CN110459239A - Role analysis method, apparatus and computer readable storage medium based on voice data - Google Patents
Role analysis method, apparatus and computer readable storage medium based on voice data Download PDFInfo
- Publication number
- CN110459239A CN110459239A CN201910210501.5A CN201910210501A CN110459239A CN 110459239 A CN110459239 A CN 110459239A CN 201910210501 A CN201910210501 A CN 201910210501A CN 110459239 A CN110459239 A CN 110459239A
- Authority
- CN
- China
- Prior art keywords
- data
- role
- voice data
- angle
- analysis method
- 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0272—Voice signal separating
- G10L21/028—Voice signal separating using properties of sound source
Abstract
The role analysis method based on voice data that the invention discloses a kind of.This method comprises: obtain the voice data and with angle-data corresponding to the voice data；Role Parsing is carried out to the voice data according to the angle-data, obtains character data corresponding with the voice data.The invention also discloses a kind of role analysis device and computer readable storage medium based on voice data.The present invention, which can be realized, provides a kind of new audio role's separation method, carries out role's separation without using microphone apparatus.
Description
Technical field
The present invention relates to recording identification field more particularly to a kind of role analysis method, apparatus based on voice data and
Computer readable storage medium.
Background technique
During the modern times consultation of doctors, the case where more human hairs are sayed is frequently involved, therefore, records and sets used in conference process
If standby can identify that the i.e. corresponding speech content of different characters seems increasingly important, the effect of meeting can be greatly improved
Rate simplifies the effect of minutes.
But currently, in the related art, role's separation in the session recording system that conference process uses mostly passes through
Multiple microphone apparatus are connected, each microphone apparatus collects the audio-frequency information of a role personnel to realize, and each Mike
It is connected between wind devices and main equipment with connecting line, connection is caused greatly to user apart from limited and not portable
It is inconvenient.
Summary of the invention
The role analysis method, apparatus and computer that the main purpose of the present invention is to provide a kind of based on voice data can
Read storage medium, it is intended to realize and a kind of new audio role's separation method is provided, carry out role point without using microphone apparatus
From.
To achieve the above object, the present invention provides a kind of role analysis method based on voice data, described to be based on sound
The role analysis methods of data the following steps are included:
Obtain the voice data and with angle-data corresponding to the voice data；
Role Parsing is carried out to the voice data according to the angle-data, obtains angle corresponding with the voice data
Chromatic number evidence.
Optionally, described that Role Parsing is carried out to the voice data according to the angle-data, it obtains and the sound
Include: before the step of data corresponding character data
The voice data is converted, lteral data is obtained；
It is described that Role Parsing is carried out to the voice data according to the angle-data, it obtains corresponding with the voice data
Character data the step of replace are as follows:
Role Parsing is carried out to the lteral data according to the angle-data, obtains angle corresponding with the lteral data
Chromatic number evidence.
Optionally, described that Role Parsing is carried out to the lteral data according to the angle-data, it obtains and the text
The step of data corresponding character data includes:
The lteral data is divided according to the angle-data, obtain Ziwen digital data and with the Ziwen number of words
According to corresponding subangle data；
Role Parsing is carried out to the subangle data, is obtained and multiple role's numbers corresponding to the Ziwen digital data
According to.
Optionally, described that the lteral data is divided according to the angle-data, obtain Ziwen digital data and with
The step of Ziwen digital data corresponding subangle data includes:
The angle-data is traversed, the variation node of the angle-data is obtained；
It is divided according to the variation node pair lteral data corresponding with the angle-data, obtains Ziwen number of words
According to.
Optionally, it is described to the subangle data carry out Role Parsing, obtain with the Ziwen digital data corresponding to
The step of multiple character datas includes:
The subangle data are calculated using preset formula, are obtained and Ziwen corresponding to the subangle data
The character data of digital data.
Optionally, the formula are as follows:
Dp=360/N,
R=(d-d0+ dp-1)/dp,
Wherein, dp indicates that everyone accounts for angled numerical value；R indicates character data；What d expression was read from merging file
Angle value, value range are [0,360]；d0It is the deviation angle angle value of initialization, value range is [0,30]；N is participant
Numerical value.
Optionally, the role analysis method based on voice data is further comprising the steps of:
The lteral data and character data corresponding with the lteral data are sent to mobile terminal, so that mobile
Terminal is shown.
Optionally, the role analysis method based on voice data is further comprising the steps of:
Receive the actual name of user's input and the corresponding relationship of the actual name and the character data；
The character data is replaced with into corresponding actual name according to corresponding relationship, and by actual name and lteral data
It is associated preservation.
In addition, to achieve the above object, the present invention also provides a kind of role analysis device based on voice data, the base
Include: memory, processor in the role analysis device of voice data and is stored on the memory and can be in the processing
The role analysis program based on voice data run on device, the role analysis program based on voice data is by the processing
The step of role analysis method based on voice data as described above is realized when device executes.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
The role analysis program based on voice data is stored on storage medium, the role analysis program based on voice data is located
The step of reason device realizes the above-mentioned role analysis method based on voice data when executing.
The present invention provides a kind of role analysis method, apparatus and computer storage medium based on voice data.In the party
In method, obtain the voice data and with angle-data corresponding to the voice data；According to the angle-data to described
Voice data carries out Role Parsing, obtains character data corresponding with the voice data.By the above-mentioned means, the present invention provides
The mode of role's separation in a kind of new acoustic information can carry out angle to voice data according to the angle-data of voice data
Colour analysis, occupied angle is different when being spoken by personage in analysis voice data, analyzes sound number by angle-data
The multiple character datas for including in identify each sound number to carry out role's separation to voice data according to angle-data
According to corresponding multiple role personages.The analysis method that character is separated by angle is not required to install each role personage special
The microphone of door carries out the separation of role in audio, can comprehensive 360 degree of knowledge sound carry out role's separation.
Detailed description of the invention
Fig. 1 is the apparatus structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is that the present invention is based on the flow diagrams of the role analysis method first embodiment of voice data；
Fig. 3 is that the present invention is based on the flow diagrams of the role analysis method second embodiment of voice data；
Fig. 4 is that the present invention is based on the flow diagrams of the role analysis method 3rd embodiment of voice data；
Fig. 5 is that the present invention is based on the flow diagrams of the role analysis method fourth embodiment of voice data；
Fig. 6 is that the present invention is based on the flow diagrams of the 5th embodiment of role analysis method of voice data；
Fig. 7 is that the present invention is based on the flow diagrams of the role analysis method sixth embodiment of voice data；
Fig. 8 is that the present invention is based on the flow diagrams of the 7th embodiment of role analysis method of voice data；
Fig. 9 is that the present invention is based on the detailed process figures of the role analysis method fourth embodiment of voice data；
Figure 10 is that the present invention is based on the detailed process figures of the 7th embodiment of role analysis method of voice data.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in Figure 1, Fig. 1 is the apparatus structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
The terminal of that embodiment of the invention can be PC, and being also possible to smart phone, tablet computer, portable computer etc. has number
According to the terminal device of processing function.
As shown in Figure 1, the terminal may include: processor 1001, such as CPU, network interface 1004, user interface
1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing the connection communication between these components.
User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional user interface
1003 can also include standard wireline interface and wireless interface.Network interface 1004 optionally may include that the wired of standard connects
Mouth, wireless interface (such as WI-FI interface).Memory 1005 can be high speed RAM memory, be also possible to stable memory
(non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.
Optionally, terminal can also include camera, RF (Radio Frequency, radio frequency) circuit, sensor, audio
Circuit, Wi-Fi module etc..Wherein, sensor such as optical sensor, motion sensor and other sensors.Specifically, light
Sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can according to the light and shade of ambient light come
The brightness of display screen is adjusted, proximity sensor can close display screen and/or backlight when mobile terminal is moved in one's ear.As
One kind of motion sensor, gravity accelerometer can detect the size of (generally three axis) acceleration in all directions, quiet
Size and the direction that can detect that gravity when only, the application that can be used to identify mobile terminal posture are (such as horizontal/vertical screen switching, related
Game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；Certainly, mobile terminal can also match
The other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor are set, details are not described herein.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal structure shown in Fig. 1, can wrap
It includes than illustrating more or fewer components, perhaps combines certain components or different component layouts.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage medium
Believe module, Subscriber Interface Module SIM and the role analysis program based on voice data.
In terminal shown in Fig. 1, network interface 1004 is mainly used for connecting background server, carries out with background server
Data communication；User interface 1003 is mainly used for connecting client (user terminal), carries out data communication with client；And processor
1001 can be used for calling the role analysis program based on voice data stored in memory 1005, and execute following operation:
Obtain the voice data and with angle-data corresponding to the voice data；
Role Parsing is carried out to the voice data according to the angle-data, obtains angle corresponding with the voice data
Chromatic number evidence.
Further, processor 1001 can call the role analysis journey based on voice data stored in memory 1005
Sequence also executes following operation:
The voice data is converted, lteral data is obtained；
It is described that Role Parsing is carried out to the voice data according to the angle-data, it obtains corresponding with the voice data
Character data the step of replace are as follows:
Role Parsing is carried out to the lteral data according to the angle-data, obtains angle corresponding with the lteral data
Chromatic number evidence.
Further, processor 1001 can call the role analysis journey based on voice data stored in memory 1005
Sequence also executes following operation:
The lteral data is divided according to the angle-data, obtain Ziwen digital data and with the Ziwen number of words
According to corresponding subangle data；
Role Parsing is carried out to the subangle data, is obtained and multiple role's numbers corresponding to the Ziwen digital data
According to.
Further, processor 1001 can call the role analysis journey based on voice data stored in memory 1005
Sequence also executes following operation:
The angle-data is traversed, the variation node of the angle-data is obtained；
It is divided according to the variation node pair lteral data corresponding with the angle-data, obtains Ziwen number of words
According to.
Further, processor 1001 can call the role analysis journey based on voice data stored in memory 1005
Sequence also executes following operation:
The subangle data are calculated using preset formula, are obtained and Ziwen corresponding to the subangle data
The character data of digital data.
Further, processor 1001 can call the role analysis journey based on voice data stored in memory 1005
Sequence also executes following operation:
The formula are as follows:
Dp=360/N,
R=(d-d0+ dp-1)/dp,
Wherein, dp indicates that everyone accounts for angled numerical value；R indicates character data；What d expression was read from merging file
Angle value, value range are [0,360]；d0It is the deviation angle angle value of initialization, value range is [0,30]；N is participant
Numerical value.
Further, processor 1001 can call the role analysis journey based on voice data stored in memory 1005
Sequence also executes following operation:
The lteral data and character data corresponding with the lteral data are sent to mobile terminal, so that mobile
Terminal is shown.
Further, processor 1001 can call the role analysis journey based on voice data stored in memory 1005
Sequence also executes following operation:
Receive the actual name of user's input and the corresponding relationship of the actual name and the character data；
The character data is replaced with into corresponding actual name according to corresponding relationship, and by actual name and lteral data
It is associated preservation.
The present invention is based on the specific embodiments of the role analysis equipment of voice data and following roles based on voice data
Each embodiment of analysis method is essentially identical, and therefore not to repeat here.
Referring to Fig. 2, Fig. 2 be the present invention is based on the flow diagram of the role analysis method first embodiment of voice data,
The role analysis method based on voice data includes:
Step S100, obtain the voice data and with angle-data corresponding to the voice data；
In embodiments of the present invention, the role analysis method based on voice data is somebody's turn to do suitable for Recording Process, is also suitable
In other scenes.In Recording Process, voice data is acquired by microphone array, and microphone array includes multiple microphones, can
Think that a variety of composition forms, the microphone arrays such as 4 microphones or 4+1 microphone, 6+1 microphone can pick up
The audio-frequency information of 360 degrees omnidirection breaks single microphone because there are directive property for self-characteristic, cannot collect 360 degree of omnidirectional's sound
The problem of sound, achievees the effect that 360 degree of omnidirections collect sound, in each direction can perfect radio reception, the people of any angle
The acoustic information of member can be collected, therefore, while picking up voice data by microphone array, it is also possible to obtain the sound
Angle-data corresponding to sound data.The voice data of acquisition is saved by WAV format, and angle-data is saved by DIR format.
Step S200 carries out Role Parsing to the voice data according to the angle-data, obtains and the sound number
According to corresponding character data.
The present embodiment carries out Role Parsing to voice data by angle-data corresponding to voice data, is said using personage
Multiple characters in voice data are distinguished when words relative to the difference of the occupied angle of microphone, and then reach role
Isolated effect.The present embodiment can be adapted for Linux x86 environment, by carrying out to angle-data corresponding to voice data
It calculates, determines the angle position of voice data to determine character data corresponding to the voice data.Such as in Recording Process,
Microphone array is collected into the one section of voice data and angle-data of the sound relative to microphone of certain personage A, to the angle
Data carry out calculating parsing, determine that this section of voice data derives from some angle, and then determine the sound source in some angle
Role A speech.
The present invention is a kind of new role's separate mode, and previous sound pick-up outfit carries out role's separation, is more by installing
A microphone, the corresponding role personage of each microphone, different microphones correspond to different role, pass through voice data source
The difference of microphone determines the role of voice data.I.e. certain section of voice data comes from microphone 1, then the angle of this section of voice data
Color is 1, certain section of voice data source microphone 2, then the role of the voice data is 2.Therefore previous sound pick-up outfit is to pass through
Different microphones is installed to determine the character data of voice data, and the application, it is not required to that multiple microphones are installed, only needs one
It is a to have the function of the microphone of microphone array, it can determine angle using the different angle that a microphone collects voice data
Color, it is different from role's separate mode of previous sound pick-up outfit, it is a kind of new role's separate mode.
The present invention provides a kind of role analysis method, apparatus and computer storage medium based on voice data.In the party
In method, obtain the voice data and with angle-data corresponding to the voice data；According to the angle-data to described
Voice data carries out Role Parsing, obtains character data corresponding with the voice data.By the above-mentioned means, the present invention provides
The mode of role's separation in a kind of new acoustic information can carry out angle to voice data according to the angle-data of voice data
Colour analysis, occupied angle is different when being spoken by personage in analysis voice data, analyzes sound number by angle-data
The multiple character datas for including in identify each sound number to carry out role's separation to voice data according to angle-data
According to corresponding multiple role personages.The analysis method that character is separated by angle is not required to install each role personage special
The microphone of door carries out the separation of role in audio, can comprehensive 360 degree of knowledge sound carry out role's separation.
Referring to Fig. 3, Fig. 3 is that the present invention is based on the signals of the process of the role analysis method second embodiment of voice data
Figure.
Based on the above embodiment, the present embodiment further include:
The voice data is converted, obtains lteral data by step S010；
In the present embodiment, voice data can be subjected to real-time voice conversion, be converted to lteral data.The lteral data can
To be saved by JSON format.The lteral data in addition to voice data by voice it is converted come text information other than, may be used also
With comprising other related informations, such as record sound receiving time data.These information are saved, after can be convenient
It is continuous to be handled.
Step S210 carries out Role Parsing to the lteral data according to the angle-data, obtains and the text number
According to corresponding character data.
Voice data is converted, after obtaining lteral data, progress can be carried out lteral data according to angle-data
Role Parsing calculates angle corresponding to certain section of lteral data, determines the role to speak corresponding to the angle, and then really
The character data of fixed this section of lteral data.The present embodiment is can achieve in this way through difference corresponding to lteral data
Angle determine the corresponding each role personage to speak of each section of lteral data, and then obtain respectively corresponding with each role
Speech content text information, can also include other information, such as the temporal information of speaking of this section of words in text information.Such as
The corresponding angle of certain section of text data is a, and correspondence is described in role 1, and the corresponding angle of certain section of text data is b, and correspondence is angle
Described in color 2.
Referring to Fig. 4, Fig. 4 is that the present invention is based on the signals of the process of the role analysis method 3rd embodiment of voice data
Figure.
Based on the above embodiment, in the present embodiment, step S210 includes:
Step S220 divides the lteral data according to the angle-data, obtain Ziwen digital data and with institute
State the corresponding subangle data of Ziwen digital data；
Specifically, lteral data can be divided according to angle-data in the present embodiment, lteral data is divided into
Multiple Ziwen digital datas, each Ziwen digital data correspond to a sub- angle-data, and a sub- lteral data corresponds to a son
Angle-data.Lteral data is divided according to the variation of the corresponding angle of lteral data, lteral data can be divided
For multiple Ziwen digital datas, the corresponding angle of each Ziwen digital data.
Step S230 is more corresponding to acquisition and the Ziwen digital data to subangle data progress Role Parsing
A character data.
Each Ziwen digital data corresponding one and only one subangle data, calculate according to the angle, are somebody's turn to do
Speak character, and then the role to speak corresponding to the determining Ziwen digital data corresponding to angle, and then can determine
The corresponding each role of various pieces in passage information, and then reach and role's separation is carried out to this section of text information
Effect.In certain section of text information, a word is what role 1 said, second and third word is the described in role 2 the 4th to the 9th
Word is described in role 3 etc..
Referring to Fig. 5, Fig. 5 is that the present invention is based on the signals of the process of the role analysis method fourth embodiment of voice data
Figure.
Based on the above embodiment, in the present embodiment, step S220 includes:
Step S221 traverses the angle-data, obtains the variation node of the angle-data；
The present embodiment be the lteral data is divided according to the angle-data, obtain Ziwen digital data and with institute
State a kind of embodiment of implementation of the corresponding subangle data of Ziwen digital data.The present embodiment can pass through computer
Computational algorithm traverses angle-data, obtains the variation node of angle-data.Such as on those nodes, angle-data hair
The angle of changing, the acoustic information collected converts, and has some angle to become another angle, and angle change institute is right
The variation node answered.
Step S222 is divided according to the variation node pair lteral data corresponding with the angle-data, is obtained
Ziwen digital data.
According to the variation node, to the angle-data, accordingly corresponding lteral data is divided, and lteral data is divided into
Multiple Ziwen digital datas, the corresponding angle of each Ziwen digital data.The corresponding angle of each Ziwen digital data can be identical,
It can be different.And then can according to corresponding to the Ziwen digital data unique angle calculate and determine the Ziwen digital data
Role, and then play the effect of role's separation.Detailed process can be found in Fig. 9.
Referring to Fig. 6, Fig. 6 is that the present invention is based on the signals of the process of the 5th embodiment of role analysis method of voice data
Figure.
Based on the above embodiment, in the present embodiment, step S230 includes:
Step S231 calculates the subangle data using preset formula, obtains and the subangle data institute
The character data of corresponding Ziwen digital data.
In the present embodiment, subangle data corresponding to sub- lteral data are calculated, determines the Ziwen digital data
Corresponding role can be calculate by the following formula:
Dp=360/N,
R=(d-d0+ dp-1)/dp,
Wherein, dp indicates that everyone accounts for angled numerical value；R indicates character data；What d expression was read from merging file
Angle value, value range are [0,360]；d0It is the deviation angle angle value of initialization, value range is [0,30]；N is participant
Numerical value.
This formula can isolate specific role, above-mentioned two formula according to preset number of participants N and start angle
All round up, if that is, fractional part be greater than 0, add 1 in integer part, as long as and integer part value.For example, default
d0It is 6, number of participants N is 4, then when the subangle data for obtaining certain cross-talk lteral data are 126 degree, is calculated from the formula
Dp is 90, and then when calculated role R=(126-6+89)/90=2, i.e. group angle-data are 126 degree, it is determined that corresponding
Character data be 2.Angle is calculated using above-mentioned formula, angle is divided, is divided into multiple angular regions, often
The corresponding character of a angular regions, and then the angular regions at place can be determined according to angle, and then determine the angle
Corresponding character.
Referring to Fig. 7, Fig. 7 is that the present invention is based on the signals of the process of the role analysis method sixth embodiment of voice data
Figure.
Based on the above embodiment, the present embodiment further includes following steps:
The lteral data and character data corresponding with the lteral data are sent to mobile terminal by step S300,
So that mobile terminal is shown.
In the present embodiment, lteral data and character data are sent to mobile terminal, so that mobile terminal is by text
Data and character data are shown, finally show the effect of role's separation and text conversion on mobile terminals.The movement
Terminal can be the mobile device of support iOS and Android, and mobile terminal, will after getting lteral data and character data
Text conversion result and role's separating resulting are shown on the interface of mobile terminal.The content of display may include: voice conversion
Rear word content, relative time, role's title, the role's head portrait spoken etc..These files can also be saved, so as to
Subsequent to be operated, such as subsequent recording playback positions word content, basis by progress playback, according to recording playback progress
Word content locating recordings progress, again transcription recording file etc. operate.By mode as synchronous mobile terminal, can incite somebody to action
Role's separating effect visualizes intuitiveization, and the effect of role's separation is intuitively seen convenient for user.
Referring to Fig. 8, Fig. 8 is that the present invention is based on the signals of the process of the 7th embodiment of role analysis method of voice data
Figure.
Based on the above embodiment, the present embodiment further includes following steps:
Step S400 receives actual name and the actual name pass corresponding with the character data of user's input
System；
It in the present embodiment, can be by role's number after obtaining character data corresponding to lteral data and lteral data
According to being modified, it is corrected as the real name or the pet name of practical Role Users, the effect for separating role is more intuitive.Such as obtaining
Under the premise of knowing that the corresponding role personage to speak of certain words is 1, the actual name for receiving user's input such as spends flower, and flower this
Character data corresponding to actual name is the information such as 1.
The character data is replaced with corresponding actual name according to corresponding relationship by step S500, and by actual name
Preservation is associated with lteral data.
Flower is such as spent in the actual name for receiving user's input, and character data corresponding to flower this actual name is
After the information such as 1, the actual name that character data 1 replaces with user's input is spent into flower, to obtain the corresponding angle spoken of certain words
Color personage is to spend flower, to reach the word content spoken and the one-to-one result of Real Name.Setting is edited by user
Specific name, the title and above-mentioned character data R are associated preservation, to reach the effect for being modified to actual name
Fruit.At the same time it can also according to original preset Icon Color or head portrait, by Icon Color and head portrait and character data R into
Row association saves, and keeps the relevant information of the corresponding role personage to speak of text information more comprehensively intuitive.Detailed process is referring to figure
10。
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium.
The role analysis program based on voice data is stored on computer readable storage medium of the present invention, it is described to be based on sound
Role analysis method based on voice data as described above is realized when the role analysis program of sound data is executed by processor
Step.
Wherein, the role analysis program based on voice data run on the processor is performed realized side
Method can refer to each embodiment of role analysis method the present invention is based on voice data, and details are not described herein again.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of role analysis method based on voice data, which is characterized in that the role analysis side based on voice data
Method the following steps are included:
Obtain the voice data and with angle-data corresponding to the voice data；
Role Parsing is carried out to the voice data according to the angle-data, obtains role's number corresponding with the voice data
According to.
2. the role analysis method based on voice data as described in claim 1, which is characterized in that described according to the angle
It is wrapped before the step of data carry out Role Parsing to the voice data, obtain character data corresponding with the voice data
It includes:
The voice data is converted, lteral data is obtained；
It is described that Role Parsing is carried out to the voice data according to the angle-data, obtain angle corresponding with the voice data
Chromatic number according to the step of replace are as follows:
Role Parsing is carried out to the lteral data according to the angle-data, obtains role's number corresponding with the lteral data
According to.
3. the role analysis method based on voice data as claimed in claim 2, which is characterized in that described according to the angle
Data to the lteral data carry out Role Parsing, obtain character data corresponding with the lteral data the step of include:
The lteral data is divided according to the angle-data, obtain Ziwen digital data and is divided with the Ziwen digital data
Not corresponding subangle data；
Role Parsing is carried out to the subangle data, is obtained and multiple character datas corresponding to the Ziwen digital data.
4. the role analysis method based on voice data as claimed in claim 3, which is characterized in that described to the text number
It is divided according to according to the angle-data, obtains Ziwen digital data and subangle number corresponding with the Ziwen digital data
According to the step of include:
The angle-data is traversed, the variation node of the angle-data is obtained；
It is divided according to the variation node pair lteral data corresponding with the angle-data, obtains Ziwen digital data.
5. the role analysis method based on voice data as claimed in claim 3, which is characterized in that described to the subangle
Data carry out Role Parsing, and acquisition includes: with the step of multiple character datas corresponding to the Ziwen digital data
The subangle data are calculated using preset formula, are obtained and Ziwen number of words corresponding to the subangle data
According to character data.
6. the role analysis method based on voice data as claimed in claim 5, which is characterized in that the formula are as follows:
Dp=360/N,
R=(d-d0+ dp-1)/dp,
Wherein, dp indicates that everyone accounts for angled numerical value；R indicates character data；D indicates the angle read from merging file
Value, value range are [0,360]；d0It is the deviation angle angle value of initialization, value range is [0,30]；N is participant numerical value.
7. the role analysis method based on voice data as claimed in claim 2, which is characterized in that described to be based on voice data
Role analysis method it is further comprising the steps of:
The lteral data and character data corresponding with the lteral data are sent to mobile terminal, so that mobile terminal
It is shown.
8. the role analysis method based on voice data as claimed in claim 2, which is characterized in that described to be based on voice data
Role analysis method it is further comprising the steps of:
Receive the actual name of user's input and the corresponding relationship of the actual name and the character data；
The character data is replaced with into corresponding actual name according to corresponding relationship, and actual name and lteral data are carried out
Association saves.
9. a kind of role analysis device based on voice data, which is characterized in that the role analysis dress based on voice data
Set include: memory, processor and be stored on the memory and can run on the processor based on voice data
Role analysis program, realize when the role analysis program based on voice data is executed by the processor such as claim
The step of role analysis method described in any one of 1 to 8 based on voice data.
10. a kind of computer readable storage medium, which is characterized in that be stored on the computer readable storage medium based on sound
The role analysis program of sound data is realized when the role analysis program based on voice data is executed by processor as right is wanted
The step of role analysis method described in asking any one of 1 to 8 based on voice data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910210501.5A CN110459239A (en) | 2019-03-19 | 2019-03-19 | Role analysis method, apparatus and computer readable storage medium based on voice data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910210501.5A CN110459239A (en) | 2019-03-19 | 2019-03-19 | Role analysis method, apparatus and computer readable storage medium based on voice data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110459239A true CN110459239A (en) | 2019-11-15 |
Family
ID=68480584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910210501.5A Pending CN110459239A (en) | 2019-03-19 | 2019-03-19 | Role analysis method, apparatus and computer readable storage medium based on voice data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110459239A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112908336A (en) * | 2021-01-29 | 2021-06-04 | 深圳壹秘科技有限公司 | Role separation method for voice processing device and voice processing device thereof |
| CN113012700A (en) * | 2021-01-29 | 2021-06-22 | 深圳壹秘科技有限公司 | Voice signal processing method, device, system and computer readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102968991A (en) * | 2012-11-29 | 2013-03-13 | 华为技术有限公司 | Method, device and system for sorting voice conference minutes |
| US20130222230A1 (en) * | 2012-02-29 | 2013-08-29 | Pantech Co., Ltd. | Mobile device and method for recognizing external input |
| US20130230179A1 (en) * | 2012-03-04 | 2013-09-05 | John Beaty | System and method for mapping and displaying audio source locations |
| CN105070304A (en) * | 2015-08-11 | 2015-11-18 | 小米科技有限责任公司 | Method, device and electronic equipment for realizing recording of object audio |
| CN105389099A (en) * | 2014-08-29 | 2016-03-09 | 三星电子株式会社 | method and apparatus for voice recording and playback |
| CN106356067A (en) * | 2016-08-25 | 2017-01-25 | 乐视控股（北京）有限公司 | Recording method, device and terminal |
| CN106448722A (en) * | 2016-09-14 | 2017-02-22 | 科大讯飞股份有限公司 | Sound recording method, device and system |
| CN108520756A (en) * | 2018-03-20 | 2018-09-11 | 北京时代拓灵科技有限公司 | A kind of method and device of speaker's speech Separation |
| CN108564952A (en) * | 2018-03-12 | 2018-09-21 | 新华智云科技有限公司 | The method and apparatus of speech roles separation |
| CN108630223A (en) * | 2017-03-21 | 2018-10-09 | 株式会社东芝 | Signal processing apparatus and signal processing method |
| CN108735227A (en) * | 2018-06-22 | 2018-11-02 | 北京三听科技有限公司 | A kind of voice signal for being picked up to microphone array carries out the method and system of Sound seperation |
-
2019
- 2019-03-19 CN CN201910210501.5A patent/CN110459239A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130222230A1 (en) * | 2012-02-29 | 2013-08-29 | Pantech Co., Ltd. | Mobile device and method for recognizing external input |
| US20130230179A1 (en) * | 2012-03-04 | 2013-09-05 | John Beaty | System and method for mapping and displaying audio source locations |
| CN102968991A (en) * | 2012-11-29 | 2013-03-13 | 华为技术有限公司 | Method, device and system for sorting voice conference minutes |
| CN105389099A (en) * | 2014-08-29 | 2016-03-09 | 三星电子株式会社 | method and apparatus for voice recording and playback |
| CN105070304A (en) * | 2015-08-11 | 2015-11-18 | 小米科技有限责任公司 | Method, device and electronic equipment for realizing recording of object audio |
| CN106356067A (en) * | 2016-08-25 | 2017-01-25 | 乐视控股（北京）有限公司 | Recording method, device and terminal |
| CN106448722A (en) * | 2016-09-14 | 2017-02-22 | 科大讯飞股份有限公司 | Sound recording method, device and system |
| CN108630223A (en) * | 2017-03-21 | 2018-10-09 | 株式会社东芝 | Signal processing apparatus and signal processing method |
| CN108564952A (en) * | 2018-03-12 | 2018-09-21 | 新华智云科技有限公司 | The method and apparatus of speech roles separation |
| CN108520756A (en) * | 2018-03-20 | 2018-09-11 | 北京时代拓灵科技有限公司 | A kind of method and device of speaker's speech Separation |
| CN108735227A (en) * | 2018-06-22 | 2018-11-02 | 北京三听科技有限公司 | A kind of voice signal for being picked up to microphone array carries out the method and system of Sound seperation |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112908336A (en) * | 2021-01-29 | 2021-06-04 | 深圳壹秘科技有限公司 | Role separation method for voice processing device and voice processing device thereof |
| CN113012700A (en) * | 2021-01-29 | 2021-06-22 | 深圳壹秘科技有限公司 | Voice signal processing method, device, system and computer readable storage medium |
| CN113012700B (en) * | 2021-01-29 | 2023-12-26 | 深圳壹秘科技有限公司 | Voice signal processing method, device and system and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11527243B1 (en) | Signal processing based on audio context | |
| CN109819313B (en) | Video processing method, device and storage medium | |
| US20210280172A1 (en) | Voice Response Method and Device, and Smart Device | |
| US8847884B2 (en) | Electronic device and method for offering services according to user facial expressions | |
| EP2821992B1 (en) | Method for updating voiceprint feature model and terminal | |
| JP6541934B2 (en) | Mobile terminal having voice interaction function and voice interaction method therefor | |
| JP2021516786A (en) | Methods, devices, and computer programs to separate the voices of multiple people | |
| CN104991754B (en) | The way of recording and device | |
| CN105556955B (en) | Video conversation apparatus and video calling processing method | |
| CN107256139A (en) | Method of adjustment, terminal and the computer-readable recording medium of audio volume | |
| KR20160026317A (en) | Method and apparatus for voice recording | |
| CN106790940B (en) | Recording method, recording playing method, device and terminal | |
| CN109257498B (en) | Sound processing method and mobile terminal | |
| KR20220148915A (en) | Audio processing methods, apparatus, readable media and electronic devices | |
| CN109887505A (en) | Method and apparatus for wake-up device | |
| CN108174236A (en) | A kind of media file processing method, server and mobile terminal | |
| US20210029304A1 (en) | Methods for generating video, electronic device and storage medium | |
| CN113033245A (en) | Function adjusting method and device, storage medium and electronic equipment | |
| CN110198375A (en) | The way of recording, terminal and computer readable storage medium | |
| CN108073572A (en) | Information processing method and its device, simultaneous interpretation system | |
| CN106128440A (en) | A kind of lyrics display processing method, device, terminal unit and system | |
| CN110459239A (en) | Role analysis method, apparatus and computer readable storage medium based on voice data | |
| CN109949793A (en) | Method and apparatus for output information | |
| CN106471493A (en) | Method and apparatus for managing data | |
| JP2008113331A (en) | Telephone system, telephone set, server device, and program |
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: 20191115 |