDA0000051672900000085
Read words "
Figure BDA0000051672900000086
Heavily come " affiliated voice files " ting5.mp3 " and " lai5.mp3 " (step 252).Wherein, the mode of record pronunciation mark is not limited to this.
If judging, read module 150 do not include pronunciation mark (step 2511) in the individual character " weight ", but when the phonetic data are spoken in the south of Fujian Province of reading corresponding individual character " weight " in by phrase table 300, but read out the pairing the south of Fujian Province of a plurality of individual characters " weight " language phonetic data, for example " t ā ng ",
Figure BDA0000051672900000087
And " ti6ng ", then can to judge individual character " weight " be polyphone (step 2512) to read module 150, so the south of Fujian Province of can the read-out systems default individual character " weight " of read module 150 phonetic data (step 2515) of speaking.
And if read module 150 judge do not comprise the pronunciation mark in the words neither polyphone, then read module 150 will directly read the pairing the south of Fujian Province of individual character language phonetic data (step 2514).
Moreover the method for the south of Fujian Province of the present invention language speech play can be implemented in the combination of hardware, software or hardware and software, also can realize or intersperse among with different assemblies the dispersing mode of the computer system of several interconnected with centralized system and realize in computer system.

Claims (10)

1. the system of the south of Fujian Province language speech play, it is characterized in that: this system comprises: database is used for storing a plurality of voice files; Load module is used for importing the target words and phrases; Module cut apart in words and phrases, is used for the target words and phrases are divided into words; Read module is used for reading the south of Fujian Province language phonetic data of corresponding words from database, and reads voice files under the words according to the south of Fujian Province language phonetic data from database respectively; Display module is used for being arranged in order in the target words and phrases according to words, arranges to show the south of Fujian Province language phonetic data; Playing module is used for being arranged in order in the target words and phrases according to words, and archives play sound; Judging unit, be used for judging whether the voice files that is played the module broadcast is last affiliated voice files of words, when if the voice files that is played is last voice files under the words, after the voice files that the broadcast of controls playing module is played is finished, postpone special time, described load module inserts words and phrases respectively cuts apart module and display module, and described words and phrases are cut apart module, display module, database and judging unit and are connected with read module respectively.
2. the system of the south of Fujian Province according to claim 1 language speech play, it is characterized in that: described database is used for storing a plurality of phrases, module cut apart in words and phrases, and to cut apart the target words and phrases according to phrase be words, words be in the target words and phrases number of words maximum match in phrase.
3. the system of the south of Fujian Province according to claim 1 language speech play, it is characterized in that: described read module is used for according to the pronunciation mark of words, reads the south of Fujian Province language phonetic data of corresponding pronunciation mark.
4. the system of the south of Fujian Province according to claim 1 language speech play, it is characterized in that: described read module is used for judging that the individual character in the words is after polyphone and individual character do not have corresponding pronunciation mark, reads the default corresponding the south of Fujian Province of individual character language phonetic data.
5. the system of the south of Fujian Province according to claim 1 language speech play, it is characterized in that: described display module is used for being provided with display area, and shows the south of Fujian Province language phonetic data in display area.
6. the method for the south of Fujian Province language speech play, it is characterized in that: this method comprises the following step:
1) input target words and phrases;
2) cutting apart the target words and phrases is words;
3) read the south of Fujian Province language phonetic data of corresponding words respectively;
4) read the voice files that adheres to words separately;
5) be arranged in order in the target words and phrases according to words, arrange and show the south of Fujian Province language phonetic data;
6) be arranged in order in the target words and phrases according to words, archives in regular turn play sound, and when playing, judge when the voice files that is played is last voice files under the words, after the voice files that is played finishes playing, postpone special time and play next voice files again.
7. the method for the south of Fujian Province according to claim 6 language speech play is characterized in that: be that to cut apart the target words and phrases according to a plurality of phrases that prestore be words described step 2), words be in the target words and phrases number of words maximum match in phrase.
8. the method for the south of Fujian Province according to claim 7 language speech play is characterized in that: be according to the pronunciation mark in the words in the described step 3), read the south of Fujian Province language phonetic data of corresponding pronunciation mark.
9. the method for the south of Fujian Province according to claim 7 language speech play is characterized in that: be to judge that the individual character in the words is after polyphone and individual character do not have corresponding pronunciation mark described 3), read the default corresponding the south of Fujian Province of individual character language phonetic data.
10. according to the method for claim 6 or 7 or 8 described the south of Fujian Provinces language speech play, it is characterized in that: also comprise in the described step 5) display area is set, and in display area, show the south of Fujian Province language phonetic data.
CN 201110068963 2011-01-19 2011-03-23 System and method thereof for speech broadcasting of Minnan dialect Pending CN102087799A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201110068963 CN102087799A (en) 2011-01-19 2011-03-23 System and method thereof for speech broadcasting of Minnan dialect

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN201110021448 2011-01-19
CN201110021448.8 2011-01-19
CN 201110068963 CN102087799A (en) 2011-01-19 2011-03-23 System and method thereof for speech broadcasting of Minnan dialect

Publications (1)

Publication Number Publication Date
CN102087799A true CN102087799A (en) 2011-06-08

Family

ID=44099579

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201110068963 Pending CN102087799A (en) 2011-01-19 2011-03-23 System and method thereof for speech broadcasting of Minnan dialect

Country Status (1)

Country Link
CN (1) CN102087799A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111028824A (en) * 2019-12-13 2020-04-17 厦门大学 Method and device for synthesizing Minnan

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111028824A (en) * 2019-12-13 2020-04-17 厦门大学 Method and device for synthesizing Minnan

Similar Documents

Publication Publication Date Title
Romero-Fresco Subtitling through speech recognition: Respeaking
Prahallad et al. The IIIT-H Indic speech databases.
Chládková et al. Native dialect matters: Perceptual assimilation of Dutch vowels by Czech listeners
Schuppler et al. A corpus of read and conversational Austrian German
Ahmed et al. The development of isolated words pashto automatic speech recognition system
Johnson et al. SpiCE: A new open-access corpus of conversational bilingual speech in Cantonese and English
Pražák et al. Live TV subtitling through respeaking with remote cutting-edge technology
Zahner et al. Konstanz prosodically annotated infant-directed speech corpus (KIDS corpus)
Karakaş English voices in ‘Text-to-speech tools’: representation of English users and their varieties from a World Englishes perspective
CN109473007B (en) English natural spelling teaching method and system combining phonemes with sound side
Aye Myanmar English
CN102087799A (en) System and method thereof for speech broadcasting of Minnan dialect
Ahmed et al. The development of isolated words corpus of pashto for the automatic speech recognition research
Yang ‘I Want to be New and Different. Anything I’m Not.’Accent-Mixing in Singing
Istiqomah et al. Discursive creation technique of English to Indonesian subtitle in Harry Potter: The chamber of secrets movie
Giwa et al. A Southern African corpus for multilingual name pronunciation
Mulyani Code mixing analysis of the judges comments and the host utterances on fine episodes of workshop round in Indonesia idol singing competition season 6
Ludwig 15 Medium and creole
Bruggeman et al. Listener adjustment of stress cue use to fit language vocabulary structure
Dimitrova Bulgarian Speech Corpora: A Review
Dwivedi et al. On documenting low resourced Indian languages insights from Kanauji speech corpus
Otake Interlingual near homophonic words and phrases in L2 listening: Evidence from misheard song lyrics
KR20110039747A (en) System for learning a foreign language and a learning method using the same
Chen The Unwritten and the Recorded: Tradition and Transfiguration in Taiwanese Aboriginal Music
ATECHI The Actuality of the English Language in Non-Native Settings: An Insight into Major Features of Nigerian Audiolects

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C12 Rejection of a patent application after its publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20110608