CN108111799A - The identification method and device of spokesman in video conference - Google Patents
The identification method and device of spokesman in video conference Download PDFInfo
- Publication number
- CN108111799A CN108111799A CN201711339270.5A CN201711339270A CN108111799A CN 108111799 A CN108111799 A CN 108111799A CN 201711339270 A CN201711339270 A CN 201711339270A CN 108111799 A CN108111799 A CN 108111799A
- Authority
- CN
- China
- Prior art keywords
- meeting
- brightness
- color
- place
- spokesman
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/15—Conference systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/57—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for processing of video signals
Abstract
The invention discloses the identification method and device of spokesman in a kind of video conference, wherein, method includes：Obtain the audio volume in meeting-place of respectively attending a meeting；Meeting-place picture according to where audio volume determines spokesman；The pre-set color of original intensity is identified into the meeting-place picture frame of spokesman, wherein, meeting-place of each attending a meeting corresponds to a meeting-place picture；The brightness of the pre-set color identified according to default gradual change rule control gradually increases, to reach color of object brightness.Pass through the border color to the meeting-place picture where spokesman, the adjustment of its colour brightness is carried out according to default gradual change rule, since the adjustment of colour brightness is gradual change type, and when there is abnormal noise, the time is generally all shorter, by the brightness adjustment of gradual change type, at the end of ensureing abnormal noise, the brightness of the border color of meeting-place picture is not high, will not cause participant's note that so that the mark accuracy of spokesman is higher in video conference.
Description
Technical field
The present invention relates to video conferencing technology fields, and in particular to the identification method and dress of spokesman in a kind of video conference
It puts.
Background technology
Increasingly mature with computer network, conveniently information communication and cooperation mode become network technology and grind
The hot spot studied carefully and developed.Video conferencing system breaches the limitation of region as a kind of new communication and media of communication, can be with
The transmission and service of more convenient flexibly comprehensive audio-video signal are provided, are widely used.
In current large-scale video conference, generally there are many participant sides to participate in discussion, need to open picture simultaneously at this time
Face synthesizes and audio mixing so that each participant side can see other with meeting side but also hear other speech contents with meeting side.That is, exist
It needs when video conference is held by multiple participant terminal accessing conference platforms and these terminals can send audio/video coding to platform
The audio/video coding data received are decoded by data, platform, audio mixing, and the terminal for being sent to participant is re-encoded after synthesis.
Wherein, so-called picture synthesis shows the small picture of all participant sides in same video pictures.Therefore, when certain
During a or some participant side's speeches, other participant sides need just navigate to current speaker's by browsing multiple small pictures
Then small picture can just see its expression, body language clearly；When spokesman changes, participant side needs to find again, positions hair again
Say people.Such case frequently occurs in multi-party discussion, exchange, and big inconvenience is brought to the use of participant side.
Chinese patent CN101080000A discloses a kind of method of displaying speaker in video conference, specifically discloses
In video conference, the volume energy according to spokesman determines current speaker according to pre-defined rule, highlights described current
The video pictures of spokesman.It, which is highlighted, predominantly only shows that the video of current speaker is met；To be more than other spokesman
Video pictures ratio show current speaker video pictures；The video pictures of current speaker are shown with special marking,
Its special marking includes the video pictures using frame mark current speaker.However problem present in the program is, when
Due to occurring unexpected abnormal voice (such as cup is reset to desktop, foreign matter decline ground, the sound that collides with etc.) in the meeting-place of participant
When, since its volume is larger, the spokesman that can cause script marks moment to convert into the picture in the exception meeting-place, and these meetings
There is no spokesman in, the accuracy that spokesman marks is influenced.
The content of the invention
In view of this, an embodiment of the present invention provides the identification method and device of spokesman in a kind of video conference, with solution
The problem of accuracy that spokesman is caused to mark is low easily certainly is influenced be subject to abnormal voice on the mark of spokesman in the prior art.
First aspect present invention provides the identification method of spokesman in video conference a kind of, comprises the following steps：
Obtain the audio volume in meeting-place of respectively attending a meeting；
Meeting-place picture according to where the audio volume determines spokesman；
The pre-set color of original intensity is identified into the meeting-place picture frame of the spokesman, wherein, each attend a meeting
Meeting-place corresponds to a meeting-place picture；
The brightness of the pre-set color identified according to default gradual change rule control gradually increases, to reach color of object
Brightness, wherein, the default gradual change rule regulation has the rate of border color gradual change and the color of object brightness.
Optionally, the brightness of the pre-set color identified according to default gradual change rule control gradually increases, to reach
Color of object brightness includes：
Judge whether the brightness of the pre-set color reaches the color of object brightness；
When the not up to color of object brightness, judge that the last meeting-place picture border color brightness identified changes
Time and current time difference whether reach prefixed time interval；
When reaching the prefixed time interval, described in the meeting-place picture border color brightness increase that is identified described in control
The brightness of pre-set color.
Optionally, the meeting-place picture according to where the audio volume determines spokesman, comprises the following steps：
Obtain the voice messaging in each meeting-place of attending a meeting；
According to the voice messaging, inquiring about in all meeting-place of attending a meeting has the meeting-place of attending a meeting of efficient voice information；
The audio volume in the extraction meeting-place of attending a meeting with efficient voice information；
From all meeting-place of attending a meeting with efficient voice information, the N number of described of audio volume maximum is filtered out
It attends a meeting meeting-place；
Determine meeting-place picture of the meeting-place picture in N number of meeting-place of attending a meeting where the spokesman.
Optionally, the brightness degree of the color of object brightness is divided into what is be sequentially increased as defined in the default gradual change rule
N number of brightness degree, N number of brightness degree and the audio volume of N number of maximum are correspondingly arranged, wherein, the bigger correspondence of audio volume
Color of object brightness it is higher.
Optionally, after the brightness of the pre-set color identified according to default gradual change rule control gradually increases, also
Including：
Determine the color of object brightness of the meeting-place picture frame in each meeting-place of attending a meeting；
Obtain the current border color brightness of the meeting-place picture in each meeting-place of attending a meeting；
Judge whether current border color brightness reaches the color of object brightness determined；
When the current border color brightness is not reaching to the pre-set color brightness, last meeting-place picture is judged
Whether the time and the difference of current time that border color brightness changes reach prefixed time interval；
When reaching the prefixed time interval, the meeting-place picture frame in each meeting-place of attending a meeting is controlled according to working as front bezel
Colour brightness is to corresponding color of object brightness adjustment.
Optionally, the meeting-place picture frame according to current border color brightness to corresponding color of object brightness adjustment,
Comprise the following steps：
When the current border color brightness is more than the corresponding color of object brightness, lower described when front bezel face
The brightness degree of colour brightness；
When the current border color brightness is less than the corresponding color of object brightness, up-regulation is described to work as front bezel face
The brightness degree of colour brightness.
Second aspect of the present invention provides the identity device of spokesman in video conference a kind of, including：
Acquiring unit, for obtaining the audio volume in meeting-place of respectively attending a meeting；
Determination unit, for the meeting-place picture where determining spokesman according to the audio volume；
Unit is identified, the pre-set color of original intensity is identified into for the meeting-place picture frame to the spokesman,
Wherein, each attend a meeting meeting-place correspond to a meeting-place picture；
Brightness control unit, the brightness of the pre-set color for being identified according to default gradual change rule control gradually increase
Add, to reach color of object brightness, wherein, the default gradual change rule regulation has the rate of border color gradual change and the target
Colour brightness.
Optionally, brightness control unit, including：
First judgment sub-unit, for judging whether the brightness of the pre-set color reaches the color of object brightness；
Second judgment sub-unit, for when the not up to color of object brightness, judging the last meeting-place identified
Whether the time and the difference of current time that the brightness of picture border color changes reach prefixed time interval；
Brightness increases subelement, for the meeting-place picture when reaching the prefixed time interval, identified described in control
Border color brightness increases the brightness of the pre-set color.
Third aspect present invention provides a kind of media platform, including at least one processor；And with it is described at least one
The memory of processor communication connection；Wherein, the memory storage has the instruction that can be performed by one processor, described
Instruction is performed by least one processor, so that at least one processor performs first aspect present invention or first party
The identification method of spokesman in video conference any one of face.
A kind of non-transient computer readable storage medium storing program for executing of fourth aspect present invention, the non-transient computer readable storage medium
Matter stores computer instruction, and the computer instruction is any in first aspect present invention or first aspect for performing computer
The identification method of spokesman in video conference described in.
Technical solution provided by the invention, has the following advantages that：
1. the identification method of spokesman in video conference provided in an embodiment of the present invention, by the meeting-place where spokesman
The border color of picture carries out the adjustment of its colour brightness according to default gradual change rule, since the adjustment of colour brightness is gradual change
Formula, and when there is abnormal noise, the time is generally all shorter, by the brightness adjustment of gradual change type, so as to ensure in meeting-place
Abnormal noise is over when the brightness of the border color of picture is not high, is terminated the frame mark to meeting-place picture, will not be caused
Participant's note that so that the mark accuracy of spokesman is higher in video conference.
2. the identification method of spokesman in video conference provided in an embodiment of the present invention passes through on the side of adjustment meeting picture
Before frame colour brightness, judge whether brightness adjustment interval reaches prefixed time interval, avoid the frequent adjustment of brightness, influence to regard
The effect of frequency meeting.
3. the identification method of spokesman in video conference provided in an embodiment of the present invention, by by voice messaging and audio sound
Amount combines, and determines the spokesman of video conference, can improve the accuracy that spokesman determines, promotes the effect of video conference.
4. the identification method of spokesman in video conference provided in an embodiment of the present invention, by by the bright of color of object brightness
The size of degree grade and audio volume is correspondingly arranged, i.e. the higher spokesman of audio volume, corresponding meeting picture frame
Brightness is higher so that respectively the side of attending a meeting can be easily positioned main presenter.
5. the identification method of spokesman in video conference provided in an embodiment of the present invention, passes through and compares meeting picture in real time
The currently relation between border color brightness and color of object brightness so that the conference system can adjust the side of spokesman in time
Frame colour brightness promotes the effect of video conference.
Description of the drawings
The features and advantages of the present invention can be more clearly understood by reference to attached drawing, attached drawing is schematically without that should manage
It solves to carry out any restrictions to the present invention, in the accompanying drawings：
Fig. 1 shows a side specifically illustrated of the identification method of spokesman in video conference in the embodiment of the present invention 1
Method flow chart；
Fig. 2 shows a side specifically illustrated of the identification method of spokesman in video conference in the embodiment of the present invention 2
Method flow chart；
Fig. 3 shows a side specifically illustrated of the identification method of spokesman in video conference in the embodiment of the present invention 3
Method flow chart；
Fig. 4 shows a knot specifically illustrated of the identity device of spokesman in video conference in the embodiment of the present invention 5
Composition；
Fig. 5 shows a structure chart specifically illustrated of media platform in the embodiment of the present invention 6.
Specific embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical solution in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art are not having
All other embodiments obtained under the premise of creative work are made, belong to the scope of protection of the invention.
Those skilled in the art it is to be appreciated that conference system described in the embodiment of the present invention include media platform and
Several conference terminals.When video conference is held, each conference terminal needs to access media platform, and then these terminals can be to matchmaker
Body platform sends audio/video coding data；Media platform is decoded after audio/video coding data are received, audio mixing, and picture closes
Each conference terminal is sent into re-encoding afterwards；Wherein, each conference terminal corresponds to a meeting-place picture, and media platform will
The corresponding meeting-place picture of all conference terminals is synthesized, and where spokesman is highlighted during video conference carries out
Meeting-place of attending a meeting picture.
Embodiment 1
The embodiment of the present invention provides the identification method of spokesman in video conference a kind of, available for spokesman in video conference
Identity device in, as shown in Figure 1, this method comprises the following steps：
Step S11 obtains the audio volume in meeting-place of respectively attending a meeting.
The identity device of spokesman obtains the audio volume in all meeting-place of attending a meeting in video conference, that is, gets all attend a meeting
The various sound that meeting-place is sent, the sound including spokesman, the noise in meeting-place or other interference sounds.
Step S12, the meeting-place picture according to where audio volume determines spokesman.
The meeting that the identity device of spokesman can be according to where the size of audio volume determines spokesman in video conference
Field picture can also combine according to audio volume and other characteristics (for example, voice messaging) in meeting-place of attending a meeting, determine spokesman institute
Meeting-place picture.
Step S13 is identified into the pre-set color of original intensity to the meeting-place picture frame of spokesman, wherein, each
Attend a meeting meeting-place correspond to a meeting-place picture.
The identity device of spokesman is when the meeting-place picture frame to all meeting-place of attending a meeting initializes in video conference,
Meeting-place picture frame where the spokesman that will be determined in step S12 identifies the pre-set color into original intensity.Wherein, it is different
The brightness degree of the original intensity of the meeting-place picture frame of spokesman is not high, can for human eye not it will be noted that brightness etc.
Grade；The pre-set color of the meeting-place picture frame of different spokesman may be the same or different.
I.e. when initialization is (from non-speaking people to spokesman), the meeting-place picture border color where spokesman is identified into bright
The not high pre-set color of degree.
Step S14, the brightness of the pre-set color identified according to default gradual change rule control gradually increases, to reach target
Colour brightness, wherein, default gradual change rule regulation has the rate of border color gradual change and the color of object brightness.
Wherein, default gradual change rule is provided in the identity device of spokesman in video conference, is defined in the rule
The rate of border color gradual change and color of object brightness.
After the meeting-place picture where determining spokesman, the brightness of corresponding border color according to setting it is default gradually
Become rule so that brightness gradually increases, until reaching color of object brightness.
It,, will be right after determining the meeting-place picture where spokesman for the first time when video conference is initial in the present embodiment
The border color brightness for the meeting-place picture answered is arranged to the pre-set color of original intensity；Then, gradually increased according to preset rules
Brightness is until predetermined luminance is reached.Wherein, by setting gradual change regular, realize in the case where there is abnormal noise, mark
It is not high to know the colour brightness of the meeting-place frame, human eye is not it will be noted that it changes；The duration of general abnormal noise is not grown,
At the end of abnormal noise, the colour brightness of represented meeting-place frame is not high and terminates brightness increase, is no longer identified, should
The change procedure of colour brightness be not enough to cause participant's note that and then for participant, spokesman in video conference
Mark accuracy it is higher.
Embodiment 2
The embodiment of the present invention provides the identification method of spokesman in video conference a kind of, available for spokesman in video conference
Identity device in, as shown in Fig. 2, this method comprises the following steps：
Step S21 obtains the audio volume in meeting-place of respectively attending a meeting.
Identical with 1 step S11 of embodiment, details are not described herein.
Step S22, the meeting-place picture according to where audio volume determines spokesman.
The identity device of spokesman determines to set out using audio volume and the voice messaging in meeting-place of attending a meeting in conference system
Say the meeting-place picture where people.Specifically include following steps：
Step S221 obtains the voice messaging in meeting-place of respectively attending a meeting.
The identity device of spokesman can be the audio-frequency information by obtaining meeting-place of respectively attending a meeting in conference system, pass through voice
What identification was got；Can also directly extract the voice messaging in meeting-place of respectively attending a meeting.
Step S222, according to voice messaging, inquiring about in all meeting-place of attending a meeting has the meeting-place of attending a meeting of efficient voice information.
Voice messaging of the identity device of spokesman to all meeting-place of attending a meeting got in conference system carries out voice Zhen
Not, recognise that with efficient voice.Wherein, so-called efficient voice is to include specific word content in voice messaging,
Specifically, the voice of people rather than the voice caused by abnormal noise.I.e. identity device can be from all meeting-place of attending a meeting
Inquire the meeting-place of attending a meeting with effective language information.
Step S223, the audio volume in attend a meeting meeting-place of the extraction with efficient voice information.
The identity device of spokesman is after the meeting-place of attending a meeting of efficient voice is inquired in conference system, from step S21
The audio volume in the meeting-place of attending a meeting with efficient voice information is extracted in the audio volume in all meeting-place of attending a meeting obtained.
Step S224 from all meeting-place of attending a meeting with efficient voice information, filters out the N number of of audio volume maximum
It attends a meeting meeting-place.
The identity device of spokesman can be to the audio in all meeting-place of attending a meeting with efficient voice information in conference system
Volume is ranked up, and filters out N number of meeting-place of attending a meeting of audio volume maximum.
Step S225 determines meeting-place picture of the meeting-place picture in N number of meeting-place of attending a meeting where spokesman.
The identity device of spokesman determines N number of the attending a meeting with efficient voice information and audio volume maximum in conference system
Meeting-place is the meeting-place where spokesman, and corresponding meeting-place picture is the meeting-place picture where spokesman.
As a kind of optional embodiment of the present embodiment, N is 1 to 4, i.e., from the meeting-place picture in all meeting-place of attending a meeting,
1 to 4 meeting-place picture with efficient voice information and audio volume maximum is selected, this 1 to 4 meeting-place picture is spokesman
The meeting-place picture at place.On the one hand the value range of N can ensure to highlight the meeting-place picture where spokesman, the opposing party
It face being capable of the excessive caused entire picture synthesis very confusion of N values.
Step S23 is identified into the pre-set color of original intensity to the meeting-place picture frame of spokesman, wherein, each
Attend a meeting meeting-place correspond to a meeting-place picture.
The identity device of spokesman at the beginning, can be by the meeting-place picture border color of all spokesman in conference system
Be identified as identical color (such as：Green), identical original intensity.
Step S24, the brightness of the pre-set color identified according to default gradual change rule control gradually increases, to reach target
Colour brightness, wherein, default gradual change rule regulation has the rate of border color gradual change and the color of object brightness.
Wherein, presetting gradual change rule regulation has the rate of border color gradual change and color of object brightness, color of object brightness
It is divided into N number of brightness degree being sequentially increased, and brightness degree is correspondingly arranged with audio volume；I.e. audio volume is bigger, corresponding
The border color brightness of meeting picture is higher where spokesman.For example, according to the ascending of audio volume, color of object it is bright
Degree grade is divided into 1,2,3 ..., N.It determines, attend a meeting meeting-place A, and the meeting-place B and meeting-place C that attends a meeting that attends a meeting is the ginseng where spokesman
Meeting meeting-place, wherein, corresponding to audio volume, attend a meeting meeting-place A>Attend a meeting meeting-place B>Attend a meeting meeting-place C.When initial, above-mentioned 3 are attended a meeting
The border color in meeting-place is arranged to green, brightness degree all 1；
Specifically, comprise the following steps：
Step S241, judges whether the brightness of pre-set color reaches color of object brightness.When judging result is no, perform
Step S242；Otherwise, step S244 is performed.
Whether the brightness of the identity device real-time judge pre-set color of spokesman has reached color of object in conference system
Brightness, when being not reaching to, it is necessary to be adjusted to the brightness of pre-set color；When reaching color of object brightness, speech is represented
The mark of people is completed.
For example, corresponding to the meeting-place A that attends a meeting, the brightness degree of corresponding color of object brightness should be 3, and present intensity
Brightness degree for 1, therefore, it is necessary to adjust the corresponding border color brightness of the meeting-place A that attends a meeting.
Step S242 judges time that the last meeting-place picture border color brightness identified changes and current time
Whether difference reaches prefixed time interval.When judging result is to be, step S243 is performed；Otherwise, step S241 is performed.
When the identity device of spokesman judges that the brightness of pre-set color is not reaching to predetermined luminance in conference system, need
The brightness of pre-set color is adjusted again.Before adjustment, it is necessary to judge the last meeting-place picture frame identified
Whether the time and the difference of current time that colour brightness changes reach prefixed time interval, are only reaching prefixed time interval
When, just the brightness of pre-set color is adjusted.
Wherein, prefixed time interval can be the refresh time of conference system.By setting the judgement of prefixed time interval,
The frequent adjustment of brightness is avoided, influences the effect of video conference.
Step S243 controls the meeting-place picture border color brightness identified to increase the brightness of pre-set color.
The time changed in the meeting-place picture border color brightness identified and the difference of current time reach between preset time
Every when, the meeting-place picture border color that the identity device of spokesman is identified according to default gradual change rule control in conference system is bright
Degree increases the brightness of pre-set color, until reaching color of object brightness.
For example, brightness degree current meeting-place A of attending a meeting is 1, the brightness degree of corresponding color of object brightness is 3, can
According to default gradual change rule, the brightness degree for the meeting-place A that attends a meeting first is adjusted to 2, is then adjusted to 3 again.
Step S244, the mark of spokesman are completed.
In conference system the identity device of spokesman by the border color brightness of the meeting-place picture of all spokesman all
It is adjusted to after corresponding color of object brightness, represents that the mark of all spokesman at this time is completed.
As a kind of optional embodiment of the present embodiment, color of object brightness specified in gradual change rule is preset, it can be with
The M brightness degrees being sequentially increased are divided into, and brightness degree is correspondingly arranged (wherein, M with audio volume>N).Specifically, sieve
After selecting the meeting-place of attending a meeting with efficient voice information, to the meeting-place picture in all meeting-place of attending a meeting with efficient voice information
Border color identify different brightness, so as to ensure to have in the meeting-place of attending a meeting of efficient voice information, audio volume compared with
The meeting-place picture border color in small meeting-place of attending a meeting can have certain brightness, and the meeting-place that enables to respectively to attend a meeting can clearly be obtained
Know the meeting-place picture where all spokesman, improve the effect of video conference.
Embodiment 3
The embodiment of the present invention provides the identification method of spokesman in video conference a kind of, available for spokesman in video conference
Identity device in, as shown in figure 3, this method comprises the following steps：
Step S31 obtains the audio volume in meeting-place of respectively attending a meeting.
Identical with 2 step S21 of embodiment, details are not described herein.
Step S32, the meeting-place picture according to where audio volume determines spokesman.
Identical with 2 step S22 of embodiment, details are not described herein.
Step S33 is identified into the pre-set color of original intensity to the meeting-place picture frame of spokesman, wherein, each
Attend a meeting meeting-place correspond to a meeting-place picture.
Identical with 2 step S23 of embodiment, details are not described herein.
Step S34, the brightness of the pre-set color identified according to default gradual change rule control gradually increases, to reach target
Colour brightness, wherein, default gradual change rule regulation has the rate of border color gradual change and the color of object brightness.
Identical with 2 step S24 of embodiment, details are not described herein.
Step S35, the color of object brightness of the meeting-place picture frame in definite meeting-place of respectively attending a meeting.
During video conference progress, the audio volume in meeting-place of respectively attending a meeting constantly is changing, and therefore, it is necessary to respectively attending a meeting
The colour brightness of the meeting-place picture frame in meeting-place is adjusted in real time.Before real-time adjustment, it is thus necessary to determine that meeting-place of respectively attending a meeting
The color of object brightness of meeting-place picture frame.
The identity device of spokesman obtains the audio volume and voice messaging in meeting-place of respectively attending a meeting in conference system, according to audio
Volume determines the meeting-place picture where spokesman with voice messaging.Wherein it is determined that the method for the meeting-place picture where spokesman, it please
With reference to 2 step S22 of embodiment, details are not described herein.
After the spokesman that the identity device of spokesman is determined to attend a meeting in meeting-place in conference system, according to preset rules
Specified in correspondence between the audio volume of spokesman and the colour brightness of meeting-place picture frame, i.e. audio volume gets over
Greatly, the colour brightness of corresponding meeting-place picture frame is higher, so that it is determined that going out the target of the meeting-place picture frame in meeting-place of respectively attending a meeting
Colour brightness.
Step S36 obtains the current border color brightness of the meeting-place picture in meeting-place of respectively attending a meeting.
In conference system the identity device of spokesman obtain in real time the meeting-place picture in each meeting-place of attending a meeting when front bezel face
Colour brightness, in order to during video conference, be adjusted in real time to current border color brightness in real time.
Step S37, judges whether current border color brightness reaches the color of object brightness determined.When judging result is no
When, perform step S38；Otherwise, step S35 is performed.
Similar with 2 step S241 of embodiment, details are not described herein.
Step S38, judge last meeting-place picture border color brightness change time and current time difference whether
Reach prefixed time interval.When the determination result is yes, step S39 is performed；Otherwise, step S35 is performed.
The identity device of spokesman is in the color of object of the meeting-place picture frame in meeting-place of determining respectively to attend a meeting in conference system
After brightness, carry out between the time of border color brightness change of last meeting-place picture and the difference and preset time of current time
Relation between.
2 step S242 of embodiment specifically is refer to, details are not described herein.
Step S39, control respectively attend a meeting meeting-place meeting-place picture frame according to current border color brightness to corresponding target
Colour brightness adjusts.
Step S391 when current border color brightness is more than corresponding color of object brightness, lowers current border color
The brightness degree of brightness.
For example, the meeting-place A that attends a meeting, current border color brightness is 3, and corresponding color of object brightness is 1, then lowers successively
The brightness degree of current border color brightness, i.e., be adjusted downward to 2 by current border color brightness first, be then adjusted downward to 1 again.
Step S392 when current border color brightness is less than corresponding color of object brightness, raises current border color
The brightness degree of brightness.
For example, the meeting-place A that attends a meeting, current border color brightness is 1, and corresponding color of object brightness is 3, then raises successively
The brightness degree of current border color brightness, i.e., will be adjusted to 2 in current border color brightness first, then again on be adjusted to 3.
The step details not being described in detail in the present embodiment, refer to embodiment 2, details are not described herein.
Embodiment 4
The embodiment of the present invention provides one specific application example of identification method of spokesman in video conference a kind of, can use
In video conference in the identity device of spokesman, this method comprises the following steps：
(1) mix module channel speech information is obtained.
(2) passage of voice is screened out, and is ranked up according to the volume of passage.
(3) it is identified according to the maximum N number of passage of sequencing selection and makes a speech everybody, other identifier non-speaking people.
(4) color of object is carried out according to mark and specifies Caim.
(5) Cend is arranged to when being identified as spokesman Caim, Cbegin is arranged to when being identified as non-speaking people Caim.
(6) whether the current color of regular check sets Ccur and Caim equal.
(7) if when current color Ccur and color of object Caim inconsistent, last color change time Tlast is judged
Whether the poor Telaspe with current time Tcur is more than to change time Tgap.If it exceeds then change to color of object, otherwise
It is constant.
(8) change when changing color to color of object direction, i.e. Caim<Ccur-- during Ccur, Caim>Ccur, Cur++.
(9) the frame state and color that mark remains unchanged do not change.
(10) data after synthesizing send encoder to carry out coding and re-send to terminal.
Embodiment 5
The embodiment of the present invention provides the identity device of spokesman in video conference a kind of, available for realization embodiment 1 to reality
The identification method of spokesman in the video conference any one of example 4 is applied, as shown in figure 4, the device includes：
Acquiring unit 41, for obtaining the audio volume in meeting-place of respectively attending a meeting.
Determination unit 42, for the meeting-place picture where determining spokesman according to audio volume.
Unit 43 is identified, the pre-set color of original intensity is identified into for the meeting-place picture frame to spokesman,
In, meeting-place of each attending a meeting corresponds to a meeting-place picture.
Brightness control unit 44, the brightness of the pre-set color for being identified according to default gradual change rule control gradually increase
Add, to reach color of object brightness, wherein, default gradual change rule regulation has the rate of border color gradual change and the color of object bright
Degree.
As a kind of optional embodiment of the present embodiment, wherein, brightness control unit, including：
First judgment sub-unit, for judging whether the brightness of pre-set color reaches color of object brightness.
Second judgment sub-unit, for when miss the mark colour brightness, judging the last meeting-place picture identified
Whether the time and the difference of current time that border color brightness changes reach time interval.
Brilliance control subelement, for when the prefixed time interval, controlling the meeting-place picture border color identified
Brightness increases the brightness of pre-set color.
Embodiment 6
Fig. 5 is the hardware architecture diagram of media platform provided in an embodiment of the present invention, as shown in figure 5, the equipment includes
One or more processors 51 and memory 52, in Fig. 5 by taking a processor 51 as an example.
Media platform can also include：Image display (not shown), for the picture of the video conference after display processing
Image.Processor 51, memory 52 can be connected with image display by bus or other modes, with by total in Fig. 5
Exemplified by line connection.
Processor 51 can be central processing unit (Central Processing Unit, CPU).Processor 51 can be with
For other general processors, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
The combination of the chips such as discrete hardware components or above-mentioned all kinds of chips.General processor can be microprocessor or the processing
Device can also be any conventional processor etc..
Memory 52 is used as a kind of non-transient computer readable storage medium storing program for executing, available for storing non-transient software program, non-
Transient computer executable program and module, as the identification method of spokesman in the video conference in the embodiment of the present application corresponds to
Program instruction/module.Processor 51 is stored in non-transient software program, instruction and mould in memory 52 by operation
Block, various function application and data processing so as to execute server, that is, realize in above-described embodiment, make a speech in video conference
The identification method of people.
Memory 52 can include storing program area and storage data field, wherein, storing program area can storage program area,
At least one required application program of function；Storage data field can be stored according to the identity device of spokesman in video conference
Use created data etc..In addition, memory 52 can include high-speed random access memory, non-transient deposit can also be included
Reservoir, for example, at least a disk memory, flush memory device or other non-transient solid-state memories.In some embodiments
In, memory 52 is optional including compared with the remotely located memory of processor 51, these remote memories can pass through network
It is connected to the identity device of spokesman in video conference.The example of above-mentioned network include but not limited to internet, intranet,
LAN, mobile radio communication and combinations thereof.
One or more of modules are stored in the memory 52, when by one or more of processors 51
During execution, the identification method of the spokesman in video conference into embodiment 4 of embodiment 1 is performed.
The said goods can perform the method that the embodiment of the present invention is provided, and possesses the corresponding function module of execution method and has
Beneficial effect.The technical detail of detailed description, the correlation that for details, reference can be made in embodiment 1 to embodiment 4 are not retouched in the present embodiment
It states.
Embodiment 7
The embodiment of the present invention additionally provides a kind of non-transient computer storage medium, and the computer storage media is stored with
Computer executable instructions, the computer executable instructions can perform the identification method embodiment of spokesman in above-mentioned video conference
In processing method.Wherein, the storage medium can be magnetic disc, CD, read-only memory (Read-Only Memory,
ROM), random access memory (Random Access Memory, RAM), flash memory (Flash Memory), hard disk
(Hard Disk Drive, abbreviation：) or solid state disk (Solid-State Drive, SSD) etc. HDD；The storage medium is also
It can include the combination of the memory of mentioned kind.
It is that can lead to it will be understood by those skilled in the art that realizing all or part of flow in above-described embodiment method
Computer program is crossed relevant hardware to be instructed to complete, the program can be stored in a computer read/write memory medium
In, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (ROM) or random access memory (RAM) etc..
Although being described in conjunction with the accompanying the embodiment of the present invention, those skilled in the art can not depart from the present invention
Spirit and scope in the case of various modification can be adapted and modification, such modifications and variations are each fallen within by appended claims institute
Within the scope of restriction.
Claims (10)
1. the identification method of spokesman in a kind of video conference, which is characterized in that comprise the following steps：
Obtain the audio volume in meeting-place of respectively attending a meeting；
Meeting-place picture according to where the audio volume determines spokesman；
The pre-set color of original intensity is identified into the meeting-place picture frame of the spokesman, wherein, meeting-place of each attending a meeting
A corresponding meeting-place picture；
The brightness of the pre-set color identified according to default gradual change rule control gradually increases, bright to reach color of object
Degree, wherein, the default gradual change rule regulation has the rate of border color gradual change and the color of object brightness.
2. identification method according to claim 1, which is characterized in that described in identifying according to default gradual change rule control
The brightness of pre-set color gradually increases, and is included with reaching color of object brightness：
Judge whether the brightness of the pre-set color reaches the color of object brightness；
When the not up to color of object brightness, judge that the last meeting-place picture border color brightness identified changes when
Between with current time difference whether reach prefixed time interval；
When reaching the prefixed time interval, the meeting-place picture border color brightness identified described in control increases described preset
The brightness of color.
3. identification method according to claim 1, which is characterized in that described that spokesman is determined according to the audio volume
The meeting-place picture at place, comprises the following steps：
Obtain the voice messaging in each meeting-place of attending a meeting；
According to the voice messaging, inquiring about in all meeting-place of attending a meeting has the meeting-place of attending a meeting of efficient voice information；
The audio volume in the extraction meeting-place of attending a meeting with efficient voice information；
From all meeting-place of attending a meeting with efficient voice information, filter out maximum N number of of audio volume and described attend a meeting
Meeting-place；
Determine meeting-place picture of the meeting-place picture in N number of meeting-place of attending a meeting where the spokesman.
4. identification method according to claim 3, which is characterized in that the target face as defined in the default gradual change rule
The brightness degree of colour brightness is divided into the N number of brightness degree being sequentially increased, N number of brightness degree and the audio volume of N number of maximum
It is correspondingly arranged, wherein, the more big corresponding color of object brightness of audio volume is higher.
5. identification method according to claim 4, which is characterized in that described in identifying according to default gradual change rule control
After the brightness of pre-set color gradually increases, further include：
Determine the color of object brightness of the meeting-place picture frame in each meeting-place of attending a meeting；
Obtain the current border color brightness of the meeting-place picture in each meeting-place of attending a meeting；
Judge whether current border color brightness reaches the color of object brightness determined；
When the current border color brightness is not reaching to the pre-set color brightness, the frame of last meeting-place picture is judged
Whether the time and the difference of current time that colour brightness changes reach prefixed time interval；
When reaching the prefixed time interval, the meeting-place picture frame in each meeting-place of attending a meeting is controlled according to current border color
Brightness is to corresponding color of object brightness adjustment.
6. identification method according to claim 5, which is characterized in that the meeting-place picture frame is according to current border color
Brightness comprises the following steps to corresponding color of object brightness adjustment：
When the current border color brightness is more than the corresponding color of object brightness, it is bright to lower the current border color
The brightness degree of degree；
When the current border color brightness is less than the corresponding color of object brightness, it is bright to raise the current border color
The brightness degree of degree.
7. a kind of identity device of spokesman in video conference, which is characterized in that including：
Acquiring unit, for obtaining the audio volume in meeting-place of respectively attending a meeting；
Determination unit, for the meeting-place picture where determining spokesman according to the audio volume；
Unit is identified, the pre-set color of original intensity is identified into for the meeting-place picture frame to the spokesman, wherein,
Each meeting-place of attending a meeting corresponds to a meeting-place picture；
Brightness control unit, the brightness of the pre-set color for being identified according to default gradual change rule control gradually increase,
To reach color of object brightness, wherein, the default gradual change rule regulation has the rate of border color gradual change and the target face
Colour brightness.
8. identification method according to claim 7, which is characterized in that brightness control unit, including：
First judgment sub-unit, for judging whether the brightness of the pre-set color reaches the color of object brightness；
Second judgment sub-unit, for when the not up to color of object brightness, judging the last meeting-place picture identified
Whether the time and the difference of current time that border color brightness changes reach prefixed time interval；
Brightness increases subelement, for the meeting-place picture frame when reaching the prefixed time interval, identified described in control
Colour brightness increases the brightness of the pre-set color.
9. a kind of media platform, which is characterized in that including at least one processor；And at least one processor communication
The memory of connection；Wherein, the memory storage has the instruction that can be performed by one processor, and described instruction is described
At least one processor performs, so that the video council any one of at least one processor perform claim requirement 1 to 6
The identification method of spokesman in view.
10. a kind of non-transient computer readable storage medium storing program for executing, which is characterized in that the non-transient computer readable storage medium storing program for executing is deposited
Computer instruction is stored up, the computer instruction is used to make the video conference any one of computer perform claim requirement 1 to 6
The identification method of middle spokesman.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711339270.5A CN108111799B (en) | 2017-12-14 | 2017-12-14 | Method and device for identifying speaker in video conference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711339270.5A CN108111799B (en) | 2017-12-14 | 2017-12-14 | Method and device for identifying speaker in video conference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108111799A true CN108111799A (en) | 2018-06-01 |
| CN108111799B CN108111799B (en) | 2020-12-18 |
Family
ID=62216005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711339270.5A Active CN108111799B (en) | 2017-12-14 | 2017-12-14 | Method and device for identifying speaker in video conference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108111799B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111447400A (en) * | 2020-05-19 | 2020-07-24 | 科大讯飞股份有限公司 | Method, device, equipment and storage medium for processing participant identification of video conference |
| CN111556277A (en) * | 2020-05-19 | 2020-08-18 | 安徽听见科技有限公司 | Method, device, equipment and storage medium for processing participant identification of video conference |
| US10771694B1 (en) | 2019-04-02 | 2020-09-08 | Boe Technology Group Co., Ltd. | Conference terminal and conference system |
| CN113286114A (en) * | 2021-07-20 | 2021-08-20 | 北京微吼时代科技有限公司 | Video mixed-flow live broadcast technology-based video picture marking method, device and equipment |
| CN113992968A (en) * | 2021-10-27 | 2022-01-28 | 深圳市宝泽科技有限公司 | Method and device for gradually changing colors of frames of screen projection pictures based on wireless screen projection field |
| CN115052126A (en) * | 2022-08-12 | 2022-09-13 | 深圳市稻兴实业有限公司 | Ultra-high definition video conference analysis management system based on artificial intelligence |
| CN115460371A (en) * | 2021-06-09 | 2022-12-09 | 苏州译牛智能科技有限公司 | Simultaneous interpretation method in video conference, server and readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010027995A1 (en) * | 1998-10-19 | 2001-10-11 | Mehul Patel | Optical code reader for producing video displays |
| CN101080000A (en) * | 2007-07-17 | 2007-11-28 | 华为技术有限公司 | Method, system, server and terminal for displaying speaker in video conference |
| CN101212751A (en) * | 2006-12-26 | 2008-07-02 | 鸿富锦精密工业（深圳）有限公司 | Mobile communication terminal capable of displaying multi-party video call and the display method |
| CN102857409A (en) * | 2012-09-04 | 2013-01-02 | 上海量明科技发展有限公司 | Display method, client and system for local sound effect conversion in instant communication |
| CN105681582A (en) * | 2016-03-18 | 2016-06-15 | 努比亚技术有限公司 | Control color adjusting method and terminal |
| CN105744208A (en) * | 2014-12-11 | 2016-07-06 | 北京视联动力国际信息技术有限公司 | Video conference control system and control method |
| CN106162046A (en) * | 2015-04-24 | 2016-11-23 | 中兴通讯股份有限公司 | A kind of video conference image rendering method and device thereof |
-
2017
- 2017-12-14 CN CN201711339270.5A patent/CN108111799B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010027995A1 (en) * | 1998-10-19 | 2001-10-11 | Mehul Patel | Optical code reader for producing video displays |
| CN101212751A (en) * | 2006-12-26 | 2008-07-02 | 鸿富锦精密工业（深圳）有限公司 | Mobile communication terminal capable of displaying multi-party video call and the display method |
| CN101080000A (en) * | 2007-07-17 | 2007-11-28 | 华为技术有限公司 | Method, system, server and terminal for displaying speaker in video conference |
| CN102857409A (en) * | 2012-09-04 | 2013-01-02 | 上海量明科技发展有限公司 | Display method, client and system for local sound effect conversion in instant communication |
| CN105744208A (en) * | 2014-12-11 | 2016-07-06 | 北京视联动力国际信息技术有限公司 | Video conference control system and control method |
| CN106162046A (en) * | 2015-04-24 | 2016-11-23 | 中兴通讯股份有限公司 | A kind of video conference image rendering method and device thereof |
| CN105681582A (en) * | 2016-03-18 | 2016-06-15 | 努比亚技术有限公司 | Control color adjusting method and terminal |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10771694B1 (en) | 2019-04-02 | 2020-09-08 | Boe Technology Group Co., Ltd. | Conference terminal and conference system |
| CN111447400A (en) * | 2020-05-19 | 2020-07-24 | 科大讯飞股份有限公司 | Method, device, equipment and storage medium for processing participant identification of video conference |
| CN111556277A (en) * | 2020-05-19 | 2020-08-18 | 安徽听见科技有限公司 | Method, device, equipment and storage medium for processing participant identification of video conference |
| CN111556277B (en) * | 2020-05-19 | 2022-07-26 | 安徽听见科技有限公司 | Method, device and equipment for processing identifiers of participants in video conference and storage medium |
| CN115460371A (en) * | 2021-06-09 | 2022-12-09 | 苏州译牛智能科技有限公司 | Simultaneous interpretation method in video conference, server and readable storage medium |
| CN113286114A (en) * | 2021-07-20 | 2021-08-20 | 北京微吼时代科技有限公司 | Video mixed-flow live broadcast technology-based video picture marking method, device and equipment |
| CN113992968A (en) * | 2021-10-27 | 2022-01-28 | 深圳市宝泽科技有限公司 | Method and device for gradually changing colors of frames of screen projection pictures based on wireless screen projection field |
| CN115052126A (en) * | 2022-08-12 | 2022-09-13 | 深圳市稻兴实业有限公司 | Ultra-high definition video conference analysis management system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108111799B (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108111799A (en) | The identification method and device of spokesman in video conference | |
| EP2172016B1 (en) | Techniques for detecting a display device | |
| CN110351443A (en) | Intelligent outgoing call processing method, device, computer equipment and storage medium | |
| EP1352521B1 (en) | Automatic multi-camera video composition | |
| CN105849685B (en) | editing options for image regions | |
| CN103155548A (en) | Control of user interface to display call participants auto focus | |
| US20130114894A1 (en) | Blending of Exposure-Bracketed Images Using Weight Distribution Functions | |
| DE112005002281T5 (en) | System and method for optimizing the sound of a media center using microphones embedded in a remote control | |
| CN110060696B (en) | Sound mixing method and device, terminal and readable storage medium | |
| CN106303361A (en) | Image processing method, device, system and graphic process unit in video calling | |
| CN112351237A (en) | Automatic switching decision algorithm for main video of video conference | |
| DE102018001729A1 (en) | Management of communication session in relation to several transmission media | |
| CN113973103B (en) | Audio processing method, device, electronic equipment and storage medium | |
| TWI811692B (en) | Method and apparatus and telephony system for acoustic scene conversion | |
| CN104836982A (en) | Image processing method and device for video chat | |
| CN104683729A (en) | Method and device for issuing video layout | |
| CN112634925B (en) | Audio debugging method and device and computer equipment | |
| CN106131355B (en) | A kind of sound playing method and device | |
| CN113965700A (en) | Automatic adjusting method and system for intelligent television scene | |
| CN106851376A (en) | A kind of method of many video playbacks in same interface, system and its mobile terminal | |
| CN112735455A (en) | Method and device for processing sound information | |
| CN104301564A (en) | Intelligent conference telephone with mouth shape identification | |
| JP2014112845A (en) | Web conference system, information processor, and control method thereof, program, recording medium | |
| CN113814975B (en) | Robot control method, system, robot and computer readable storage medium | |
| JP5783157B2 (en) | Information processing apparatus, information processing apparatus control method, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |