CN103793364B - The method and apparatus that automatic phonetic notation processing and display are carried out to text - Google Patents

The method and apparatus that automatic phonetic notation processing and display are carried out to text Download PDF

Info

Publication number
CN103793364B
CN103793364B CN201410032479.7A CN201410032479A CN103793364B CN 103793364 B CN103793364 B CN 103793364B CN 201410032479 A CN201410032479 A CN 201410032479A CN 103793364 B CN103793364 B CN 103793364B
Authority
CN
China
Prior art keywords
text
language
phonetic notation
demand
user
Prior art date
Application number
CN201410032479.7A
Other languages
Chinese (zh)
Other versions
CN103793364A (en
Inventor
韩中华
何中军
吴华
王海峰
Original Assignee
北京百度网讯科技有限公司
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 北京百度网讯科技有限公司 filed Critical 北京百度网讯科技有限公司
Priority to CN201410032479.7A priority Critical patent/CN103793364B/en
Publication of CN103793364A publication Critical patent/CN103793364A/en
Application granted granted Critical
Publication of CN103793364B publication Critical patent/CN103793364B/en

Links

Abstract

The present invention proposes a kind of method and apparatus carrying out automatic phonetic notation processing and display to text, wherein the method for carrying out automatic phonetic notation processing to text includes:Based on hidden code model by the text conversion of original language be object language phonetic notation text;The identification information of acquisition demand user;The current text demand information that active user is sent by client is received, determines that active user is demand user according to identification information, corresponding phonetic notation text is sent to client according to current text demand information, for showing to active user.The method for carrying out automatic phonetic notation processing to text of the present invention can automatically generate Chinese character phonetic alphabet text that is intelligible or easily pronouncing according to foreign language source language text, and Chinese character phonetic alphabet text is actively supplied to demand user, easily learn the pronunciation of foreign language original language song convenient for demand user, user experience is high, and at low cost.

Description

The method and apparatus that automatic phonetic notation processing and display are carried out to text

Technical field

The present invention relates to field of computer technology more particularly to a kind of methods and dress carrying out automatic phonetic notation processing to text It sets and a kind of method and apparatus that phonetic notation text is shown.

Background technology

It is more and more convenient with the acquisition of information, much sing fan start it is interested in various foreign language songs, but Usually perplexed by various uncomprehending words.

Understand song content for the ease of singing fan, in the related technology, various music players or video player For foreign language song, usually play when simultaneous display corresponding language or by translation Lrc(Lyric, the lyrics)The song of format Word.

The shortcomings that above-mentioned the relevant technologies is:Fan is sung for do not know how pronunciation completely, such as being ignorant of The general learner of China of foreign language, no matter the audio or video of player provides lyrics original text or the song by translation Word is all nonsensical.In addition, to the Chinese learner offer lyrics original text for understanding foreign language but cacoepy or by translation The lyrics can not solve articulation problems of the Chinese learner when foreign language song is sung in study.

Therefore, user in the urgent need to address can not understand the foreign language lyrics provided in the related technology, or can not be outer according to this The problems such as literary lyrics are accurately pronounced.

Invention content

The present invention is directed at least solve one of above-mentioned technical problem.

For this purpose, first purpose of the present invention is to propose a kind of method carrying out automatic phonetic notation processing to text.This is right The method that text carries out automatic phonetic notation processing can automatically generate intelligible according to foreign language source language text or easily pronounce Literary phonetic notation text, and Chinese character phonetic alphabet text is actively supplied to demand user, easily learn foreign language source language convenient for demand user Say the pronunciation of song, user experience is high, and at low cost.

Second object of the present invention is to propose a kind of method showing phonetic notation text.This to phonetic notation text into The method of row display can make display mode of the user according to demand with the flexible selection Chinese character phonetic alphabet text of custom, user Just, operability is good, and user experience is high.

Third object of the present invention is to propose a kind of device carrying out text automatic phonetic notation processing.

Fourth object of the present invention is to propose a kind of device showing phonetic notation text.

To achieve the goals above, the method that automatic phonetic notation processing is carried out to text of first aspect present invention embodiment, Include the following steps:Based on hidden code model by the text conversion of original language be object language phonetic notation text;Acquisition demand user Identification information;And the current text demand information that active user is sent by client is received, it is determined according to identification information Active user is demand user, and corresponding phonetic notation text is sent to client according to current text demand information, for working as Preceding user shows.

The method for carrying out automatic phonetic notation processing to text of the embodiment of the present invention passes through client receiving active user After the current text demand information of transmission, determine that active user is demand according to the identification information of the demand user obtained User, and then sent to client according to current text demand information and transformed note is carried out to current text based on hidden code model Sound text.The method for carrying out automatic phonetic notation processing to text can automatically generate phonetic notation text and active according to source language text Phonetic notation text is supplied to demand user, it is convenient to obtain.

To achieve the goals above, the method that phonetic notation text is shown of second aspect of the present invention embodiment, including Following steps:The current text demand information of active user is sent to server;The phonetic notation text that server is sent is received, with pre- Determine mode and show phonetic notation text, for showing to active user;Wherein, phonetic notation text is server according to current text Demand information is based on the phonetic notation text obtained after hidden code model conversion.

The method of the embodiment of the present invention shown to phonetic notation text to server by sending the current of active user Text demand information obtains phonetic notation text, and then shows the phonetic notation text in a predetermined manner.This shows phonetic notation text The method shown is easy to use, and operability is good.

To achieve the goals above, the device that automatic phonetic notation processing is carried out to text of third aspect present invention embodiment, Including:Phonetic notation module is used for the phonetic notation text by the text conversion of original language for object language based on hidden code model;Obtain mould Block, the identification information for obtaining demand user;And transceiver module, worked as by what client was sent for receiving active user Preceding text demand information determines that active user is demand user, according to current text demand information to client according to identification information End sends corresponding phonetic notation text, for showing to active user.

The device that automatic phonetic notation processing is carried out to text of the embodiment of the present invention receives active user in transceiver module and leads to It crosses after the current text demand information of client transmission, it is true according to the identification information for obtaining the demand user that module has obtained It is demand user to determine active user, and then sends phonetic notation module to client according to current text demand information and be based on hidden code model Transformed phonetic notation text is carried out to current text.The device that automatic phonetic notation processing is carried out to text can be according to source text certainly Dynamic to generate phonetic notation text and phonetic notation text is actively supplied to demand user, it is convenient to obtain.

To achieve the goals above, the device that phonetic notation text is shown of fourth aspect present invention embodiment, including: Sending module, the current text demand information for sending active user to server;Display module, for receiving server hair The phonetic notation text sent, shows phonetic notation text in a predefined manner, for showing to active user;Wherein, phonetic notation text is Server is according to current text demand information based on the phonetic notation text obtained after hidden code model conversion.

The device of the embodiment of the present invention shown to phonetic notation text sends current use by sending module to server The current text demand information at family, and then the display module phonetic notation text that display server is sent in a predetermined manner.This is to note The device that sound text is shown is easy to use, and operability is good.

The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description Obviously, or practice through the invention is recognized.

Description of the drawings

Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments Obviously and it is readily appreciated that, wherein

Fig. 1 is the flow chart of the method according to an embodiment of the invention that automatic phonetic notation processing is carried out to text;

Fig. 2 is the flow chart of the method in accordance with another embodiment of the present invention that automatic phonetic notation processing is carried out to text;

Fig. 3 is the flow chart according to the method for carrying out automatic phonetic notation processing to text of further embodiment of the present invention;

Fig. 4 is the flow chart of the method according to an embodiment of the invention shown to phonetic notation text;

Fig. 5 is the flow chart of the method in accordance with another embodiment of the present invention shown to phonetic notation text;

Fig. 6 is the schematic diagram of the display interface one of phonetic notation text according to an embodiment of the invention;

Fig. 7 is the schematic diagram of the display interface two of phonetic notation text according to an embodiment of the invention;

Fig. 8 is the schematic diagram of the display interface one according to an embodiment of the invention that phonetic notation text is switched to by the former lyrics;

Fig. 9 is the schematic diagram of the display interface two according to an embodiment of the invention that phonetic notation text is switched to by the former lyrics;

Figure 10 is the schematic diagram of the display interface three according to an embodiment of the invention that phonetic notation text is switched to by the former lyrics;

Figure 11 is the flow chart according to the method for further embodiment of the present invention shown to phonetic notation text;

Figure 12 is showing for the display interface one in accordance with another embodiment of the present invention that the former lyrics are switched to by phonetic notation text It is intended to;

Figure 13 is showing for the display interface two in accordance with another embodiment of the present invention that the former lyrics are switched to by phonetic notation text It is intended to;

Figure 14 is showing for the display interface three in accordance with another embodiment of the present invention that the former lyrics are switched to by phonetic notation text It is intended to;

Figure 15 is the structural schematic diagram of the device according to an embodiment of the invention that automatic phonetic notation processing is carried out to text; And

Figure 16 is the structural schematic diagram of the device according to an embodiment of the invention shown to phonetic notation text.

Specific implementation mode

The embodiment of the present invention is described below in detail, the example of embodiment is shown in the accompanying drawings, wherein identical from beginning to end Or similar label indicates same or similar element or element with the same or similar functions.It is retouched below with reference to attached drawing The embodiment stated is exemplary, and is only used for explaining the present invention, and is not considered as limiting the invention.On the contrary, of the invention Embodiment include all changes, modification and the equivalent fallen within the scope of the spirit and intension of attached claims.

In the description of the present invention, term " first ", " second " etc. are used for description purposes only, and should not be understood as instruction or Imply relative importance.In the description of the present invention unless specifically defined or limited otherwise, term " connected ", " connection " are answered It is interpreted broadly, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;Can be that machinery connects It connects, can also be electrical connection;It can be directly connected, it can also be indirectly connected through an intermediary.For the common of this field For technical staff, the concrete meaning of above-mentioned term in the present invention can be understood with concrete condition.In addition, in description of the invention In, unless otherwise indicated, the meaning of " plurality " is two or more.

Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable Sequence, include according to involved function by it is basic simultaneously in the way of or in the opposite order, to execute function, this should be of the invention Embodiment person of ordinary skill in the field understood.

Below with reference to the accompanying drawings describe the embodiment of the present invention to text carry out automatic phonetic notation processing method and apparatus and The method and apparatus that phonetic notation text is shown.

Fig. 1 is the flow chart of the method according to an embodiment of the invention that automatic phonetic notation processing is carried out to text, the reality Example is applied to be described from server side.

As shown in Figure 1, the method for carrying out automatic phonetic notation processing to text includes the following steps:

S11, based on hidden code model by the text conversion of original language be object language phonetic notation text.

In an embodiment of the present invention, can be object language by the text automatic phonetic notation of original language, wherein original language can Think that the foreign languages such as English, Japanese, object language can be Chinese, text can be the lyrics.In addition, in the implementation of the present invention In example, the phonetic notation text based on hidden code model by the text conversion of original language for object language can be concentrated down online, so as to It is converted to avoid being repeated several times, is greatly saved and calculates cost and computing capability.

Specifically, in one embodiment of the invention, hidden code model can be:

Original language:アイしてる

Language model:Auntie's frenulum road

Hidden code model:Auntie leads the way

The phonetic notation text of the more above-mentioned corresponding language model of source language text in long phrase rank and hidden code model Sequence labelling text, it is found that although the sequence labelling text of hidden code model be language model phonetic notation text On the basis of adjustment system for, but the sequence labelling text of hidden code model compared with language model phonetic notation text on feel for the language and semantically It is all more clear and coherent, to be easier to be understood and remembered by user.In addition, it is necessary to explanation, the sequence labelling of hidden code model Text also has in phrase rank and sentence level, feel for the language and semantic also more clear and coherent advantage.

S12 obtains the identification information of demand user.

Specifically, in another embodiment of the present invention, as shown in Fig. 2, the identification information for obtaining demand user walks Rapid S12 may be used following two modes and realize:

S121 receives the text demand information that all users are sent by client, counts each user demand text Language form includes the number of the text demand information of original language such as foreign language, and the user that number is more than to pre-determined number is determined as Demand user.

It should be noted that can include in one embodiment of the invention, in text demand information demand text Language form and title etc..

Specifically, user can be by client such as client online music service or Online Video service client Come select online service content such as the foreign language song in foreign language categorizing songs or the outer text video in foreign language visual classification simultaneously The text demand information for sending request, and then client sending information demand information according to the user's choice, and sending as user In the language form of demand text when including original language, statistics includes the number of the text demand information of original language, and when this When number is more than pre-determined number such as 5 times, the user of often selection original language online service content is determined that the user is, and is identified The user is phonetic notation text demand user.

S122 determines demand user according to preset condition.

It should be noted that preset condition can be by client such as client or Online Video online music service Service client etc. is selected for the first time in foreign language song or foreign language visual classification in online service content such as foreign language categorizing songs Outer text video etc. user, and have determined that mother tongue is the user etc. of non-original language.

Above-mentioned steps S121 and step S122 is step arranged side by side.

S13 receives the current text demand information that active user is sent by client, is determined according to identification information current User is demand user, and corresponding phonetic notation text is sent to client according to current text demand information, for being used to current Family is showed.Wherein, as shown in figure 3, in yet another embodiment of the present invention, step S13 may include following sub-step:

S131 receives the current text demand information that active user is sent by client.

S132 determines that the language form for the demand text for including in the current text demand information received is original language.

After the current text demand information that step S131 receives that active user is sent by client, if step S132 determines that the language form for the demand text for including in the current text demand information received is original language, then enters step S133。

S133 determines that active user is demand user according to identification information.

S134 sends corresponding phonetic notation text according to current text demand information to client, for active user Showed.

It should be noted that the language form for the demand text for including in determining the current text demand information received For original language, and determine that active user is just to send current text demand letter to client after demand user according to identification information Corresponding phonetic notation text is ceased, network transmission cost can be greatly saved.In addition, step S134 is according to current text demand information Corresponding phonetic notation text actively is sent to client, it can be in order to actively finding the demand user of phonetic notation text and do not find actively The demand user of phonetic notation text has for example formed the user of specific custom, can easily obtain phonetic notation text, In to have formed the user of specific custom can be to learn the song of original language by learning the pronunciation of original language such as Japanese Or the user of video etc..

Further, in one embodiment of the invention, it is sent and is corresponded to client according to current text demand information Phonetic notation text while, source language text, and the data format and original language of phonetic notation text can also be sent to client The data format of text can be Lrc formats or other formats.

The method for carrying out automatic phonetic notation processing to text of the embodiment of the present invention passes through client receiving active user After the current text demand information of transmission, determine that the language form in the current text demand information received is original language, And determine that active user is demand user according to the identification information of the demand user obtained, and then according to current text demand Information sends to client and carries out transformed phonetic notation text to current text based on hidden code model.This notes text automatically The method of sound processing can automatically generate Chinese character phonetic alphabet text that is intelligible or easily pronouncing according to foreign language source language text, and main It is dynamic that Chinese character phonetic alphabet text is supplied to demand user, easily learn the pronunciation of foreign language original language song convenient for demand user, uses Family Experience Degree is high, and at low cost.

Second aspect of the present invention embodiment also proposes a kind of method shown to phonetic notation text, and this method is from client Side is described, as shown in figure 4, this approach includes the following steps:

S41 sends the current text demand information of active user to server.

It should be noted that in one embodiment of the invention, the demand text for including in current text demand information Language form be original language foreign language such as Japanese.

S42 receives the phonetic notation text that server is sent, shows phonetic notation text in a predefined manner, for active user Showed.Wherein, phonetic notation text be server according to current text demand information based on the note obtained after hidden code model conversion Sound text.Specifically, to hidden code model illustrate same step S11 pair it should be noted that following repeat no more.Further, In another embodiment of the present invention, as shown in figure 5, step S42 can be divided into following three sub-steps:

S421 receives the phonetic notation text that server is sent.

S422 shows phonetic notation text in a predefined manner, for showing to active user.

In addition, in one embodiment of the invention, as shown in figure 5, when phonetic notation text is the phonetic notation lyrics, with predetermined party Formula shows that phonetic notation text, that is, step S422 may be used following two modes and realize:

S423 shows phonetic notation text below the former lyrics.

Specifically, in one embodiment of the invention, in PC(Personal Computer, personal computer), mobile phone In the mobile devices such as tablet computer, show that the display interface of phonetic notation text is as shown in Figure 6 below the former lyrics.In Fig. 6, original song The language of word is Japanese, and the language of phonetic notation text is Chinese, and shows a line and corresponding former song of content by phonetic notation text A line alternating sequence of word is shown.In addition, in one embodiment of the invention, under card OK patterns, in the former lyrics Lower section shows that the display interface of phonetic notation text is as shown in Figure 7.In Fig. 7, the language of the former lyrics is Japanese, and the language of phonetic notation text is Chinese, and show that content is a line phonetic notation text and the corresponding former lyrics of a line, the former lyrics are subsequent below phonetic notation text Display content and so on shown on interface.It should be noted that phonetic notation text and the former lyrics under card OK patterns It can not roll simultaneously.It should be further noted that showing that phonetic notation text can be in order to original language and correspondence below the former lyrics Phonetic notation text show simultaneously, and without to playout software carry out it is any adjustment can be realized, application is convenient and simple.

S424 obtains the switching request of active user, and phonetic notation text is shown in the position of the former lyrics of display.

Specifically, in one embodiment of the invention, as shown in Figure 8 and Figure 9, user can be in PC, mobile phone and tablet In the mobile devices such as computer and under card OK patterns by click double click or by clicking or double-clicking touch screen etc. it is dynamic Make to send out switching request, and then phonetic notation text is shown in the position of the former lyrics of display according to switching request.

It should be noted that above-mentioned steps S423 and S424 are two kinds of display modes arranged side by side.

Further, in one embodiment of the invention, user can be in mobile devices such as PC, mobile phone and tablet computers On by sliding finger or other actions on the touchscreen send out switching request, and then according to switching request in the former lyrics of display Position show phonetic notation text.Specifically, as shown in Figure 10, user can be sent out by sliding finger to the left on the touchscreen Switching request, and then phonetic notation text is shown in the position of the former lyrics of display according to switching request.

Further, it in yet another embodiment of the present invention, as shown in figure 11, is shown in the position of the former lyrics of display I.e. after step S424, this method can also include phonetic notation text:

S425 obtains the switching request of active user, in the former lyrics of position display of display phonetic notation text.

Specifically, in another embodiment of the present invention, as shown in Figure 12 and Figure 13, user can PC, mobile phone and By clicking or double click or by clicking or double-clicking touch screen in the mobile devices such as tablet computer and under card OK patterns Equal actions show the former lyrics according to switching request to send out switching request in the position of display phonetic notation text.

Further, in another embodiment of the present invention, user can set in the movement such as PC, mobile phone and tablet computer Switching request is sent out by sliding finger or other actions on the touchscreen on standby, and then according to switching request in display phonetic notation The former lyrics of position display of text.Specifically, as shown in figure 14, user can be sent out by sliding finger to the right on the touchscreen Go out switching request, and then phonetic notation text is shown in the position of the former lyrics of display according to switching request.It is above-mentioned with a variety of predetermined ways Display phonetic notation text can so that after sending phonetic notation text, demand user can use and show according to individual demand and hobby Show phonetic notation text, to psychologically be easier to receive and be accustomed to this mode for actively providing phonetic notation text, and it is a variety of aobvious The mode of showing may be that user brings better experience.

The method that phonetic notation text is shown of the embodiment of the present invention, by sending the current of active user to server Text demand information obtains phonetic notation text, and then shows the phonetic notation text in a predetermined manner.This shows phonetic notation text The method shown can make display mode of the user according to demand with the flexible selection Chinese character phonetic alphabet text of custom, easy to use, Operability is good, and user experience is high.

Third aspect present invention embodiment also proposes a kind of device carrying out automatic phonetic notation processing to text, such as Figure 15 institutes Show, which includes:Phonetic notation module 10 obtains module 20 and transceiver module 30.Wherein, Phonetic notation module 10 is used for the phonetic notation text by the text conversion of original language for object language based on hidden code model.Module 20 is obtained to use In the identification information for obtaining demand user.Transceiver module 30 is used to receive active user and is needed by the current text that client is sent Seek information, according to identification information determine active user be demand user, according to current text demand information to client send pair The phonetic notation text answered, for showing to active user.It should be noted that in one embodiment of the invention, text Can include language form and title of demand text etc. in this demand information.It should be further noted that the present invention is implemented The text automatic phonetic notation of original language can be object language by the device to text progress automatic phonetic notation processing of example, wherein source Language can be the foreign languages such as English, Japanese, and object language can be Chinese, and text can be the lyrics.In addition, the one of the present invention In a embodiment, the text conversion of original language can lower concentrate based on hidden code model be online object language by phonetic notation module 10 Phonetic notation text is converted so as to avoid being repeated several times, the calculating cost and computing capability of phonetic notation module 10 is greatly saved.

Specifically, in one embodiment of the invention, hidden code model can be:

Original language:アイしてる

Language model:Auntie's frenulum road

Hidden code model:Auntie leads the way

The phonetic notation text of the more above-mentioned corresponding language model of source language text in long phrase rank and hidden code model Sequence labelling text, it is found that although the sequence labelling text of hidden code model be language model phonetic notation text On the basis of adjustment system for, but the sequence labelling text of hidden code model compared with language model phonetic notation text on feel for the language and semantically It is all more clear and coherent, to be easier to be understood and remembered by user.In addition, it is necessary to explanation, the sequence labelling of hidden code model Text also has in phrase rank and sentence level, feel for the language and semantic also more clear and coherent advantage.

In addition, in one embodiment of the invention, obtaining module 20 specifically for receiving all users and passing through client The text demand information of transmission, the language form for counting each user demand text include time of the text demand information of original language Number, the user that number is more than to pre-determined number are determined as demand user, or for determining demand user according to preset condition.Tool Body, user can be selected online by client such as client online music service or Online Video service client Service content is such as the foreign language song in foreign language categorizing songs or the outer text video in foreign language visual classification, and then client root According to the selection sending information demand information of user, module 20 is obtained after receiving text demand information, to the language of demand text Speech type includes that the number of text demand information of original language is counted, and when the number is more than pre-determined number such as 5 times, It obtains module 20 and determines that the user is the user of often selection original language online service content, and it is phonetic notation text to identify the user Demand user.Furthermore, it is necessary to explanation, preset condition can be by client for example online music service client or Line Video service client etc. selects the foreign language song in online service content such as foreign language categorizing songs or outer text video for the first time The user of outer text video in classification etc., and obtain module 20 and have determined that mother tongue is the user etc. of non-original language.

Further, in one embodiment of the invention, transceiver module 30 is additionally operable to work as according to identification information determination Before preceding user is demand user, determine that the language form for the demand text for including in the current text demand information received is Original language.

It should be noted that determining the demand text for including in the current text demand information received in transceiver module 30 Language form be original language, and according to identification information determine active user be just sent to client after demand user it is current The corresponding phonetic notation text of text demand information, can greatly save network transmission cost.In addition, transceiver module 30 is according to current Text demand information actively sends corresponding phonetic notation text to client, can be in order to actively finding the demand user of phonetic notation text The demand user for not finding phonetic notation text actively has for example formed the user of specific custom, can easily obtain Phonetic notation text, wherein the user for having formed specific custom can be to learn source by learning the pronunciation of original language such as Japanese The user of the song of language or video etc..Further, in one embodiment of the invention, transceiver module 30 is according to ought be above While this demand information sends corresponding phonetic notation text to client, source language text can also be sent to client, and The data format of phonetic notation text and the data format of source language text can be Lrc formats or other formats.

It is logical to receive active user in transceiver module for the device that automatic phonetic notation processing is carried out to text of the embodiment of the present invention It crosses after the current text demand information of client transmission, determines that the language form in the current text demand information received is Original language, and then determine that active user is demand user according to the identification information for obtaining the demand user that module has obtained, and Phonetic notation module is sent to client be based on hidden code model to the transformed note of current text progress according to current text demand information Sound text.This to text carry out automatic phonetic notation processing device can be automatically generated according to foreign language source language text it is intelligible or The Chinese character phonetic alphabet text easily to pronounce, and Chinese character phonetic alphabet text is actively supplied to demand user, convenient for demand, user easily learns The pronunciation of foreign language original language song is practised, user experience is high, and at low cost.

In addition, fourth aspect present invention embodiment also proposes a kind of device shown to phonetic notation text, such as Figure 16 institutes Show, which includes:Sending module 101 and display module 102.Wherein, sending module 101 is used In the current text demand information for sending active user to server 103.Display module 102 is for receiving the transmission of server 103 Phonetic notation text, phonetic notation text is shown in a predefined manner, for showing to active user.Wherein, phonetic notation text is clothes Business device 103 is according to current text demand information based on the phonetic notation text obtained after hidden code model conversion.It should be noted that at this In one embodiment of invention, the language form for the demand text for including in current text demand information is original language such as Japanese Equal foreign languages.

Further, in one embodiment of the invention, when phonetic notation text is the phonetic notation lyrics, display module 102 has Body below the former lyrics for showing phonetic notation text, or the switching request for obtaining active user, in the former lyrics of display Position shows phonetic notation text.It should be noted that display module 102 shows that phonetic notation text can be in order to source language below the former lyrics It makes peace and corresponding phonetic notation text while showing, and can be realized without carrying out any adjustment to playout software, using facilitating letter It is single.Specifically, in one embodiment of the invention, user can in the mobile devices such as PC, mobile phone and tablet computer and Block under OK patterns, by clicking or double click or by clicking or double-clicking touch screen or sliding finger etc. is dynamic on the touchscreen Make to send out switching request, and then display module 102 shows phonetic notation text according to switching request in the position of the former lyrics of display.

Further, in another embodiment of the present invention, display module 102 can be also used in the former lyrics of display After position shows phonetic notation text, the switching request of active user is obtained, in the former lyrics of position display of display phonetic notation text.Tool Body, in another embodiment of the present invention, user can be in the mobile devices such as PC, mobile phone and tablet computer and in card Under OK patterns, by click double click or by click or double-click touch screen or on the touchscreen the actions of sliding finger etc. come Switching request is sent out, and then display module 102 shows the former lyrics according to switching request in the position of display phonetic notation text.

It should be noted that above-mentioned display module 102 shows that phonetic notation text can to send mould with a variety of predetermined ways For block 101 after sending phonetic notation text, demand user can use and show phonetic notation text according to individual demand and hobby, to It is psychologically easier to receive and be accustomed to this mode that phonetic notation text is actively provided, and a variety of displays of display module 102 Mode may be that user brings better experience.

The device of the embodiment of the present invention shown to phonetic notation text sends current use by sending module to server The current text demand information at family, and then the display module phonetic notation text that display server is sent in a predetermined manner.This is to note The device that sound text is shown can make display side of the user according to demand with the flexible selection Chinese character phonetic alphabet text of custom Formula, easy to use, operability is good, and user experience is high.

It should be appreciated that each section of the present invention can be realized with hardware, software, firmware or combination thereof.Above-mentioned In embodiment, software that multiple steps or method can in memory and by suitable instruction execution system be executed with storage Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware Any one of row technology or their combination are realized:With the logic gates for realizing logic function to data-signal Discrete logic, with suitable combinational logic gate circuit application-specific integrated circuit, programmable gate array(PGA), scene Programmable gate array(FPGA)Deng.

In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any One or more embodiments or example in can be combined in any suitable manner.

Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that:Not In the case of being detached from the principle of the present invention and objective a variety of change, modification, replacement and modification can be carried out to these embodiments, this The range of invention is limited by claim and its equivalent.

Claims (8)

1. a kind of method carrying out automatic phonetic notation processing to text, which is characterized in that including:
Based on hidden code model by the phonetic notation text that the text conversion of original language is object language, wherein described will based on hidden code model The text conversion of original language is the phonetic notation text of object language, including is handled under online processing and line, and the hidden code model is:Wherein,For original language sequence,For object language sequence,For Original language to original language phoneme probability,For original language phoneme to the probability of object language phoneme,For target Language phoneme to object language sequence probability,For object language phoneme, For transition probability, π is statistics Language modelObtained original state, For the probability of object language phoneme to object language,For the probability of language model;
The identification information of acquisition demand user, wherein receive the text demand information that all users are sent by client, count The language form of each user demand text includes the number of the text demand information of the original language, and the number is big It is determined as the demand user in the user of pre-determined number;Or the demand user is determined according to preset condition;And
The current text demand information that active user is sent by client is received, is determined according to the identification information described current User is the demand user, and corresponding phonetic notation text is sent to the client according to the current text demand information, with For showing to the active user, wherein determine that the active user is described according to the identification information described Before demand user, the method further includes:Determine the demand text for including in the current text demand information received Language form be the original language.
2. the method as described in claim 1, which is characterized in that include the class of languages of demand text in the text demand information Type and title.
3. a kind of method shown to phonetic notation text, which is characterized in that including:
The current text demand information of active user is sent to server;
The phonetic notation text that the server is sent is received, shows the phonetic notation text in a predefined manner, for described current User shows, wherein described to show the phonetic notation text packet in a predefined manner when the phonetic notation text is the phonetic notation lyrics It includes:The phonetic notation text is shown below the former lyrics;Or the switching request of the active user is obtained, showing the former song The position of word shows the phonetic notation text, wherein it is described show the position of the former lyrics show the phonetic notation text it Afterwards, the method further includes:The switching request for obtaining the active user, described in showing that the position of the phonetic notation text shows The former lyrics;
Wherein, the phonetic notation text is to be obtained after the server is based on hidden code model conversion according to the current text demand information The current text demand information is converted to phonetic notation text by the phonetic notation text arrived based on hidden code model, including online processing and It is handled under line, the hidden code model is:Wherein,For original language sequence Row,For object language sequence,For original language to the probability of original language phoneme,For original language phoneme To the probability of object language phoneme,For object language phoneme to the probability of object language sequence,For object language sound Element, For transition probability, π is statistical language modelObtained original state, For object language phoneme to object language Probability,For the probability of language model.
4. method as claimed in claim 3, which is characterized in that the demand text for including in the current text demand information Language form is original language.
5. a kind of device carrying out automatic phonetic notation processing to text, which is characterized in that including:
Phonetic notation module is used for the phonetic notation text that the text conversion of original language is object language based on hidden code model, wherein described be based on The text conversion of original language is the phonetic notation text of object language by hidden code model, including is handled under online processing and line, the hidden code mould Type is:Wherein,For original language sequence,For object language sequence,For original language to the probability of original language phoneme,For original language phoneme to the probability of object language phoneme,For object language phoneme to the probability of object language sequence,For object language phoneme, To turn Probability is moved, π is statistical language modelObtained original state, For the probability of object language phoneme to object language,For the probability of language model;
Obtain module, the identification information for obtaining demand user, wherein receive the text that all users are sent by client Demand information, the language form for counting each user demand text include time of the text demand information of the original language Number, the user that the number is more than to pre-determined number are determined as the demand user;Or the need are determined according to preset condition Ask user;And
Transceiver module, the current text demand information sent by client for receiving active user are believed according to the mark Breath determines that the active user is the demand user, is sent and is corresponded to the client according to the current text demand information Phonetic notation text, for showing to the active user;
Wherein, the transceiver module, is additionally operable to:Determining that the active user is the demand user according to the identification information Before, determine that the language form for the demand text for including in the current text demand information received is the original language.
6. device as claimed in claim 5, which is characterized in that include the class of languages of demand text in the text demand information Type and title.
7. a kind of device shown to phonetic notation text, which is characterized in that including:
Sending module, the current text demand information for sending active user to server;
Display module, the phonetic notation text sent for receiving the server, shows the phonetic notation text in a predefined manner, with Show in the active user, wherein when the phonetic notation text is the phonetic notation lyrics, the display module is specific to use In:The phonetic notation text is shown below the former lyrics;Or the switching request of the active user is obtained, showing the former song The position of word shows that the phonetic notation text, the display module are additionally operable to:The note is shown in the position of the display former lyrics After sound text, the switching request of the active user is obtained, the former lyrics are shown in the position of the display phonetic notation text;
Wherein, the phonetic notation text is to be obtained after the server is based on hidden code model conversion according to the current text demand information The current text demand information is converted to phonetic notation text by the phonetic notation text arrived based on hidden code model, including online processing and It is handled under line, the hidden code model is:Wherein,For original language sequence,For object language sequence,For original language to the probability of original language phoneme,It is arrived for original language phoneme The probability of object language phoneme,For object language phoneme to the probability of object language sequence,For object language phoneme, For transition probability, π is statistical language modelObtained original state, For object language phoneme to object language Probability,For the probability of language model.
8. device as claimed in claim 7, which is characterized in that the demand text for including in the current text demand information Language form is original language.
CN201410032479.7A 2014-01-23 2014-01-23 The method and apparatus that automatic phonetic notation processing and display are carried out to text CN103793364B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410032479.7A CN103793364B (en) 2014-01-23 2014-01-23 The method and apparatus that automatic phonetic notation processing and display are carried out to text

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410032479.7A CN103793364B (en) 2014-01-23 2014-01-23 The method and apparatus that automatic phonetic notation processing and display are carried out to text

Publications (2)

Publication Number Publication Date
CN103793364A CN103793364A (en) 2014-05-14
CN103793364B true CN103793364B (en) 2018-09-07

Family

ID=50669051

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410032479.7A CN103793364B (en) 2014-01-23 2014-01-23 The method and apparatus that automatic phonetic notation processing and display are carried out to text

Country Status (1)

Country Link
CN (1) CN103793364B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104809929B (en) * 2015-05-14 2018-07-13 广东小天才科技有限公司 Ancient Chinese prose learning device and its control method
CN105244027B (en) * 2015-08-31 2019-10-15 百度在线网络技术(北京)有限公司 Generate the method and system of homophonic text
CN108763521A (en) * 2018-05-25 2018-11-06 腾讯音乐娱乐科技(深圳)有限公司 The method and apparatus for storing lyrics phonetic notation
CN108763182A (en) * 2018-05-25 2018-11-06 腾讯音乐娱乐科技(深圳)有限公司 The method and apparatus for rendering the lyrics
CN108763441A (en) * 2018-05-25 2018-11-06 腾讯音乐娱乐科技(深圳)有限公司 Method, apparatus, electronic equipment and the storage medium for generating the lyrics, showing the lyrics

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1945562A (en) * 2005-10-09 2007-04-11 株式会社东芝 Training transliteration model, segmentation statistic model and automatic transliterating method and device
US7983903B2 (en) * 2007-09-07 2011-07-19 Microsoft Corporation Mining bilingual dictionaries from monolingual web pages
CN102982025A (en) * 2011-09-02 2013-03-20 北京百度网讯科技有限公司 Identification method and device for searching requirement
CN103309855A (en) * 2013-06-18 2013-09-18 江苏华音信息科技有限公司 Audio-video recording and broadcasting device capable of translating speeches and marking subtitles automatically in real time for Chinese and foreign languages
US8612206B2 (en) * 2009-12-08 2013-12-17 Microsoft Corporation Transliterating semitic languages including diacritics

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6288991B1 (en) * 1995-03-06 2001-09-11 Fujitsu Limited Storage medium playback method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1945562A (en) * 2005-10-09 2007-04-11 株式会社东芝 Training transliteration model, segmentation statistic model and automatic transliterating method and device
US7983903B2 (en) * 2007-09-07 2011-07-19 Microsoft Corporation Mining bilingual dictionaries from monolingual web pages
US8612206B2 (en) * 2009-12-08 2013-12-17 Microsoft Corporation Transliterating semitic languages including diacritics
CN102982025A (en) * 2011-09-02 2013-03-20 北京百度网讯科技有限公司 Identification method and device for searching requirement
CN103309855A (en) * 2013-06-18 2013-09-18 江苏华音信息科技有限公司 Audio-video recording and broadcasting device capable of translating speeches and marking subtitles automatically in real time for Chinese and foreign languages

Also Published As

Publication number Publication date
CN103793364A (en) 2014-05-14

Similar Documents

Publication Publication Date Title
Estes et al. Can infants map meaning to newly segmented words? Statistical segmentation and word learning
Woolard Codeswitching
Paciello Web accessibility for people with disabilities
Rosell-Aguilar Top of the pods—In search of a podcasting “podagogy” for language learning
Brewster Using nonspeech sounds to provide navigation cues
Wouters et al. How to optimize learning from animated models: A review of guidelines based on cognitive load
US6377925B1 (en) Electronic translator for assisting communications
US10002132B2 (en) User interface for realtime language translation
JP2005031882A (en) Information processing method and device
US9262935B2 (en) Systems and methods for extracting keywords in language learning
Bain et al. Speech recognition in university classrooms: liberated learning project
CN103703431B (en) Automatically create the mapping between text data and voice data
Vonderohe et al. Adaptation of geographic information systems for transportation
Gall et al. Music composition lessons: the multimodal affordances of technology
US9317500B2 (en) Synchronizing translated digital content
Bauer Music learning today: Digital pedagogy for creating, performing, and responding to music
CN103988193B (en) Manage the broadcasting of synchronizing content
CN105190607A (en) User training by intelligent digital assistant
CN102667889A (en) Apparatus and method for foreign language study
Perlman et al. Iconicity can ground the creation of vocal symbols
CN1423216A (en) Alternative supporting device and method
James Presenting HTML structure in audio: User satisfaction with audio hypertext
US8793118B2 (en) Adaptive multimodal communication assist system
US20130068086A1 (en) Piano learning system for tablet and touchscreen devices
Gottlieb et al. Academic language in diverse classrooms: Definitions and contexts

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant