CN105869447A - Generating method and device of audiobook - Google Patents
Generating method and device of audiobook Download PDFInfo
- Publication number
- CN105869447A CN105869447A CN201610192366.2A CN201610192366A CN105869447A CN 105869447 A CN105869447 A CN 105869447A CN 201610192366 A CN201610192366 A CN 201610192366A CN 105869447 A CN105869447 A CN 105869447A
- Authority
- CN
- China
- Prior art keywords
- background
- reading matter
- voice
- sound
- talking book
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/06—Electrically-operated educational appliances with both visual and audible presentation of the material to be studied
- G09B5/062—Combinations of audio and printed presentations, e.g. magnetically striped cards, talking books, magnetic tapes with printed texts thereon
Abstract
The invention provides a generating method and device of an audiobook, relating to the technical field of information processing. The problems of low generation efficiency and poor generation flexibility of existing audiobooks are solved. The technical scheme of the invention is that the method comprises a step of obtaining background pictures and book audios of an audiobook to be generated, a step of receiving an instruction of adjusting a background picture display sequence, wherein, the instruction comprises background pictures to be adjusted and book voice time points corresponding to the background pictures to be adjusted, a step of adjusting the sequence of the background pictures to be adjusted to the corresponding book voice time points according to the instruction. The invention is mainly used for generating the audiobooks.
Description
Technical field
The present embodiments relate to technical field of information processing, particularly relate to the generation side of a kind of talking book
Method and device.
Background technology
Along with knowledge, the diversification of information acquiring pattern, especially constantly rush at emerging digitlization medium
Hitting under traditional papery books ,newspapers and magazines, social system monitoring custom occurs to change the most to a certain extent, sound
Reading matter arises at the historic moment under this scene.Wherein, talking book is the book of sound, such as sound news,
Sound novel, children voice material etc., talking book has and intersects with digitlization and traditional publication and distinguish,
There is the advantage of its uniqueness, the reading requirement of different user can be met by talking book.
At present, talking book is background video and the captions being made talking book by video software, then
Obtain for the sound that this talking book typing is corresponding.But the background of talking book is done by video software
Video and captions require a great deal of time and energy, and the background video of this talking book and captions are only
Can be applied on this talking book, the formation efficiency of the most existing talking book is low, and flexibility is poor.
Summary of the invention
Embodiments provide the generation method and device of a kind of talking book, in order to solve existing skill
In art the formation efficiency of talking book low and generate very flexible problem.
The problem existed for prior art, embodiments provides the generation side of a kind of talking book
Method, including:
Obtain the background picture of talking book to be generated, reading matter voice；
Receive adjust background picture DISPLAY ORDER instruction, described instruction include background picture to be adjusted and with
The reading matter Speech time point that described background picture to be adjusted is corresponding；
According to described instruction, the order of described background picture to be adjusted is adjusted to the reading matter Speech time of correspondence
On point；
According to talking book described in the background picture order after described adjustment and described reading matter speech production.
Concrete, the background picture of described acquisition talking book to be generated, reading matter voice include:
Obtain the background music of talking book to be generated, described background music and the broadcasting of described reading matter voice
Duration is equal；
Concrete, described according to described in the background picture order after described adjustment and described reading matter speech production
Talking book includes:
According to the background picture order after described adjustment, described background music and described reading matter speech production institute
State talking book.
Further, after the background music of described acquisition talking book to be generated, described method also includes:
Extracting the attribute tags in described reading matter voice, each attribute tags all correspondences have described reading matter voice
In reproduction time scope, described attribute tags includes but are not limited to scene properties label, atmosphere attribute
Label, character attribute label.
Further, after the attribute tags in described extraction described reading matter voice, described method also includes:
If described attribute tags is scene properties label, then from scene sound bank, obtain the scene back of the body of correspondence
Jing Yin；
If described attribute tags is atmosphere attribute tags, then from atmosphere sound bank, obtain the atmosphere back of the body of correspondence
Jing Yin；
If described attribute tags is personage's attribute tags, then the personage obtaining correspondence from personage's sound bank belongs to
Property.
Further, after the background music of described acquisition talking book to be generated, described method also includes:
Background sound corresponding with described reproduction time scope in described background music is replaced to corresponding scene
Background sound or atmosphere background sound.
Voice evil spirit sound corresponding with described reproduction time scope in described reading matter voice become corresponding personage belong to
Property.
Embodiments provide the generating means of a kind of talking book, including:
Acquiring unit, for obtaining the background picture of talking book to be generated, reading matter voice；
Receiving unit, be used for receiving adjustment background picture DISPLAY ORDER instruction, described instruction includes waiting to adjust
Whole background picture and the reading matter Speech time point corresponding with described background picture to be adjusted；
Adjustment unit, for being adjusted to correspondence according to described instruction by the order of described background picture to be adjusted
Reading matter Speech time point on；
Signal generating unit, for according to the background picture order after described adjustment and described reading matter speech production institute
State talking book.
Described acquiring unit, is additionally operable to obtain the background music of talking book to be generated, described background music
Equal with the playing duration of described reading matter voice；
Described signal generating unit, specifically for according to the background picture order after described adjustment, described background sound
Talking book described in happy described reading matter speech production.
Further, described device also includes:
Extraction unit, for extracting the attribute tags in described reading matter voice, each attribute tags is the most corresponding
Having the reproduction time scope in described reading matter voice, described attribute tags includes but are not limited to scene properties
Label, atmosphere attribute tags, character attribute label.
Described acquiring unit, if being additionally operable to described attribute tags is scene properties label, then from scene voice
Storehouse obtains the scene background sound of correspondence；
Described acquiring unit, if being additionally operable to described attribute tags is atmosphere attribute tags, then from atmosphere voice
Storehouse obtains the atmosphere background sound of correspondence；
Described acquiring unit, if being additionally operable to described attribute tags is personage's attribute tags, then from personage's voice
Storehouse obtains the character attribute of correspondence.
Further, described device also includes:
Replacement unit, for replacing background sound corresponding with described reproduction time scope in described background music
Change scene background sound or the atmosphere background sound of correspondence into.
Evil spirit sound unit, for by voice evil spirit sound corresponding with described reproduction time scope in described reading matter voice
Become corresponding character attribute.
The generation method and device of a kind of talking book that the embodiment of the present invention provides, first obtains to be generated
The background picture of talking book, reading matter voice, then receive and adjust the instruction of background picture DISPLAY ORDER, institute
State instruction and include background picture to be adjusted and the reading matter Speech time corresponding with described background picture to be adjusted
Point, when being adjusted to corresponding reading matter voice further according to described instruction by the order of described background picture to be adjusted
Between point on, finally according to after described adjustment background picture order and described reading matter speech production described in sound
Reading matter.Make with the reading matter voice of the background video and recording of making talking book by video software at present
Talking book compare, the background video of the talking book in the middle of the embodiment of the present invention is to pass through plurality of pictures
Generate, therefore background video can be obtained flexibly and configure by the embodiment of the present invention, thus
Solved the problem making talking book background video difficulty in prior art by the embodiment of the present invention, enter
And improve the formation efficiency of talking book, and the flexibility that talking book generates.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to reality
Execute the required accompanying drawing used in example or description of the prior art to be briefly described, it should be apparent that below,
Accompanying drawing in description is some embodiments of the present invention, for those of ordinary skill in the art, not
On the premise of paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The generation method flow diagram of a kind of talking book that Fig. 1 provides for the embodiment of the present invention；
The generation method flow diagram of the another kind of talking book that Fig. 2 provides for the embodiment of the present invention；
The generating means structural representation of a kind of talking book that Fig. 3 provides for the embodiment of the present invention；
The generating means structural representation of the another kind of talking book that Fig. 4 provides for the embodiment of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with this
Accompanying drawing in bright embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention,
Obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on
Embodiment in the present invention, those of ordinary skill in the art are obtained under not making creative work premise
The every other embodiment obtained, broadly falls into the scope of protection of the invention.
Embodiments provide a kind of generation method of talking book, as it is shown in figure 1, described method
Including:
101, the background picture of talking book to be generated, reading matter voice are obtained.
Wherein, described background picture can be the photo of shooting, it is also possible to be the figure downloaded in the middle of network
Sheet, it is also possible to being the picture etc. by Software on Drawing, the embodiment of the present invention is not specifically limited.Described reading
Story sound is the voice that user records, it is also possible to the voice downloaded by network, and the embodiment of the present invention is not done
Concrete restriction.
Such as, if user's talking book to be generated is children's story " small red cap ", then available by clapping
The mode taking the photograph " small red cap " strip cartoon obtains the background picture of talking book, the most permissible as reading matter voice
Obtain by recording the voice of " small red cap " story that user reads.
102, adjustment background picture DISPLAY ORDER instruction is received.
Wherein, described instruction includes background picture to be adjusted and corresponding with described background picture to be adjusted
Reading matter Speech time point.In embodiments of the present invention, the reading matter time point that background picture to be adjusted is corresponding is
User is configured, and user can be according to its reading matter speech play recorded order, from background picture
Select the picture corresponding with its playing sequence, reach background picture and reading matter in the talking book generated with this
The coupling of voice.Such as, the description in first 1-3 minute in " Snow White " reading matter voice that user records
Be the appearance in Snow White's childhood, within 4-6 minute, tell about is the arrival of its stepmother, within 7-8 minute, tells about
It is that stepmother hello Snow White eats poison apple, then according to the description of plot in reading matter voice, divides for 1-3
The picture in clock distribution Snow White's childhood, distributed, for 4-6 minute, the picture that stepmother arrives, for 7-8 minute
Distribution stepmother feeds Snow White and eats poison apple picture, completes mating of reading matter voice and background picture with this.
103, according to described instruction, the order of described background picture to be adjusted is adjusted to the reading matter voice of correspondence
On time point.
If it should be noted that not receiving adjustment background picture DISPLAY ORDER instruction, then background picture
DISPLAY ORDER is the order uploading background picture, and the display duration of each background picture is identical.Example
As, reading matter voice time a length of 10 minutes, background picture is 5, if adjusting the display of background picture
The order i.e. playing duration of its correspondence, during the display of the most each background picture a length of 2 minutes, background picture
The order that DISPLAY ORDER is uploading pictures.
104, according to sound reading described in the background picture order after described adjustment and described reading matter speech production
Thing.
In embodiments of the present invention, the background picture after adjustment can play out by the way of lantern slide,
While playing lantern slides background picture, configure the reading matter voice of correspondence, generate described talking book with this.
In embodiments of the present invention, it is by many due to the background video of the talking book in the middle of the embodiment of the present invention
Pictures generates, and therefore can be obtained background video flexibly by the embodiment of the present invention and configure,
Thus solved by the embodiment of the present invention and prior art makes asking of talking book background video difficulty
Topic, and then improve the formation efficiency of talking book, and the flexibility that talking book generates.
The generation method of a kind of talking book that the embodiment of the present invention provides, first obtains sound reading to be generated
The background picture of thing, reading matter voice, then receive and adjust the instruction of background picture DISPLAY ORDER, described instruction
Include background picture to be adjusted and the reading matter Speech time point corresponding with described background picture to be adjusted, then
According to described instruction, the order of described background picture to be adjusted is adjusted to the reading matter Speech time point of correspondence
On, finally according to talking book described in the background picture order after described adjustment and described reading matter speech production.
Sound with what the reading matter voice of the background video and recording of making talking book by video software at present made
Reading matter is compared, owing to the background video of the talking book in the middle of the embodiment of the present invention is raw by plurality of pictures
Become, therefore background video can be obtained flexibly and configure by the embodiment of the present invention, thus logical
Cross the embodiment of the present invention and solve the problem making talking book background video difficulty in prior art, and then
Improve the formation efficiency of talking book, and the flexibility that talking book generates.
Embodiments provide the generation method of another kind of talking book, as in figure 2 it is shown, described side
Method includes:
201, the background picture of talking book to be generated, reading matter voice, background music are obtained.
Wherein, the playing duration of described background music and described reading matter voice is equal, and described background music can
Being that user makes, it is also possible to be that network is downloaded, it is also possible to being to record, the embodiment of the present invention is not
It is specifically limited.If it should be noted that the playing duration of background music and reading matter voice is not desired to, then
Can be by the way of intercepting background music so that the duration of background music is identical with reading matter voice.
In embodiments of the present invention, after step 201, described method also includes: extract described reading matter
Attribute tags in voice, each attribute tags is all corresponding the reproduction time scope in described reading matter voice,
Described attribute tags includes but are not limited to scene properties label, atmosphere attribute tags, character attribute label.
In embodiments of the present invention, the process extracting the attribute tags in reading matter voice concrete can be: first knows
Do not go out word corresponding to reading matter voice and the time point the most corresponding with each word, then by reading matter voice
Attribute tags in corresponding word and preset attribute tag library is mated, wherein preset attribute tag library
In attribute tags be to be set according to the actual requirements, such as scene properties label, atmosphere attribute tags,
Character attribute labels etc., the embodiment of the present invention is not specifically limited.If the word that reading matter voice is corresponding is deposited
Describe at certain section of word and mate with the attribute tags in preset attribute tag library, then obtain this section of word and reading
Reproduction time section corresponding in story sound.
Such as, after " small red cap " reading matter voice is carried out speech recognition, get 1-5 before in reading matter voice
Minute word to describe rough idea be that small red cap is walked on woodland path, local environment gentle breeze blows slowly bird's twitter
The fragrance of a flower, then extracting the attribute tags of 1-5 minute in reading matter voice according to preset attribute tag library is that scene belongs to
Property label, this scene properties label is specifically as follows the label of various sound in the woodland corresponding with its linguistic context；
Getting the word of 6-10 minute in reading matter voice and describing rough idea is small red cap and disguise oneself as the big of grandmother
Grey wolf is talked with, then extracting in reading matter voice according to preset attribute tag library 6-10 minute is character attribute mark
Signing, wherein character attribute label is specially animal tag and little girl's label.
In embodiments of the present invention, after the attribute tags in described extraction described reading matter voice, described side
Method also includes: if described attribute tags is scene properties label, then obtain correspondence from scene sound bank
Scene background sound；If described attribute tags is atmosphere attribute tags, then from atmosphere sound bank, obtain correspondence
Atmosphere background sound；If described attribute tags is personage's attribute tags, then it is right to obtain from personage's sound bank
The character attribute answered.Wherein, scene sound bank, atmosphere sound bank and personage's sound bank are all pre-configured with
Alright, described scene sound bank includes various types of scene background sound, such as rainy day scene, arena
Scape, scene in summer etc.；Described atmosphere sound bank includes various types of atmosphere background sound, as cheerful and light-hearted
Background sound, sad background sound, gloomy background sound etc.；Described personage's sound bank includes all kinds
Personage, such as the sound of children, the sound of old man, the sound of woman, the sound etc. of animal, the present invention
Embodiment is not specifically limited.
For the embodiment of the present invention, after obtaining the voice of correspondence in various types of voice storehouse, described method is also
Including: background sound corresponding with described reproduction time scope in described background music is replaced to corresponding field
Scape background sound or atmosphere background sound.By voice corresponding with described reproduction time scope in described reading matter voice
Evil spirit sound becomes corresponding character attribute.In embodiments of the present invention, by reading matter voice with described reproduction time
Voice evil spirit sound corresponding to scope becomes corresponding character attribute, can increase vividness that talking book reads and
Interesting.As can be by " small red cap " reading matter voice, the dialogue evil spirit sound of small red cap becomes the sound of little girl
Sound, the dialogue evil spirit sound of lobo becomes to comprise the sound of wolf characteristic.
202, adjustment background picture DISPLAY ORDER instruction is received.
Wherein, described instruction includes background picture to be adjusted and corresponding with described background picture to be adjusted
Reading matter Speech time point.In embodiments of the present invention, the reading matter time point that background picture to be adjusted is corresponding is
User is configured, and user can be according to its reading matter speech play recorded order, from background picture
Select the picture corresponding with its playing sequence, reach background picture and reading matter in the talking book generated with this
The coupling of voice.
203, according to described instruction, the order of described background picture to be adjusted is adjusted to the reading matter language of correspondence
On sound time point.
If it should be noted that not receiving adjustment background picture DISPLAY ORDER instruction, then background picture
DISPLAY ORDER is the order uploading background picture, and the display duration of each background picture is identical.Example
As, reading matter voice time a length of 20 minutes, background picture is 10, if adjusting the aobvious of background picture
Show the order i.e. playing duration of its correspondence, during the display of the most each background picture a length of 2 minutes, Background
The DISPLAY ORDER of sheet is the order of uploading pictures.
204, raw according to the background picture order after described adjustment, described background music and described reading matter voice
Become described talking book.
In embodiments of the present invention, the background picture after adjustment can play out by the way of lantern slide,
While playing lantern slides background picture, configure the reading matter voice of correspondence, generate described talking book with this.
In embodiments of the present invention, it is by many due to the background video of the talking book in the middle of the embodiment of the present invention
Pictures generates, and therefore can be obtained background video flexibly by the embodiment of the present invention and configure,
Thus solved by the embodiment of the present invention and prior art makes asking of talking book background video difficulty
Topic, and then improve the formation efficiency of talking book, and the flexibility that talking book generates.
For the embodiment of the present invention, according to the plot in reading matter voice, the scene background sound that will obtain
Corresponding with atmosphere background sound it is inserted in background music, the most also reading matter voice will comprise personage's characteristic
Dialogue evil spirit sound becomes corresponding personage, thus the talking book generated by the embodiment of the present invention can increase reading
Interest and vividness.
The generation method of the another kind of talking book that the embodiment of the present invention provides, first obtains to be generated sound
The background picture of reading matter, reading matter voice, then receive and adjust the instruction of background picture DISPLAY ORDER, described finger
Order includes background picture to be adjusted and the reading matter Speech time point corresponding with described background picture to be adjusted,
Further according to described instruction, the order of described background picture to be adjusted is adjusted to the reading matter Speech time point of correspondence
On, finally according to talking book described in the background picture order after described adjustment and described reading matter speech production.
Sound with what the reading matter voice of the background video and recording of making talking book by video software at present made
Reading matter is compared, owing to the background video of the talking book in the middle of the embodiment of the present invention is raw by plurality of pictures
Become, therefore background video can be obtained flexibly and configure by the embodiment of the present invention, thus logical
Cross the embodiment of the present invention and solve the problem making talking book background video difficulty in prior art, and then
Improve the formation efficiency of talking book, and the flexibility that talking book generates.
Further, as implementing of method described in Fig. 1, embodiments providing one has
The generating means of sound reading matter, as it is shown on figure 3, described device includes: acquiring unit 31, receive unit 32,
Adjustment unit 33, signal generating unit 34.
Acquiring unit 31, for obtaining the background picture of talking book to be generated, reading matter voice；Wherein,
Described background picture can be the photo of shooting, it is also possible to be the picture downloaded in the middle of network, it is also possible to
Being the picture etc. by Software on Drawing, the embodiment of the present invention is not specifically limited.Described reading matter voice is to use
The voice that family is recorded, it is also possible to the voice downloaded by network, the embodiment of the present invention is not specifically limited.
Receiving unit 32, be used for receiving adjustment background picture DISPLAY ORDER instruction, described instruction includes treating
Adjust background picture and the reading matter Speech time point corresponding with described background picture to be adjusted；Real in the present invention
Executing in example, the reading matter time point that background picture to be adjusted is corresponding is that user is configured, and user can root
According to its reading matter speech play recorded order, from background picture, select the picture corresponding with its playing sequence,
Background picture and the coupling of reading matter voice in the talking book generated is reached with this.
Adjustment unit 33, right for the order of described background picture to be adjusted being adjusted to according to described instruction
On the reading matter Speech time point answered；If it should be noted that not receiving adjustment background picture DISPLAY ORDER
Instruction, then the DISPLAY ORDER of background picture is the order uploading background picture, and each background picture
Display duration identical
Signal generating unit 34, for according to the background picture order after described adjustment and described reading matter speech production
Described talking book.In embodiments of the present invention, the background picture after adjustment can be by the side of lantern slide
Formula plays out, and configures the reading matter voice of correspondence, generate with this while playing lantern slides background picture
Described talking book.In embodiments of the present invention, due to the back of the body of the talking book in the middle of the embodiment of the present invention
Scape video is generated by plurality of pictures, therefore background video can be carried out spirit by the embodiment of the present invention
The acquisition lived and configuration, thus solved by the embodiment of the present invention and prior art makes the talking book back of the body
The problem of scape video difficulty, and then improve the formation efficiency of talking book, and the spirit that talking book generates
Activity.
It should be noted that it is each involved by the generating means of a kind of talking book of embodiment of the present invention offer
Other of functional unit describe accordingly, the corresponding description being referred in Fig. 1, do not repeat them here.This
Inventive embodiments can be passed through hardware processor (hardware processor) and realize correlation function
Module.
The generating means of a kind of talking book that the embodiment of the present invention provides, first obtains sound reading to be generated
The background picture of thing, reading matter voice, then receive and adjust the instruction of background picture DISPLAY ORDER, described instruction
Include background picture to be adjusted and the reading matter Speech time point corresponding with described background picture to be adjusted, then
According to described instruction, the order of described background picture to be adjusted is adjusted to the reading matter Speech time point of correspondence
On, finally according to talking book described in the background picture order after described adjustment and described reading matter speech production.
With background video and the talking book phase of reading matter voice making being made talking book at present by video software
Ratio, owing to the background video of the talking book in the middle of the embodiment of the present invention is generated by plurality of pictures,
Therefore background video can be obtained flexibly and configure by the embodiment of the present invention, thus by this
Bright embodiment solves the problem making talking book background video difficulty in prior art, and then improves
The formation efficiency of talking book, and the flexibility that talking book generates.
Further, as implementing of method described in Fig. 2, another kind is embodiments provided
The generating means of talking book, as shown in Figure 4, described device includes: acquiring unit 41, reception unit
42, adjustment unit 43, signal generating unit 44.
Acquiring unit 41, for obtaining the background picture of talking book to be generated, reading matter voice；Wherein,
Described background picture can be the photo of shooting, it is also possible to be the picture downloaded in the middle of network, it is also possible to
Being the picture etc. by Software on Drawing, the embodiment of the present invention is not specifically limited.Described reading matter voice is to use
The voice that family is recorded, it is also possible to the voice downloaded by network, the embodiment of the present invention is not specifically limited.
Receiving unit 42, be used for receiving adjustment background picture DISPLAY ORDER instruction, described instruction includes treating
Adjust background picture and the reading matter Speech time point corresponding with described background picture to be adjusted；Real in the present invention
Executing in example, the reading matter time point that background picture to be adjusted is corresponding is that user is configured, and user can root
According to its reading matter speech play recorded order, from background picture, select the picture corresponding with its playing sequence,
Background picture and the coupling of reading matter voice in the talking book generated is reached with this.
Adjustment unit 43, right for the order of described background picture to be adjusted being adjusted to according to described instruction
On the reading matter Speech time point answered；If it should be noted that not receiving adjustment background picture DISPLAY ORDER
Instruction, then the DISPLAY ORDER of background picture is the order uploading background picture, and each background picture
Display duration identical
Signal generating unit 44, for according to the background picture order after described adjustment and described reading matter speech production
Described talking book.In embodiments of the present invention, the background picture after adjustment can be by the side of lantern slide
Formula plays out, and configures the reading matter voice of correspondence, generate with this while playing lantern slides background picture
Described talking book.In embodiments of the present invention, due to the back of the body of the talking book in the middle of the embodiment of the present invention
Scape video is generated by plurality of pictures, therefore background video can be carried out spirit by the embodiment of the present invention
The acquisition lived and configuration, thus solved by the embodiment of the present invention and prior art makes the talking book back of the body
The problem of scape video difficulty, and then improve the formation efficiency of talking book, and the spirit that talking book generates
Activity.
Described acquiring unit 41, is additionally operable to obtain the background music of talking book to be generated, described background sound
The playing duration of happy described reading matter voice is equal；Described background music can be that user makes, it is possible to
To be network download, it is also possible to being to record, the embodiment of the present invention is not specifically limited.Need explanation
If the playing duration of background music and reading matter voice is not desired to, then can be by intercepting background music
Mode so that the duration of background music is identical with reading matter voice.
Described signal generating unit 44, specifically for according to the background picture order after described adjustment, described background
Talking book described in music and described reading matter speech production.
Further, described device also includes:
Extraction unit 45, for extracting the attribute tags in described reading matter voice, each attribute tags is the most right
Should have the reproduction time scope in described reading matter voice, described attribute tags includes but are not limited to scene and belongs to
Property label, atmosphere attribute tags, character attribute label.In embodiments of the present invention, reading matter voice is extracted
In the concrete process of attribute tags can be: first identify word corresponding to reading matter voice and and each
The time point that word is the most corresponding, then by word corresponding for reading matter voice and preset attribute tag library
Attribute tags is mated, and wherein the attribute tags in preset attribute tag library is to carry out according to the actual requirements
Setting, such as scene properties label, atmosphere attribute tags, character attribute label etc., the embodiment of the present invention is not
It is specifically limited.If the word that reading matter voice is corresponding existing certain section of word describe and preset attribute tag library
In attribute tags coupling, then obtain the reproduction time section that this section of word is corresponding in reading matter voice.
Described acquiring unit 41, if being additionally operable to described attribute tags is scene properties label, then from scene language
Sound storehouse obtains the scene background sound of correspondence；
Described acquiring unit 41, if being additionally operable to described attribute tags is atmosphere attribute tags, then from atmosphere language
Sound storehouse obtains the atmosphere background sound of correspondence；
Described acquiring unit 41, if being additionally operable to described attribute tags is personage's attribute tags, then from people's story
Sound storehouse obtains the character attribute of correspondence.Wherein, scene sound bank, atmosphere sound bank and personage's sound bank
Being all pre-configured, described scene sound bank includes various types of scene background sound, such as the rainy day
Scene, match scene, scene in summer etc.；Described atmosphere sound bank includes various types of atmosphere background
Sound, such as cheerful and light-hearted background sound, sad background sound, gloomy background sound etc.；In described personage's sound bank
Including various types of personages, such as the sound of children, the sound of old man, the sound of woman, the sound of animal
Sounds etc., the embodiment of the present invention is not specifically limited.
Further, described device also includes:
Replacement unit 46, for by background sound corresponding with described reproduction time scope in described background music
Replace to scene background sound or the atmosphere background sound of correspondence.
Evil spirit sound unit 47, for by voice evil spirit corresponding with described reproduction time scope in described reading matter voice
Sound becomes corresponding character attribute.In embodiments of the present invention, by reading matter voice with described reproduction time model
The voice evil spirit sound enclosing correspondence becomes the character attribute of correspondence, can increase vividness and interest that talking book is read
Taste.
It should be noted that involved by the generating means of the another kind of talking book of embodiment of the present invention offer
Other of each functional unit describe accordingly, the corresponding description being referred in Fig. 2, do not repeat them here.
The embodiment of the present invention can realize related function module by hardware processor.
The generating means of the another kind of talking book that the embodiment of the present invention provides, first obtains to be generated sound
The background picture of reading matter, reading matter voice, then receive and adjust the instruction of background picture DISPLAY ORDER, described finger
Order includes background picture to be adjusted and the reading matter Speech time point corresponding with described background picture to be adjusted,
Further according to described instruction, the order of described background picture to be adjusted is adjusted to the reading matter Speech time point of correspondence
On, finally according to talking book described in the background picture order after described adjustment and described reading matter speech production.
Sound with what the reading matter voice of the background video and recording of making talking book by video software at present made
Reading matter is compared, owing to the background video of the talking book in the middle of the embodiment of the present invention is raw by plurality of pictures
Become, therefore background video can be obtained flexibly and configure by the embodiment of the present invention, thus logical
Cross the embodiment of the present invention and solve the problem making talking book background video difficulty in prior art, and then
Improve the formation efficiency of talking book, and the flexibility that talking book generates.
Device embodiment described above is only schematically, wherein said illustrates as separating component
Unit can be or may not be physically separate, the parts shown as unit can be or
Person may not be physical location, i.e. may be located at a place, or can also be distributed to multiple network
On unit.Some or all of module therein can be selected according to the actual needs to realize the present embodiment
The purpose of scheme.Those of ordinary skill in the art are not in the case of paying performing creative labour, the most permissible
Understand and implement.
Through the above description of the embodiments, those skilled in the art is it can be understood that arrive each reality
The mode of executing can add the mode of required general hardware platform by software and realize, naturally it is also possible to by firmly
Part.Based on such understanding, the portion that prior art is contributed by technique scheme the most in other words
Dividing and can embody with the form of software product, this computer software product can be stored in computer can
Read in storage medium, such as ROM/RAM, magnetic disc, CD etc., including some instructions with so that one
Computer equipment (can be personal computer, server, or the network equipment etc.) performs each to be implemented
The method described in some part of example or embodiment.
Last it is noted that above example is only in order to illustrate technical scheme, rather than to it
Limit；Although the present invention being described in detail with reference to previous embodiment, the ordinary skill of this area
Personnel it is understood that the technical scheme described in foregoing embodiments still can be modified by it, or
Person carries out equivalent to wherein portion of techniques feature；And these amendments or replacement, do not make corresponding skill
The essence of art scheme departs from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (12)
1. the generation method of a talking book, it is characterised in that including:
Obtain the background picture of talking book to be generated, reading matter voice；
Receive adjust background picture DISPLAY ORDER instruction, described instruction include background picture to be adjusted and with
The reading matter Speech time point that described background picture to be adjusted is corresponding；
According to described instruction, the order of described background picture to be adjusted is adjusted to the reading matter Speech time of correspondence
On point；
According to talking book described in the background picture order after described adjustment and described reading matter speech production.
Method the most according to claim 1, it is characterised in that described acquisition talking book to be generated
Background picture, reading matter voice includes:
Obtain the background music of talking book to be generated, described background music and the broadcasting of described reading matter voice
Duration is equal；
Described according to talking book described in the background picture order after described adjustment and described reading matter speech production
Including:
According to the background picture order after described adjustment, described background music and described reading matter speech production institute
State talking book.
Method the most according to claim 2, it is characterised in that described acquisition talking book to be generated
Background music after, described method also includes:
Extracting the attribute tags in described reading matter voice, each attribute tags all correspondences have described reading matter voice
In reproduction time scope, described attribute tags includes but are not limited to scene properties label, atmosphere attribute
Label, character attribute label.
Method the most according to claim 3, it is characterised in that in described extraction described reading matter voice
Attribute tags after, described method also includes:
If described attribute tags is scene properties label, then from scene sound bank, obtain the scene back of the body of correspondence
Jing Yin；
If described attribute tags is atmosphere attribute tags, then from atmosphere sound bank, obtain the atmosphere back of the body of correspondence
Jing Yin；
If described attribute tags is personage's attribute tags, then the personage obtaining correspondence from personage's sound bank belongs to
Property.
Method the most according to claim 4, it is characterised in that described acquisition talking book to be generated
Background music after, described method also includes:
Background sound corresponding with described reproduction time scope in described background music is replaced to corresponding scene
Background sound or atmosphere background sound.
Method the most according to claim 4, it is characterised in that described method also includes:
Voice evil spirit sound corresponding with described reproduction time scope in described reading matter voice become corresponding personage belong to
Property.
7. the generating means of a talking book, it is characterised in that including:
Acquiring unit, for obtaining the background picture of talking book to be generated, reading matter voice；
Receiving unit, be used for receiving adjustment background picture DISPLAY ORDER instruction, described instruction includes waiting to adjust
Whole background picture and the reading matter Speech time point corresponding with described background picture to be adjusted；
Adjustment unit, for being adjusted to correspondence according to described instruction by the order of described background picture to be adjusted
Reading matter Speech time point on；
Signal generating unit, for according to the background picture order after described adjustment and described reading matter speech production institute
State talking book.
Device the most according to claim 7, it is characterised in that
Described acquiring unit, is additionally operable to obtain the background music of talking book to be generated, described background music
Equal with the playing duration of described reading matter voice；
Described signal generating unit, specifically for according to the background picture order after described adjustment, described background sound
Talking book described in happy described reading matter speech production.
Device the most according to claim 8, it is characterised in that described device also includes:
Extraction unit, for extracting the attribute tags in described reading matter voice, each attribute tags is the most corresponding
Having the reproduction time scope in described reading matter voice, described attribute tags includes but are not limited to scene properties
Label, atmosphere attribute tags, character attribute label.
Device the most according to claim 9, it is characterised in that
Described acquiring unit, if being additionally operable to described attribute tags is scene properties label, then from scene voice
Storehouse obtains the scene background sound of correspondence；
Described acquiring unit, if being additionally operable to described attribute tags is atmosphere attribute tags, then from atmosphere voice
Storehouse obtains the atmosphere background sound of correspondence；
Described acquiring unit, if being additionally operable to described attribute tags is personage's attribute tags, then from personage's voice
Storehouse obtains the character attribute of correspondence.
11. devices according to claim 10, it is characterised in that described device also includes:
Replacement unit, for replacing background sound corresponding with described reproduction time scope in described background music
Change scene background sound or the atmosphere background sound of correspondence into.
12. devices according to claim 10, it is characterised in that described device also includes:
Evil spirit sound unit, for by voice evil spirit sound corresponding with described reproduction time scope in described reading matter voice
Become corresponding character attribute.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610192366.2A CN105869447A (en) | 2016-03-30 | 2016-03-30 | Generating method and device of audiobook |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610192366.2A CN105869447A (en) | 2016-03-30 | 2016-03-30 | Generating method and device of audiobook |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105869447A true CN105869447A (en) | 2016-08-17 |
Family
ID=56626604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610192366.2A Pending CN105869447A (en) | 2016-03-30 | 2016-03-30 | Generating method and device of audiobook |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105869447A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844679A (en) * | 2017-01-24 | 2017-06-13 | 广州朗锐数字传媒科技有限公司 | A kind of audiobook illustration display systems and method |
| CN109036388A (en) * | 2018-07-25 | 2018-12-18 | 李智彤 | A kind of intelligent sound exchange method based on conversational device |
| CN111968424A (en) * | 2020-08-27 | 2020-11-20 | 北京大米科技有限公司 | Interactive learning method, device, system and computer storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177611A (en) * | 2011-12-23 | 2013-06-26 | 李云峰 | Method for realizing multimedia courseware on E-ink book |
| CN104021152A (en) * | 2014-05-19 | 2014-09-03 | 广州酷狗计算机科技有限公司 | Picture display method and device based on audio file playing |
| CN104144280A (en) * | 2013-05-08 | 2014-11-12 | 上海恺达广告有限公司 | Voice and action animation synchronous control and device of electronic greeting card |
| CN104952471A (en) * | 2015-06-16 | 2015-09-30 | 深圳新创客电子科技有限公司 | Method, device and equipment for synthesizing media file |
| CN105096932A (en) * | 2015-07-14 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Voice synthesis method and apparatus of talking book |
| CN105205844A (en) * | 2015-08-27 | 2015-12-30 | 林彬 | Manufacturing method and apparatus of interactive electronic animation book, and mobile terminal |
-
2016
- 2016-03-30 CN CN201610192366.2A patent/CN105869447A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177611A (en) * | 2011-12-23 | 2013-06-26 | 李云峰 | Method for realizing multimedia courseware on E-ink book |
| CN104144280A (en) * | 2013-05-08 | 2014-11-12 | 上海恺达广告有限公司 | Voice and action animation synchronous control and device of electronic greeting card |
| CN104021152A (en) * | 2014-05-19 | 2014-09-03 | 广州酷狗计算机科技有限公司 | Picture display method and device based on audio file playing |
| CN104952471A (en) * | 2015-06-16 | 2015-09-30 | 深圳新创客电子科技有限公司 | Method, device and equipment for synthesizing media file |
| CN105096932A (en) * | 2015-07-14 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Voice synthesis method and apparatus of talking book |
| CN105205844A (en) * | 2015-08-27 | 2015-12-30 | 林彬 | Manufacturing method and apparatus of interactive electronic animation book, and mobile terminal |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106844679A (en) * | 2017-01-24 | 2017-06-13 | 广州朗锐数字传媒科技有限公司 | A kind of audiobook illustration display systems and method |
| CN106844679B (en) * | 2017-01-24 | 2021-01-22 | 广州朗锐数字传媒科技有限公司 | System and method for displaying audio book illustration |
| CN109036388A (en) * | 2018-07-25 | 2018-12-18 | 李智彤 | A kind of intelligent sound exchange method based on conversational device |
| CN111968424A (en) * | 2020-08-27 | 2020-11-20 | 北京大米科技有限公司 | Interactive learning method, device, system and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111741326B (en) | Video synthesis method, device, equipment and storage medium | |
| CN108833973A (en) | Extracting method, device and the computer equipment of video features | |
| CN109691124B (en) | Method and system for automatically generating video highlights | |
| US8892497B2 (en) | Audio classification by comparison of feature sections and integrated features to known references | |
| CN105096932A (en) | Voice synthesis method and apparatus of talking book | |
| CN109147800A (en) | Answer method and device | |
| CN108536655A (en) | Audio production method and system are read aloud in a kind of displaying based on hand-held intelligent terminal | |
| CN108877765A (en) | Processing method and processing device, computer equipment and the readable medium of voice joint synthesis | |
| CN102752540A (en) | Automatic categorization method based on face recognition technology | |
| CN105869447A (en) | Generating method and device of audiobook | |
| CN106294612A (en) | A kind of information processing method and equipment | |
| CN111108557A (en) | Method of modifying a style of an audio object, and corresponding electronic device, computer-readable program product and computer-readable storage medium | |
| Stenport | Lukas Moodysson’s Show me love | |
| CN112422844A (en) | Method, device and equipment for adding special effect in video and readable storage medium | |
| Grothaus | Trust No One: Inside the World of Deepfakes | |
| CN104036227A (en) | Electronic music score generating method and mobile terminal | |
| Alexy et al. | Pop Empires: Transnational and Diasporic Flows of India and Korea | |
| CN110797001A (en) | Method and device for generating voice audio of electronic book and readable storage medium | |
| CN108040289A (en) | A kind of method and device of video playing | |
| CN109587543B (en) | Audio synchronization method and apparatus and storage medium | |
| CN107680598A (en) | Information interacting method, device and its equipment based on good friend's vocal print address list | |
| CN110324702A (en) | Information-pushing method and device in video display process | |
| WO2022143349A1 (en) | Method and device for determining user intent | |
| CN112135201B (en) | Video production method and related device | |
| CN115134662A (en) | Multi-sample processing method and system based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160817 |
|
| WD01 | Invention patent application deemed withdrawn after publication |