CN108744521A - The method and device of game speech production, electronic equipment, storage medium - Google Patents
The method and device of game speech production, electronic equipment, storage medium Download PDFInfo
- Publication number
- CN108744521A CN108744521A CN201810687837.6A CN201810687837A CN108744521A CN 108744521 A CN108744521 A CN 108744521A CN 201810687837 A CN201810687837 A CN 201810687837A CN 108744521 A CN108744521 A CN 108744521A
- Authority
- CN
- China
- Prior art keywords
- drama
- document
- audio event
- role
- voice
- 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
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/60—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
- A63F2300/60—Methods for processing data by generating or executing the game program
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Machine Translation (AREA)
Abstract
An embodiment of the present invention provides the game method and device of speech production, electronic equipment, storage medium, the method includes：The corresponding role attribute of drama role is determined according to drama document and to white text；It is voice document by the dialogue text conversion based on the role attribute；Audio event is created according to institute's voice file；When triggering the audio event, the corresponding voice document of the audio event is played.Through the invention, it realizes and the automation for voice of playing is generated, improve the efficiency that game voice makes.
Description
Technical field
The present invention relates to field of play, are situated between more particularly to the method and device of game speech production, electronic equipment, storage
Matter.
Background technology
In online game, it usually needs make and play relevant voice, and plays voice in the process for playing game, with
The game experiencing of player is promoted, such as when game player is close to a certain NPC (Non Player Character, non-player role),
Play the corresponding voices of the NPC.
Currently, can be recorded to planning drama by after arranging for the planning drama of game, inviting voice-over actor
Sound, then supplying game manually, but the fabrication cycle of this mode is long, needs to expend a large amount of resource, and be susceptible to artificial
Mistake.
Invention content
In view of the above problems, it is proposed that the embodiment of the present invention is in order to provide overcoming the above problem or solve at least partly
The method and device of the game speech production of the above problem, electronic equipment, storage medium.
To solve the above-mentioned problems, the invention discloses game speech production method, the method includes：
The corresponding role attribute of drama role is determined according to drama document and to white text；
It is voice document by the dialogue text conversion based on the role attribute；
Audio event is created according to institute's voice file；
When triggering the audio event, the corresponding voice document of the audio event is played.
Optionally, described to be based on the role attribute, include for the step of voice document by the dialogue text conversion：
Determine the corresponding timbre information of the role attribute；
It generates described to white text corresponding dialogue vector；
According to the timbre information, the dialogue vector is converted into voice document.
Optionally, the generation step to white text corresponding dialogue vector includes：
It generates described to white text corresponding linguistics vector；
It generates described to white text corresponding mood vector；
According to linguistics vector sum mood vector, obtain described to white text corresponding dialogue vector.
Optionally, the generation step to white text corresponding mood vector includes：
From described in white text, determining key mood word；
In preset mood data library, the corresponding emotional information of the crucial mood word is matched；
Generate the corresponding mood vector of the emotional information.
Optionally, described that the corresponding role attribute of drama role is determined according to drama document and the step of white text is wrapped
It includes：
One or more drama roles are determined according to drama document；
Obtain the tag identifier in the drama document；
The role attribute of the corresponding drama role of the tag identifier is determined according to the tag identifier.
Optionally, described the corresponding role attribute of drama role determined according to drama document and the step of to white text it
Before, further include：
A drama template for creating drama document is provided, the drama template provides the mark for identified role attribute
Label mark.
Optionally, after described the step of creating audio event according to institute's voice file, further include：By the audio
Event is mounted to game engine.
Optionally, described the step of creating audio event according to institute's voice file includes calling audio engine, creates needle
To the audio event of institute's voice file；
Described mount the audio event to the step of game engine include：
Obtain the corresponding incident path of the speech events；
Using the incident path, the audio event is articulated in game engine.
Optionally, further include：
In the test process for the audio event, the result of broadcast of record institute voice file；
Generate the corresponding test log of the result of broadcast.
Optionally, the role attribute includes following one or more：
Gender, age, personality.
The invention also discloses the device of game speech production, described device includes：
Role Information determining module, for determining the corresponding role attribute of drama role according to drama document and to the text of an annotated book
This；
The dialogue text conversion is voice document for being based on the role attribute by text conversion module；
Audio event creation module, for creating audio event according to institute's voice file；
Voice document playing module, for when triggering the audio event, playing the corresponding voice of the audio event
File.
The invention also discloses electronic equipment, including processor, memory and it is stored on the memory and can be
The computer program run on the processor realizes trip as described above when the computer program is executed by the processor
The step of method of play speech production.
The invention also discloses computer readable storage medium, computer journey is stored on the computer readable storage medium
Sequence, when the computer program is executed by processor the step of the method for realization game speech production as described above.
The embodiment of the present invention includes following advantages：
In the present invention, by determining the corresponding role attribute of drama role according to drama document and to white text, and base
In role attribute, it is voice document by dialogue text conversion, audio event is then created according to voice document, in triggering audio thing
When part, the corresponding voice document of audio event is played, realizes and the automation for voice of playing is generated, improves game voice system
The efficiency of work.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the step flow chart of the method for the game speech production that one embodiment of the invention provides；
Fig. 2 is the step flow chart of the method for the game speech production that another embodiment of the present invention provides；
Fig. 3 is the structure diagram of the device for the game speech production that one embodiment of the invention provides.
Specific implementation mode
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is described in further detail.Obviously, described embodiments are some of the embodiments of the present invention, without
It is whole embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
The every other embodiment obtained is put, shall fall within the protection scope of the present invention.
Referring to Fig.1, the step flow chart of the method for the game speech production that one embodiment of the invention provides is shown, specifically
It may include steps of：
Step 101, the corresponding role attribute of drama role determined according to drama document and to white text；
In the concrete realization, project staff can be obtained and be directed to the drama document that online game is write, it then can be to play
This document is analyzed, and determines the drama role for including in drama document, and obtains the corresponding role attribute of each drama role
With to white text.
As an example, role attribute may include following one or more：
Gender, age, personality.
In an embodiment of the present invention, the step of determining drama role corresponding role attribute according to drama document can wrap
Include following sub-step：
One or more drama roles are determined according to drama document；Obtain the tag identifier in drama document；According to label
Mark determines the role attribute of the corresponding drama role of tag identifier.
As an example, tag identifier can be what project staff selected in dramatization document for drama role
Tag identifier, such as " male ", " middle age ".
After obtaining drama document, it may be determined that then the drama role in drama document searches every in drama document
The corresponding tag identifier of a drama role, to obtain corresponding role attribute.
It is, of course, also possible to the determinant attribute word for drama role be searched in drama document, as existed in drama document
To white text " small red be really a lovely girl ", then drama role " small red " can be used as corresponding " lovely ", " female "
Determinant attribute word.
When reading determinant attribute word in drama document, it may be determined that the corresponding drama role of the determinant attribute word,
Then from preset attribute database, the corresponding role attribute of determinant attribute word is matched, it is corresponding as drama role
Role attribute, and recorded.
Correspondingly, before step 101, may include steps of：
A drama template for creating drama document is provided, drama template provides the label mark for identified role attribute
Know.
In the concrete realization, the drama template for creating drama document can be pre-set, in dramatization, planning
It is that tag identifier is arranged in drama role that drama template, which may be used, in personnel.
Before step 101, parameter initialization can also be carried out, it is specific as follows：
1) the prefabricated file of parameter is judged whether；
2) if there are the prefabricated file of parameter, whether the prefabricated file of checking parameter is effective；
If 3) verification is effective, ask whether that selection uses parameter in the prefabricated file of parameter；
4) if selection uses, parameter is loaded from the prefabricated file of parameter.
If 1) be any one of -4) no, need to input new parameter list, and new parameter list write parameters are pre-
File processed, to carry out completing parameter initialization.
As an example, parameter list may include following parameter：
Fmod installation paths, Unity installation paths, Fmod engineered paths, Unity engineered paths, docx dramas path, play
This display Name, drama identification name, audio resource prefix, Fmod Event folder paths, the paths Fmod Bank,
FmodAsset folder paths, the paths Fmod Mixer Group.
In fact, drama document can be the file of docx formats, python-docx tools may be used, by docx lattice
Formula resolves to text formatting, and then from the drama document of text formatting, determines the corresponding role attribute of drama role and dialogue
Text.
It in one example, can be according to pre-loaded parameter, by the corresponding role attribute of drama role and to white text
The file for being converted to json formats the following is the example of a json formatted files：
For " example drama ", in " chapters and sections 1：Guide chapters and sections " in, there are drama role " Xiao Zhao ", role attribute is
"sex"：1, i.e. " male " are that " you have eaten today to white text？".
Meanwhile can be according to parameter, it is " event to set incident path:/ VO/example_test_1 " (incident paths
Hereinafter there is corresponding description, details are not described herein), it is " cv_default_ also to set CV table format templates
Selected CV table format templates may be used in normal ", call openpyxl tools, generate the corresponding CV tables of json information
Lattice, in order to store drama role and role attribute, to the correspondence of white text.
Step 102, dialogue text conversion is voice document by based role attribute；
Determine role attribute and to white text after, may be used TTS technologies, the sound that selection matches with role attribute
Dialogue text conversion is voice document by color.
It is asked for example, POST in HTTP (HyperText Transfer Protocol, hypertext transfer protocol) may be used
It asks, by setting HTTP Header to " content-type:Application/json ", and then json information is sent
To TTS (Text To Speech, from Text To Speech) interface, the conversion from Text To Speech is realized.
Step 103, audio event is created according to voice document；
After obtaining voice document, the audio event for voice document can be created.
In an embodiment of the present invention, step 103 may include following sub-step：
Audio engine is called, the audio event for institute's voice file is created；
In the concrete realization, calling sound can be may then pass through such as FMOD, WWISE audio engine with preset audio engine
Frequency engine, handles voice document, obtains corresponding audio event.
In an embodiment of the present invention, can also include the following steps after step 103：
Audio event is mounted to game engine；
After creating audio event, audio event can be articulated in game engine.
Specifically, it may include following sub-step that audio event, which was mounted to the step of game engine,：：
Obtain the corresponding incident path of the speech events；Using the incident path, the audio event is articulated in
In game engine.
After creating audio event, the corresponding incident path of audio event can be determined according to pre-loaded parameter, it will
Audio event is stored in corresponding incident path, and can determine that the audio event is corresponding to white text, establishes event road
Diameter and the correspondence to white text, and game engine is imported, realize the mounting to audio event.
Step 104, when triggering audio event, the corresponding voice document of audio event is played.
When some game role is needed using certain lines, it may be determined where the lines to white text, and determine
Incident path corresponding to white text triggers audio event, to play the corresponding voice document of audio event using incident path.
In an embodiment of the present invention, can also include the following steps：
In the test process for audio event, the result of broadcast of voice document is recorded；It is corresponding to generate result of broadcast
Test log.
After audio event mounting, audio event can automatically be tested by repeatedly triggering, and can record
The result of broadcast of voice document when triggering audio event every time, such as whether broadcasting, playback loudness etc., and then generate test log.
After obtaining test log, by the result of broadcast recorded in read test daily record, judge whether result of broadcast is full
The default playing condition of foot completes the production flow, can formally be reached the standard grade if so, judgement audio event triggering is normal, if
It is no, then judge that audio event triggering is abnormal, engineer can be notified to carry out abnormality processing, to improve the efficiency of test.
In the present invention, by determining the corresponding role attribute of drama role according to drama document and to white text, and base
In role attribute, it is voice document by dialogue text conversion, audio event is then created according to voice document, in triggering audio thing
When part, the corresponding voice document of audio event is played, realizes and the automation for voice of playing is generated, improves game voice system
The efficiency of work.
With reference to Fig. 2, the step flow chart of the method for the game speech production that another embodiment of the present invention provides, tool are shown
Body may include steps of：
Step 201, the corresponding role attribute of drama role determined according to drama document and to white text；
In the concrete realization, project staff can be obtained and be directed to the drama document that online game is write, it then can be to play
This document is analyzed, and determines the drama role for including in drama document, and obtains the corresponding role attribute of each drama role
With to white text.
Step 202, the corresponding timbre information of role attribute is determined；
As an example, timbre information may include the mark of tone color.
Wherein, tone color can characterize the characteristic in terms of different sound frequencies shows waveform, the vibration of sounding body be by
A variety of homophonic compositions, wherein having fundamental tone and overtone, the opposite intensity that the number and overtone of overtone compare from each other is different,
Decide some specific tone color.
Applied to tamber data library in the present invention, can be pre-set, multiple roles can be stored in tamber data library and are belonged to
The correspondence of property and timbre information can be matched when determining the corresponding role attribute of drama role in tamber data library
The role attribute obtains corresponding timbre information.
Step 203, it generates to white text corresponding dialogue vector；
It after obtaining to white text, can read to white text, be determined to including linguistics, mood in white text sentence by sentence
Relevant information, and then be dialogue vector by dialogue text conversion.
In an embodiment of the present invention, step 203 may include following sub-step：
It generates to white text corresponding linguistics vector；It generates to white text corresponding mood vector；According to linguistics to
Amount and mood vector are obtained to white text corresponding dialogue vector.
On the one hand, it may be determined that linguistic information corresponding to white text, linguistic information may include phoneme, such as
" I " corresponding phoneme is " wo " in " I is at table ", and according to the sequence occurred in white text, by linguistic information group
It is made into linguistics vector.
On the other hand, it can also determine to the corresponding emotional information of white text, as " anger " in " me as mad as a wet hen " can
With the mood of correspondence " indignation ", and can be according to the sequence occurred in white text, by emotional information tissue mood vector.
As an example, pleasant degree, degree of excitation, three latitude coordinates of slackness and emotion may be used in mood vector
Classification indicates.
Wherein, the coordinate value of each dimension can be normalized, and emotional category can mark into discrete class.
Surprised emotional category is represented for example, 0 represents happy emotional category, 1, and a certain happy mood vector can be with
It is expressed as (0.9,0.8,0.5,0), 0.9 is pleasure degree, 0.8 is degree of excitation, 0.5 is slackness, 0 is emotional category.
In an embodiment of the present invention, it may include following sub-step to the step of white text corresponding mood vector to generate
Suddenly：
From to white text, key mood word is determined；In preset mood data library, it is corresponding to match crucial mood word
Emotional information；Generate the corresponding mood vector of emotional information.
In the concrete realization, mood data library can be pre-set, multiple crucial moods can be stored in mood data library
The correspondence of word and emotional information, such as mood of " auspicious day " correspondence " happiness ".
When reading crucial mood word in dialogue document, the key mood word can be matched in mood data library,
Corresponding emotional information is obtained, and then generates the corresponding mood vector of emotional information.
Step 204, according to timbre information, dialogue vector is converted into voice document；
It, can be by timbre information and the advance trained neural network mould of dialogue vector input after generating dialogue vector
Type obtains the voice document of neural network model output
Step 205, audio event is created according to voice document；
After obtaining voice document, the audio event for voice document can be created.
Step 206, when triggering audio event, the corresponding voice document of audio event is played.
When game player triggers audio event, the corresponding voice document of the audio event can be played.
In the present invention, by determining the corresponding timbre information of role attribute, and generate to the corresponding dialogue of white text to
Amount, dialogue vector can be made of linguistics vector sum mood vector, can then proceed in timbre information, dialogue vector is converted
It for voice document, realizes to the changeable in mood of voice so that the voice of dialogue text conversion is more naturally, promote the game of player
Experience.
It should be noted that above method embodiment can be applied to client, alternatively, server, alternatively, certain applications
In client and certain applications are in server.
For embodiment of the method, for simple description, therefore it is all expressed as a series of combination of actions, but this field
Technical staff should know that the embodiment of the present invention is not limited by the described action sequence, because implementing according to the present invention
Example, certain steps can be performed in other orders or simultaneously.Next, those skilled in the art should also know that, specification
Described in embodiment belong to preferred embodiment, necessary to the involved action not necessarily embodiment of the present invention.
With reference to Fig. 3, the step flow chart of the device for the game speech production that one embodiment of the invention provides is shown, specifically
It may include following module：
Role Information determining module 301, for determining the corresponding role attribute of drama role and dialogue according to drama document
Text；
Text conversion module 302 is used for based role attribute, is voice document by dialogue text conversion；
Audio event creation module 303, for creating audio event according to voice document；
Voice document playing module 304, for when triggering audio event, playing the corresponding voice document of audio event.
In an embodiment of the present invention, text conversion module 302 includes：
Timbre information determination sub-module, for determining the corresponding timbre information of role attribute；
Dialogue vector generates submodule, for generating to white text corresponding dialogue vector；
Voice document generates submodule, for according to timbre information, dialogue vector to be converted to voice document.
In an embodiment of the present invention, dialogue vector generation submodule includes：
Linguistics vector generation unit, for generating to white text corresponding linguistics vector；
Mood vector generation unit, for generating to white text corresponding mood vector；
Dialogue vector obtains unit, for according to linguistics vector sum mood vector, obtaining to the corresponding dialogue of white text
Vector.
In an embodiment of the present invention, mood vector generation unit includes：
Crucial mood word determination subelement, for to white text, determining key mood word；
Emotional information coupling subelement, in preset mood data library, matching the corresponding mood of crucial mood word
Information；
Mood vector obtains subelement, for generating the corresponding mood vector of emotional information.
In an embodiment of the present invention, Role Information determining module 301 includes：
Drama role's determination sub-module, for determining one or more drama roles according to drama document；
Tag identifier acquisition submodule, for obtaining the tag identifier in drama document；
Role attribute determination sub-module, for determining that the role of the corresponding drama role of tag identifier belongs to according to tag identifier
Property.
In an embodiment of the present invention, further include：
Drama template provides module, and for providing a drama template for creating drama document, drama template provides use
In the tag identifier of identified role attribute.
In an embodiment of the present invention, further include：
Audio event knock-down module, for mounting audio event to game engine.
In an embodiment of the present invention, audio event creation module 303 includes：
Audio engine calls submodule, for calling audio engine, creates the audio event for voice document；
Audio event knock-down module includes：
Incident path acquisition submodule, for obtaining the corresponding incident path of speech events；
Incident path mounts submodule, and for using incident path, audio event is articulated in game engine.
In an embodiment of the present invention, further include：
Result of broadcast logging modle, the broadcasting effect in the test process for audio event, recording voice document
Fruit；
Test log generation module, for generating the corresponding test log of result of broadcast.
In an embodiment of the present invention, role attribute includes following one or more：
Gender, age, personality.
For device embodiments, since it is basically similar to the method embodiment, so fairly simple, the correlation of description
Place illustrates referring to the part of embodiment of the method.
The present invention also provides electronic equipment, may include processor, memory and storage on a memory and can be
The computer program run on processor, the method that game speech production as above is realized when computer program is executed by processor
The step of.
The present invention also provides computer readable storage medium, computer program is stored on computer readable storage medium,
The step of method of game speech production as above is realized when computer program is executed by processor.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiment, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can be provided as method, apparatus or calculate
Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present invention be with reference to according to the method for the embodiment of the present invention, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in flow and/or box combination.These can be provided
Computer program instructions are set to all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine so that is held by the processor of computer or other programmable data processing terminal equipments
Capable instruction generates for realizing in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes
The device of specified function.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing terminal equipments
In computer-readable memory operate in a specific manner so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one flow of flow chart or multiple flows and/or one side of block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing terminal equipments so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one flow of flow chart or multiple flows
And/or in one box of block diagram or multiple boxes specify function the step of.
Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also include other elements that are not explicitly listed, or further include for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device including the element.
Above to the method and device of game speech production provided by the present invention, electronic equipment, storage medium, carry out
It is discussed in detail, principle and implementation of the present invention are described for specific case used herein, above example
Illustrate the method and its core concept for being merely used to help understand the present invention；Meanwhile for those of ordinary skill in the art, according to
According to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification
It should not be construed as limiting the invention.
Claims (13)
1. the method for speech production of playing, which is characterized in that the method includes：
The corresponding role attribute of drama role is determined according to drama document and to white text；
It is voice document by the dialogue text conversion based on the role attribute；
Audio event is created according to institute's voice file；
When triggering the audio event, the corresponding voice document of the audio event is played.
2. according to the method described in claim 1, it is characterized in that, described be based on the role attribute, by described to white text
The step of being converted to voice document include：
Determine the corresponding timbre information of the role attribute；
It generates described to white text corresponding dialogue vector；
According to the timbre information, the dialogue vector is converted into voice document.
3. according to the method described in claim 2, it is characterized in that, it is described generate it is described to white text corresponding dialogue vector
Step includes：
It generates described to white text corresponding linguistics vector；
It generates described to white text corresponding mood vector；
According to linguistics vector sum mood vector, obtain described to white text corresponding dialogue vector.
4. according to the method described in claim 3, it is characterized in that, it is described generate it is described to white text corresponding mood vector
Step includes：
From described in white text, determining key mood word；
In preset mood data library, the corresponding emotional information of the crucial mood word is matched；
Generate the corresponding mood vector of the emotional information.
5. method according to claim 1 or 2 or 3 or 4, which is characterized in that described to determine drama angle according to drama document
The corresponding role attribute of color and include to the step of white text：
One or more drama roles are determined according to drama document；
Obtain the tag identifier in the drama document；
The role attribute of the corresponding drama role of the tag identifier is determined according to the tag identifier.
6. according to the method described in claim 5, it is characterized in that, determining that drama role is corresponding according to drama document described
Role attribute and the step of to white text before, further include：
A drama template for creating drama document is provided, the drama template provides the label mark for identified role attribute
Know.
7. according to the method described in claim 1, it is characterized in that, creating audio event according to institute's voice file described
After step, further include：The audio event is mounted to game engine.
8. the method according to the description of claim 7 is characterized in that the step for creating audio event according to institute's voice file
Rapid includes calling audio engine, creates the audio event for institute's voice file；
Described mount the audio event to the step of game engine include：
Obtain the corresponding incident path of the speech events；
Using the incident path, the audio event is articulated in game engine.
9. according to the method described in claim 1, it is characterized in that, further including：
In the test process for the audio event, the result of broadcast of record institute voice file；
Generate the corresponding test log of the result of broadcast.
10. according to the method described in claim 1, it is characterized in that, the role attribute includes following one or more：
Gender, age, personality.
11. the device for speech production of playing, which is characterized in that described device includes：
Role Information determining module, for determining the corresponding role attribute of drama role according to drama document and to white text；
The dialogue text conversion is voice document for being based on the role attribute by text conversion module；
Audio event creation module, for creating audio event according to institute's voice file；
Voice document playing module, for when triggering the audio event, playing the corresponding voice document of the audio event.
12. electronic equipment, which is characterized in that including processor, memory and be stored on the memory and can be described
The computer program run on processor realizes such as claims 1 to 10 when the computer program is executed by the processor
Any one of described in game speech production method the step of.
13. computer readable storage medium, which is characterized in that computer program is stored on the computer readable storage medium,
The side of the game speech production as described in any one of claims 1 to 10 is realized when the computer program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810687837.6A CN108744521A (en) | 2018-06-28 | 2018-06-28 | The method and device of game speech production, electronic equipment, storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810687837.6A CN108744521A (en) | 2018-06-28 | 2018-06-28 | The method and device of game speech production, electronic equipment, storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108744521A true CN108744521A (en) | 2018-11-06 |
Family
ID=63974501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810687837.6A Pending CN108744521A (en) | 2018-06-28 | 2018-06-28 | The method and device of game speech production, electronic equipment, storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108744521A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584858A (en) * | 2019-01-08 | 2019-04-05 | 武汉西山艺创文化有限公司 | A kind of virtual dubbing method and its device based on AI artificial intelligence |
| CN110459200A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Phoneme synthesizing method, device, computer equipment and storage medium |
| CN110851130A (en) * | 2019-11-14 | 2020-02-28 | 成都西山居世游科技有限公司 | Data processing method and device |
| CN110865809A (en) * | 2019-11-14 | 2020-03-06 | 北京西山居互动娱乐科技有限公司 | Method and device for importing data into illusion engine |
| CN110933330A (en) * | 2019-12-09 | 2020-03-27 | 广州酷狗计算机科技有限公司 | Video dubbing method and device, computer equipment and computer-readable storage medium |
| CN111367490A (en) * | 2020-02-28 | 2020-07-03 | 广州华多网络科技有限公司 | Voice playing method and device and electronic equipment |
| CN111494950A (en) * | 2020-04-14 | 2020-08-07 | 网易（杭州）网络有限公司 | Game voice processing method and device, storage medium and electronic equipment |
| CN111696516A (en) * | 2020-05-28 | 2020-09-22 | 闫钊杰 | Multi-role intelligent sound box companion system |
| CN112631814A (en) * | 2021-01-05 | 2021-04-09 | 网易（杭州）网络有限公司 | Game plot dialogue playing method and device, storage medium and electronic equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1774715A (en) * | 2003-04-14 | 2006-05-17 | 皇家飞利浦电子股份有限公司 | System and method for performing automatic dubbing on an audio-visual stream |
| CN101359473A (en) * | 2007-07-30 | 2009-02-04 | 国际商业机器公司 | Auto speech conversion method and apparatus |
| JP4622356B2 (en) * | 2004-07-16 | 2011-02-02 | ヤマハ株式会社 | Script generator for speech synthesis and script generation program for speech synthesis |
| CN102324231A (en) * | 2011-08-29 | 2012-01-18 | 北京捷通华声语音技术有限公司 | Game dialogue voice synthesizing method and system |
| CN105975622A (en) * | 2016-05-28 | 2016-09-28 | 蔡宏铭 | Multi-role intelligent chatting method and system |
| CN107172449A (en) * | 2017-06-19 | 2017-09-15 | 微鲸科技有限公司 | Multi-medium play method, device and multimedia storage method |
| CN107396177A (en) * | 2017-08-28 | 2017-11-24 | 北京小米移动软件有限公司 | Video broadcasting method, device and storage medium |
| CN107731219A (en) * | 2017-09-06 | 2018-02-23 | 百度在线网络技术（北京）有限公司 | Phonetic synthesis processing method, device and equipment |
| CN107773982A (en) * | 2017-10-20 | 2018-03-09 | 科大讯飞股份有限公司 | Game voice interactive method and device |
-
2018
- 2018-06-28 CN CN201810687837.6A patent/CN108744521A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1774715A (en) * | 2003-04-14 | 2006-05-17 | 皇家飞利浦电子股份有限公司 | System and method for performing automatic dubbing on an audio-visual stream |
| JP4622356B2 (en) * | 2004-07-16 | 2011-02-02 | ヤマハ株式会社 | Script generator for speech synthesis and script generation program for speech synthesis |
| CN101359473A (en) * | 2007-07-30 | 2009-02-04 | 国际商业机器公司 | Auto speech conversion method and apparatus |
| CN102324231A (en) * | 2011-08-29 | 2012-01-18 | 北京捷通华声语音技术有限公司 | Game dialogue voice synthesizing method and system |
| CN105975622A (en) * | 2016-05-28 | 2016-09-28 | 蔡宏铭 | Multi-role intelligent chatting method and system |
| CN107172449A (en) * | 2017-06-19 | 2017-09-15 | 微鲸科技有限公司 | Multi-medium play method, device and multimedia storage method |
| CN107396177A (en) * | 2017-08-28 | 2017-11-24 | 北京小米移动软件有限公司 | Video broadcasting method, device and storage medium |
| CN107731219A (en) * | 2017-09-06 | 2018-02-23 | 百度在线网络技术（北京）有限公司 | Phonetic synthesis processing method, device and equipment |
| CN107773982A (en) * | 2017-10-20 | 2018-03-09 | 科大讯飞股份有限公司 | Game voice interactive method and device |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584858A (en) * | 2019-01-08 | 2019-04-05 | 武汉西山艺创文化有限公司 | A kind of virtual dubbing method and its device based on AI artificial intelligence |
| CN110459200A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Phoneme synthesizing method, device, computer equipment and storage medium |
| CN110865809B (en) * | 2019-11-14 | 2023-05-09 | 珠海金山数字网络科技有限公司 | Method and device for importing data into illusion engine |
| CN110851130A (en) * | 2019-11-14 | 2020-02-28 | 成都西山居世游科技有限公司 | Data processing method and device |
| CN110865809A (en) * | 2019-11-14 | 2020-03-06 | 北京西山居互动娱乐科技有限公司 | Method and device for importing data into illusion engine |
| CN110851130B (en) * | 2019-11-14 | 2023-09-01 | 珠海金山数字网络科技有限公司 | Data processing method and device |
| CN110933330A (en) * | 2019-12-09 | 2020-03-27 | 广州酷狗计算机科技有限公司 | Video dubbing method and device, computer equipment and computer-readable storage medium |
| CN111367490A (en) * | 2020-02-28 | 2020-07-03 | 广州华多网络科技有限公司 | Voice playing method and device and electronic equipment |
| CN111367490B (en) * | 2020-02-28 | 2024-04-09 | 广州华多网络科技有限公司 | Voice playing method and device and electronic equipment |
| CN111494950A (en) * | 2020-04-14 | 2020-08-07 | 网易（杭州）网络有限公司 | Game voice processing method and device, storage medium and electronic equipment |
| CN111494950B (en) * | 2020-04-14 | 2023-04-07 | 网易（杭州）网络有限公司 | Game voice processing method and device, storage medium and electronic equipment |
| CN111696516B (en) * | 2020-05-28 | 2023-06-20 | 闫钊杰 | Multi-role intelligent sound box partner system |
| CN111696516A (en) * | 2020-05-28 | 2020-09-22 | 闫钊杰 | Multi-role intelligent sound box companion system |
| CN112631814A (en) * | 2021-01-05 | 2021-04-09 | 网易（杭州）网络有限公司 | Game plot dialogue playing method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108744521A (en) | The method and device of game speech production, electronic equipment, storage medium | |
| CN107464555B (en) | Method, computing device and medium for enhancing audio data including speech | |
| US8712776B2 (en) | Systems and methods for selective text to speech synthesis | |
| US9330657B2 (en) | Text-to-speech for digital literature | |
| CN103345467B (en) | Speech translation system | |
| US9659572B2 (en) | Apparatus, process, and program for combining speech and audio data | |
| CN109272984A (en) | Method and apparatus for interactive voice | |
| CN104471512A (en) | Content customization | |
| CN109949783A (en) | Song synthetic method and system | |
| CN107516511A (en) | The Text To Speech learning system of intention assessment and mood | |
| CN110019962B (en) | Method and device for generating video file information | |
| CN109360550A (en) | Test method, device, equipment and the storage medium of voice interactive system | |
| US20140258858A1 (en) | Content customization | |
| CN101557483A (en) | Methods and systems for generating a media program | |
| CN106155470B (en) | A kind of audio file generation method and device | |
| US20140258462A1 (en) | Content customization | |
| JP2009210790A (en) | Music selection singer analysis and recommendation device, its method, and program | |
| CN111316350A (en) | System and method for automatically generating media | |
| CN106559469A (en) | A kind of method and apparatus that music information is pushed based on instant messaging | |
| JP6153255B2 (en) | Singing part decision system | |
| WO2023005193A1 (en) | Subtitle display method and device | |
| CN108777804A (en) | media playing method and device | |
| JP7117228B2 (en) | karaoke system, karaoke machine | |
| JP2018091998A (en) | Information processing system and information processing method | |
| Nio et al. | Conversation dialog corpora from television and movie scripts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181106 |