CN111683183B - Multimedia conference non-participant conversation shielding processing method and system thereof - Google Patents
Multimedia conference non-participant conversation shielding processing method and system thereof Download PDFInfo
- Publication number
- CN111683183B CN111683183B CN202010474772.4A CN202010474772A CN111683183B CN 111683183 B CN111683183 B CN 111683183B CN 202010474772 A CN202010474772 A CN 202010474772A CN 111683183 B CN111683183 B CN 111683183B
- Authority
- CN
- China
- Prior art keywords
- voice information
- information
- participant
- voice
- voiceprint
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/56—Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities
- H04M3/567—Multimedia 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/56—Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities
- H04M3/568—Arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities audio processing specific to telephonic conferencing, e.g. spatial distribution, mixing of participants
Abstract
The invention provides a non-participant conversation shielding processing method and a system thereof for a multimedia conference, wherein the method comprises the following steps: the method comprises the steps of collecting first voice information of a participant and extracting first voiceprint information from the first voice information, detecting a non-participant terminal near the participant terminal, collecting second voice information of a host from the non-participant terminal and extracting second voiceprint information from the non-participant terminal, judging whether the second voiceprint information is the same as the first voiceprint information, judging whether the host of the non-participant terminal is in agreement with the participant if the host of the non-participant terminal is in agreement with the participant, storing the second voiceprint information if the owner is in agreement with the participant, collecting newly added voice information in environmental sound and extracting third voiceprint information from the environment sound, judging whether the third voiceprint information is the same as the second voiceprint information, judging whether third voice information of the participant is generated after the newly added voice information if the third voice information is generated, judging whether sound level movement of the third voice information relative to the first voice information occurs if the third voice information is generated, and shielding the third voice information and the newly added voice information if the third voice information is generated.
Description
Technical Field
The invention relates to the technical field of multimedia conferences, in particular to a multimedia conference non-participant conversation shielding processing method and a system thereof.
Background
With the development of society, the application of audio and video conference software is increasingly popularized, and the audio and video conference software is a multimedia communication mode for holding a conference through a communication network by using electronic equipment, and can enable geographically dispersed participants to exchange and share real-time information through video and sound information streams so as to develop a cooperative working mode.
During the course of a meeting, such a scenario is often encountered: hum sounds of the participants and other people in the same space in reality (such as daily conversations of the participants and family) are collected to be transmitted to audio and video conference software, so that the voices are heard by the other participants, and the quality of a conference and the privacy of a user are affected.
In contrast, the practice adopted in the prior art is to reduce the noise of the ambient sound, i.e., to recognize the sound of the non-participant, so as to reduce the noise and filter the sound.
This approach has the disadvantage of filtering only the voices of non-participants, but not the conversations between the participants and non-participants at the same time, resulting in inadequate voice filtering and failure to take into account the actual filtering requirements.
Disclosure of Invention
The invention aims to:
in order to overcome the disadvantages in the background art, embodiments of the present invention provide a method and a system for processing non-participant conversation screening in a multimedia conference, which can effectively solve the problems related to the background art.
The technical scheme is as follows:
a multimedia conference non-participant conversation screening processing method, the method comprising:
collecting first voice information of participants and extracting first voiceprint information from the first voice information;
detecting non-participant terminals near the participant terminals;
acquiring second voice information of the owner from the detected non-participant terminal and extracting second voiceprint information from the second voice information;
comparing the second voiceprint information with the first voiceprint information, judging whether the second voiceprint information is the same as the first voiceprint information, and if the second voiceprint information is different from the first voiceprint information, judging whether the owner of the non-participant terminal is acquainted with the participant;
if so, storing the second voiceprint information;
acquiring newly added voice information in the environmental sound and extracting third voiceprint information from the newly added voice information;
judging whether the third voiceprint information is the same as the second voiceprint information;
if the voice information is the same as the voice information of the newly added person, judging whether third voice information of the participant is generated or not, and if the third voice information is generated, judging whether the third voice information moves relative to the first voice information or not;
and if the third voice information occurs, shielding the third voice information and the newly added voice information.
As a preferable aspect of the present invention, detecting a non-participant terminal in the vicinity of a participant terminal includes:
sending a detection instruction to a router accessed with the participating terminal, judging whether other accessed terminals exist through the router, and if so, confirming the terminals as nearby non-participating terminals;
or, the participating terminal detects whether the nearby Bluetooth equipment is started or not, and if so, the participating terminal is determined as a nearby non-participating terminal.
As a preferred mode of the present invention, the acquiring of the second voice information of the owner from the detected non-participant terminal includes:
sending a second voice information acquisition request to the detected non-participant terminal;
and the non-participant terminal acquires the installed chat application according to the acquisition request, acquires one voice section of the owner from the chat application and feeds the voice section as second voice information.
As a preferred aspect of the present invention, the process of masking the third speech information and the newly added speech information includes:
and canceling the conference transmission of the audio signals corresponding to the third voice information and the newly added voice information.
As a preferred mode of the present invention, the method further includes:
and judging whether the newly added voice information in the environmental sound stops or not, if so, judging whether the sound level of the third voice information is recovered, and if so, canceling the shielding processing of the third voice information and the newly added voice information.
A system for processing non-participant conversation screening in a multimedia conference, comprising:
the first voice information acquisition module is used for acquiring first voice information of the participants;
the first voiceprint information extraction module is used for extracting first voiceprint information from the first voice information;
the non-participant terminal detection module is used for detecting non-participant terminals near the participant terminals;
the second voice information acquisition module is used for acquiring second voice information of the owner from the detected non-participant terminal;
the second voiceprint information extraction module is used for extracting second voiceprint information from the second voice information;
the first voiceprint information comparison module is used for comparing the second voiceprint information with the first voiceprint information and judging whether the second voiceprint information is the same as the first voiceprint information;
the personnel acquaintance judging module is used for judging whether the owner of the non-participant terminal and the participant acquaintance or not when the second voiceprint information is judged to be different from the first voiceprint information;
the second fingerprint information storage module is used for storing the second fingerprint information when the owner of the non-participant terminal is judged to be acquainted with the participant;
the newly-added voice information acquisition module is used for acquiring newly-added voice information in the environmental sound;
the third voiceprint information extraction module is used for extracting third voiceprint information from the newly added voice information;
a second voiceprint information determination module, configured to determine whether the third voiceprint information is the same as the second voiceprint information;
the third voice information judging module is used for judging whether third voice information of the participant is generated immediately after the newly added voice information when the third voice print information is judged to be the same as the second voice print information;
the voiceprint judging module is used for judging whether the third voice information of the participant moves relative to the first voice information when judging that the third voice information of the participant is generated immediately after the newly added voice information;
and the sound shielding module is used for shielding the third voice information and the newly added voice information when judging that the third voice information has sound level movement relative to the first voice information.
As a preferred mode of the present invention, the non-participant terminal detection module is further configured to:
sending a detection instruction to a router accessed with the participating terminal, judging whether other accessed terminals exist through the router, and if so, confirming the terminals as nearby non-participating terminals;
or detecting whether the nearby Bluetooth equipment is started or not, and if so, confirming the nearby Bluetooth equipment as a nearby non-participating terminal.
As a preferred mode of the present invention, the second voice information collecting module is further configured to:
sending a second voice information acquisition request to the detected non-participant terminal;
and the non-participant terminal acquires the installed chat application according to the acquisition request, acquires one voice section of the owner from the chat application and feeds the voice section as second voice information.
As a preferable mode of the present invention, the sound shielding module is further configured to:
and canceling the conference transmission of the audio signal corresponding to the third voice information and the newly added voice information.
As a preferred aspect of the present invention, a sound shielding module includes:
the newly added voice information judgment module is used for judging whether the newly added voice information in the environmental sound stops or not;
the sound level recovery judging module is used for judging whether the sound level of the third voice information is recovered or not when judging that the newly added voice information in the environmental sound stops;
and the sound shielding submodule is used for canceling the shielding processing of the third voice information and the newly added voice information when the sound level of the third voice information is judged to be recovered.
The invention realizes the following beneficial effects:
the method comprises the steps of collecting first voice information of participants and extracting first voiceprint information from the first voice information, detecting a non-participant terminal near the participant terminal, collecting second voice information of a host from the detected non-participant terminal and extracting second voiceprint information from the second voice information, storing the second voiceprint information when the host of the non-participant terminal is judged to be different from the first voiceprint information and the host of the non-participant terminal is identified with the participants, collecting newly-added voice information in environmental sound and extracting third voiceprint information from the environment sound, shielding the third voice information and the newly-added voice information when the third voiceprint information is judged to be the same as the second voiceprint information and the third voice information is generated after the newly-added voice information is generated, and shielding the third voice information and the newly-added voice information when the third voice information is subjected to voice displacement relative to the first voice information, so that the participants and the non-participant can be subjected to a multimedia conference in the process, and the influence of the non-participant on the conference is avoided (the conversation between the participants and the participants is not heard by other participants).
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a schematic flowchart of a non-participant session shielding processing method for a multimedia conference according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a non-participant session shielding processing method for a multimedia conference according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a system for processing a non-participant session shielding in a multimedia conference according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a sound shielding module according to a third embodiment of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments; in the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure; one skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc.; in other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale; the same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted; the structures shown in the drawings are illustrative only and do not necessarily include all of the elements; for example, some components may be split and some components may be combined to show one device.
Example one
As shown with reference to fig. 1. The embodiment provides a multimedia conference non-participating session shielding processing method, wherein the method provided by the invention can be implemented by software installed or set in a device, and the software can be an application program, such as a typical APP, or implemented by an operating system running in the device. The participant terminal mentioned in the embodiment of the invention refers to a terminal which is provided with multimedia conference software and is starting the software to carry out a conference, the non-participant terminal refers to other terminals which are positioned in the same space with the participant terminal except the participant terminal, wherein the non-participant terminal can also be one of the participant terminals, but the non-participant terminal is converted into the participant terminal when the multimedia conference software is operated to carry out the conference, and the terminal mentioned in the embodiment of the invention can be electronic equipment such as a mobile phone, a computer, a tablet and the like; the multimedia conference mentioned in this embodiment includes an audio conference and a video conference.
The method provided by the embodiment of the invention comprises the following steps:
s101, collecting first voice information of the participants and extracting first voiceprint information from the first voice information.
The participant in this embodiment refers to a person who is in a multimedia conference, that is, a participant terminal is used to conference with other participants, the participant terminal (specifically using APP or an operating system) collects the sound of the participant, that is, first voice information, the first voice information may be collected in an instant manner or in advance, and then voiceprint information is extracted from the collected first voice information.
The voiceprint information is the sound wave frequency spectrum carrying speech information and displayed by an electroacoustic instrument, and the voiceprint has the characteristics of specificity and relative stability; after the adult, the voice of the human can be kept relatively stable and unchanged for a long time; experiments prove that whether a speaker intentionally imitates the voice and tone of other people or speaks with whisper and whisper, even if the imitation is vivid, the voiceprint of the speaker is different all the time, so that the voiceprint information can be considered to represent the identity of each user, and different people can be distinguished.
S102, detecting non-participant terminals near the participant terminals.
In the embodiment of the present invention, S102 may specifically be implemented in the following manner:
and sending a detection instruction to a router accessed with the participating terminal, judging whether other accessed terminals exist through the router, and if so, confirming the terminals as nearby non-participating terminals.
Or, the participating terminal detects whether the nearby Bluetooth device is started or not, and if so, the participating terminal is determined as a nearby non-participating terminal.
For the former, the participating terminal sends a detection instruction to a router accessed by the participating terminal, the router judges which terminals exist in the terminals connected with the participating terminal after receiving the detection instruction sent by the participating terminal, and confirms the detected other terminals except the participating terminal as non-participating terminals.
For the latter, the participant terminal searches nearby bluetooth devices through a built-in bluetooth search function, and confirms the searched bluetooth devices as non-participant terminals in the vicinity of the participant terminal.
And S103, acquiring second voice information of the owner from the detected non-participant terminal and extracting second voiceprint information from the second voice information.
In this step, the second voice information of the owner collected from the detected non-participant terminal may be specifically implemented in the following manner:
sending a second voice information acquisition request to the detected non-participant terminal; and the non-participant terminal acquires the installed chat application according to the acquisition request, acquires one voice section of the owner from the chat application and feeds the voice section as second voice information.
Specifically, the participant terminal sends a second voice information acquisition request to the detected non-participant terminal, the non-participant terminal acquires the installed chat application after receiving the second voice information acquisition request, for example, the application can send voice messages such as QQ and WeChat, of course, other chat applications capable of sending and receiving voice messages are also within the protection scope of the present invention, then finds out any voice chat record from the chat application, identifies the master user (the master user can be acquired through the arrangement mode of the message interface), and then correspondingly acquires the voice message of the master user, namely one voice segment of the collector owner, and feeds back the voice segment as the second voice message to the participant terminal.
And S104, comparing the second voiceprint information with the first voiceprint information, judging whether the second voiceprint information is the same as the first voiceprint information, and if the second voiceprint information is different from the first voiceprint information, executing S105.
In S104, specifically, the voiceprint characteristics of the second voiceprint information and the first voiceprint information are respectively provided, then the respective voiceprint characteristics are input into the voiceprint recognition software for comparison, then a comparison result is output, whether the two voiceprint characteristics are the same is judged according to the comparison result, if the two voiceprint characteristics are the same, it is determined that the two corresponding users are the same person, otherwise, it is determined that the two corresponding users are different users, and if the two corresponding voiceprint characteristics are the same, S105 is executed.
And S105, judging whether the owner of the non-participant terminal is acquainted with the participant, and executing S106 if the owner of the non-participant terminal is acquainted with the participant.
In S105, determining whether the owner of the non-participant terminal and the participant meet each other may specifically be implemented as follows: judging by an address book or chatting software mode, namely judging whether the contact way of one party exists in the address book of the other party terminal or chatting software or whether historical chatting records exist among the contact ways of the two parties, and if so, judging that the two parties are identified; the picture recognition mode can also be used, namely, a picture of one person is obtained, whether the picture exists is searched and recognized in the other terminal, and if the picture exists, the two persons are considered to be acquainted.
And S106, storing the second voiceprint information.
It is stored in a specific database.
And S107, acquiring newly added voice information in the environmental sound and extracting third voiceprint information from the newly added voice information.
The newly added voice information refers to voice of people except for the participants, the voice information comprises voice of other participants who carry out the multimedia conference with the participants, the participants terminal filters (only does not consider and is not filtering in practical significance) voice of other participants in the step, then whether new voice information exists in the environment or not is detected, and if the voice information is detected, third voiceprint information is extracted from the voice information.
And S108, judging whether the third voiceprint information is the same as the second voiceprint information or not, and if so, executing S109.
Similar to S104, in S108, the third voiceprint information and the voiceprint features of the second voiceprint information are respectively extracted through the participant terminal, then the respective voiceprint features are input into voiceprint recognition software for comparison, then a comparison result is output, whether the third voiceprint information and the second voiceprint information are the same is judged according to the comparison result, if the third voiceprint information and the second voiceprint information are the same, it is determined that the users corresponding to the third voiceprint information and the second voiceprint information are the same, otherwise, it is determined that the users are different, and if the third voiceprint information and the second voiceprint information are the same, S109 is executed.
And S109, judging whether the third voice information of the participant is generated immediately after the newly added voice information, and if so, executing S110.
The immediate judgment can be determined by judging whether the third voice information of the participant is generated within a preset time threshold after the newly-added voice information is generated, and the preset time threshold can be set according to actual conditions, for example, by acquiring an average interval time value of the participant and the newly-added voice information (namely, the owner of the non-participant terminal) in an actual conversation, the preset time threshold is correspondingly set; if the second voice information is within the preset time threshold, the third voice information of the participant is considered to be generated immediately after the newly added voice information.
The third voice information of the participant is not a section of voice in a specific time point, and may be continuous or intermittent, that is, the participant can be considered as the third voice information as long as it is judged that the participant utters voice (immediately) within a preset time after the new voice information is generated.
And S110, judging whether the third voice message generates sound level movement relative to the first voice message, and if so, executing S111.
Specifically, when the participant terminal acquires the first voice information, it records a sound level corresponding to the first voice information, that is, a sound source position relative to the participant terminal, where the sound source position may be determined by training positions corresponding to sounds at different positions in advance to serve as a basis for judgment, for example, when a sound source is at one of the positions, a band, a frequency, a volume value, and the like corresponding to the detected sound source are acquired, so as to record sound source information corresponding to different positions.
In the embodiment of the present invention, it is necessary to determine a sound generating position of the third voice information, after the sound generating position of the third voice information is obtained, compare the sound generating position with the sound generating position of the first voice information, and if the sound generating position of the third voice information is different or exceeds a certain range, it is determined that the sound generating position of the third voice information moves relative to the sound generating position of the first voice information.
Based on the test result, when the sound level of the third voice information is judged to move relative to the first voice information, the third voice information is considered to be the voice information which carries out conversation with the newly added voice information, namely the conversation information carried out by the participants and the host of the non-participant terminal, but not the voice information which carries out conversation with other participants in the conference.
And S111, shielding the third voice information and the newly added voice information.
In this embodiment of the present invention, the shielding processing on the third voice information and the newly added voice information may specifically refer to: and canceling the conference transmission of the audio signals corresponding to the third voice information and the newly added voice information.
That is, in the process of carrying out the multimedia conference between the participant and other participants, if the conversation between the participant and non-participants is generated, the conversation between the participant and non-participants is sound-shielded, and specifically, the audio information corresponding to the participant is acquired, so that the participant is cancelled to carry out conference transmission, namely, the audio information is not transmitted to the ongoing multimedia conference, so that the conference is not influenced (the participant can normally hear the sound of other participants), and meanwhile, the conversation between the participant and non-participants is prevented from being heard by other participants, thereby effectively guaranteeing the quality of the conference and the privacy of users.
Example two
As shown with reference to fig. 2. In this embodiment, on the basis of the first embodiment, the method further includes the following steps:
s201, judging whether the voice information added in the environment sound stops, and if the voice information stops, executing S202.
The judgment of whether the newly added voice information stops or not can also be determined by judging whether the disappearance time of the newly added voice information exceeds a preset time threshold or not, and if the disappearance time of the newly added voice information exceeds the preset time threshold, the newly added voice information in the environmental sound is considered to stop.
S202, judging whether the sound level of the third voice information is recovered or not, and if so, executing S203.
Specifically, the participant terminal determines whether the sound level of the third voice message is restored to the position before the movement, that is, the sound source position corresponding to the first voice message, and if the sound level of the third voice message is matched or tends to be matched, the participant terminal regards that the sound level is restored.
In this case, the conversation between the participant and the non-participant will be considered to have ended.
And S203, canceling the shielding processing of the third voice information and the newly added voice information.
After the recovery, the audio signal corresponding to the third voice information can be normally transmitted to the multimedia conference, and other participants can normally hear the sound of the participants.
EXAMPLE III
As shown with reference to fig. 3. The embodiment provides a non-participant session screening processing system for a multimedia conference, which comprises:
the first voice information collecting module 301 is configured to collect first voice information of a participant.
A first voiceprint information extraction module 302, configured to extract first voiceprint information from the first voice information.
A non-participant terminal detecting module 303, configured to detect a non-participant terminal near the participant terminal.
And the second voice information acquisition module 304 is configured to acquire second voice information of the owner from the detected non-participant terminal.
A second voiceprint information extracting module 305, configured to extract second voiceprint information from the second voice information.
The first voiceprint information comparison module 306 is configured to compare the second voiceprint information with the first voiceprint information, and determine whether the second voiceprint information is the same as the first voiceprint information.
And a person acquaintance determination module 307, configured to determine whether the owner of the non-participant terminal and the participant acquaintance with each other when determining that the second voiceprint information is different from the first voiceprint information.
And a second fingerprint information storage module 308, configured to store the second fingerprint information when it is determined that the owner of the non-participant terminal is acquainted with the participant.
And a new voice information acquisition module 309, configured to acquire new voice information in the environmental sound.
And a third voiceprint information extraction module 310, configured to extract third voiceprint information from the newly added voice information.
And a second voiceprint information determining module 311, configured to determine whether the third voiceprint information is the same as the second voiceprint information.
The third voice information determining module 312 is configured to determine whether the third voice information of the participant is generated immediately after the newly added voice information when it is determined that the third voiceprint information is the same as the second voiceprint information.
And a voiceprint determination module 313, configured to determine whether a phonic shift occurs in the third voice message relative to the first voice message when it is determined that the third voice message of the participant is generated immediately after the newly added vocal message.
The sound masking module 314 is configured to mask the third voice message and the newly added voice message when it is determined that the sound level of the third voice message moves relative to the sound level of the first voice message.
Wherein, the non-participating terminal detecting module 303 is further configured to:
and sending a detection instruction to a router accessed with the participating terminal, judging whether other accessed terminals exist through the router, and if so, confirming the terminals as nearby non-participating terminals.
Or detecting whether the nearby Bluetooth equipment is started or not, and if so, confirming the nearby Bluetooth equipment as a nearby non-participating terminal.
Wherein the second voice information collecting module 304 is further configured to:
and sending a second voice information acquisition request to the detected non-participating terminal.
And the non-participant terminal acquires the installed chat application according to the acquisition request, acquires one voice section of the owner from the chat application and feeds the voice section as second voice information.
Wherein the sound masking module 314 is further configured to:
and canceling the conference transmission of the audio signal corresponding to the third voice information and the newly added voice information.
As shown with reference to fig. 4. As a preferable mode of the embodiment of the present invention, the sound shielding module 314 includes:
and a newly added voice information determining module 315, configured to determine whether the newly added voice information in the environmental sound stops.
The sound level restoration determining module 316 is configured to determine whether the sound level of the third voice information is restored when it is determined that the voice information added in the environmental sound stops.
And the sound masking submodule 317 is configured to cancel the masking processing on the third voice information and the newly added voice information when it is determined that the sound level of the third voice information is recovered.
The implementation process of this embodiment is the same as that of the first and second embodiments, and the above contents are specifically referred to.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and are intended to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the scope of the present invention. All equivalent changes or modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (10)
1. A multimedia conference non-participant conversation screening processing method is characterized by comprising the following steps:
collecting first voice information of participants and extracting first voiceprint information from the first voice information;
detecting non-participant terminals near the participant terminals;
acquiring second voice information of the owner from the detected non-participant terminal and extracting second voiceprint information from the second voice information;
comparing the second voiceprint information with the first voiceprint information, judging whether the second voiceprint information is the same as the first voiceprint information, and if the second voiceprint information is different from the first voiceprint information, judging whether the owner of the non-participant terminal is acquainted with the participant;
if yes, storing the second fingerprint information;
acquiring newly added voice information in the environmental sound and extracting third voiceprint information from the newly added voice information;
judging whether the third voiceprint information is the same as the second voiceprint information;
if the voice information is the same as the voice information of the newly added person, judging whether third voice information of the participant is generated or not, and if the third voice information is generated, judging whether the third voice information moves relative to the first voice information or not; specifically, the sound generating position of the third voice information is judged firstly, after the sound generating position of the third voice information is obtained, the sound generating position of the third voice information is compared with the sound generating position of the first voice information, if the sound generating position of the third voice information is different or exceeds a certain range, the sound generating position of the third voice information relative to the first voice information is considered to move, and when the first voice information is collected by the conference participating terminal, the corresponding sound generating position of the conference participating terminal, namely the sound source position relative to the conference participating terminal, is recorded; when the third voice information is judged to have the sound level movement relative to the first voice information, the third voice information is considered to be the voice information for carrying out conversation with the newly-added voice information, namely the conversation information carried out by the participants and the host of the non-participant terminal, but not the voice information for carrying out conversation with other participants in the conference;
and if the third voice information occurs, shielding the third voice information and the newly added voice information.
2. The method as claimed in claim 1, wherein detecting non-participating terminals in the vicinity of the participating terminals comprises:
sending a detection instruction to a router accessed with the participating terminal, judging whether other accessed terminals exist through the router, and if so, confirming the terminals as nearby non-participating terminals;
or, the participating terminal detects whether the nearby Bluetooth equipment is started or not, and if so, the participating terminal is determined as a nearby non-participating terminal.
3. The method as claimed in claim 1, wherein the step of collecting the second voice information of the owner from the detected non-participating terminal comprises:
sending a second voice information acquisition request to the detected non-participant terminal;
and the non-participant terminal acquires the installed chat application according to the acquisition request, acquires one voice section of the owner from the chat application and feeds the voice section as second voice information.
4. The method as claimed in claim 1, wherein the step of masking the third voice message and the new voice message comprises:
and canceling the conference transmission of the audio signal corresponding to the third voice information and the newly added voice information.
5. The method as claimed in claim 1, wherein the method further comprises:
and judging whether the newly added voice information in the environmental sound stops or not, if so, judging whether the sound level of the third voice information is recovered, and if so, canceling the shielding processing of the third voice information and the newly added voice information.
6. A system for processing non-participant conversation screening in a multimedia conference, comprising:
the first voice information acquisition module is used for acquiring first voice information of the participants;
the first voiceprint information extraction module is used for extracting first voiceprint information from the first voice information;
the non-participant terminal detection module is used for detecting non-participant terminals near the participant terminals;
the second voice information acquisition module is used for acquiring second voice information of the owner from the detected non-participant terminal;
the second voiceprint information extraction module is used for extracting second voiceprint information from the second voice information;
the first voiceprint information comparison module is used for comparing the second voiceprint information with the first voiceprint information and judging whether the second voiceprint information is the same as the first voiceprint information;
the personnel acquaintance judging module is used for judging whether the owner of the non-participant terminal and the participant acquaintance or not when the second voiceprint information is judged to be different from the first voiceprint information;
the second fingerprint information storage module is used for storing the second fingerprint information when the owner of the non-participant terminal is judged to be acquainted with the participant;
the newly added voice information acquisition module is used for acquiring newly added voice information in the environmental sound;
the third voiceprint information extraction module is used for extracting third voiceprint information from the newly added voice information;
a second voiceprint information judgment module, configured to judge whether the third voiceprint information is the same as the second voiceprint information;
the third voice information judging module is used for judging whether third voice information of the participant is generated immediately after the newly added voice information when the third voice print information is judged to be the same as the second voice print information;
the voiceprint judging module is used for judging whether the third voice information moves relative to the first voice information or not when judging that the third voice information of the participant is generated immediately after the newly added voice information; specifically, the sound generating position of the third voice information is judged firstly, after the sound generating position of the third voice information is obtained, the sound generating position of the third voice information is compared with the sound generating position of the first voice information, if the sound generating position of the third voice information is different or exceeds a certain range, the sound generating position of the third voice information relative to the first voice information is considered to move, and when the first voice information is collected by the conference participating terminal, the corresponding sound generating position of the conference participating terminal, namely the sound source position relative to the conference participating terminal, is recorded; when the third voice information is judged to have the sound level movement relative to the first voice information, the third voice information is considered to be the voice information for carrying out conversation with the newly-added voice information, namely the conversation information carried out by the participants and the host of the non-participant terminal, but not the voice information for carrying out conversation with other participants in the conference;
and the sound shielding module is used for shielding the third voice information and the newly added voice information when judging that the third voice information moves relative to the sound level of the first voice information.
7. The system according to claim 6, wherein the non-participant terminal detection module is further configured to:
sending a detection instruction to a router accessed with the participating terminal, judging whether other accessed terminals exist through the router, and if so, confirming the terminals as nearby non-participating terminals;
or detecting whether the nearby Bluetooth equipment is started or not, and if so, confirming the nearby Bluetooth equipment as a nearby non-participating terminal.
8. The system of claim 6, wherein the second voice information collection module is further configured to:
sending a second voice information acquisition request to the detected non-participant terminal;
and the non-participant terminal acquires the installed chat application according to the acquisition request, acquires one voice section of the owner from the chat application and feeds the voice section as second voice information.
9. The system according to claim 6, wherein the sound masking module is further configured to:
and canceling the conference transmission of the audio signals corresponding to the third voice information and the newly added voice information.
10. The system of claim 6, wherein the sound masking module comprises:
the newly added voice information judgment module is used for judging whether the newly added voice information in the environmental sound stops or not;
the sound level restoration judging module is used for judging whether the sound level of the third voice information is restored or not when judging that the voice information newly added in the environmental sound stops;
and the sound shielding submodule is used for canceling the shielding processing of the third voice information and the newly added voice information when the sound level of the third voice information is judged to be recovered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010474772.4A CN111683183B (en) | 2020-05-29 | 2020-05-29 | Multimedia conference non-participant conversation shielding processing method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010474772.4A CN111683183B (en) | 2020-05-29 | 2020-05-29 | Multimedia conference non-participant conversation shielding processing method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111683183A CN111683183A (en) | 2020-09-18 |
| CN111683183B true CN111683183B (en) | 2022-11-11 |
Family
ID=72434530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010474772.4A Active CN111683183B (en) | 2020-05-29 | 2020-05-29 | Multimedia conference non-participant conversation shielding processing method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111683183B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112261347A (en) * | 2020-10-14 | 2021-01-22 | 浙江大华技术股份有限公司 | Method and device for adjusting participation right, storage medium and electronic device |
| CN113064994A (en) * | 2021-03-25 | 2021-07-02 | 平安银行股份有限公司 | Conference quality evaluation method, device, equipment and storage medium |
| CN113271430B (en) * | 2021-05-13 | 2022-11-18 | 中国联合网络通信集团有限公司 | Anti-interference method, system, equipment and storage medium in network video conference |
| CN115333879B (en) * | 2022-08-09 | 2023-11-07 | 深圳市研为科技有限公司 | Remote conference method and system |
| CN116708709B (en) * | 2023-08-01 | 2024-03-08 | 深圳市海域达赫科技有限公司 | Communication system and method based on cloud service |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007241130A (en) * | 2006-03-10 | 2007-09-20 | Matsushita Electric Ind Co Ltd | System and device using voiceprint recognition |
| EP2936791B1 (en) * | 2012-12-21 | 2017-01-04 | Dolby Laboratories Licensing Corporation | Audio burst collision resolution |
| CN105933558B (en) * | 2016-04-25 | 2019-01-04 | 四川联友电讯技术有限公司 | A kind of intelligent shielding and release method of videoconference strong noise participant |
| CN105933556B8 (en) * | 2016-04-25 | 2019-08-06 | 上海新殿光电子科技有限公司 | A kind of videoconference noise isolation system and method determined based on participant |
| CN109979467B (en) * | 2019-01-25 | 2021-02-23 | 出门问问信息科技有限公司 | Human voice filtering method, device, equipment and storage medium |
| CN109949818A (en) * | 2019-02-15 | 2019-06-28 | 平安科技（深圳）有限公司 | A kind of conference management method and relevant device based on Application on Voiceprint Recognition |
-
2020
- 2020-05-29 CN CN202010474772.4A patent/CN111683183B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111683183A (en) | 2020-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111683183B (en) | Multimedia conference non-participant conversation shielding processing method and system thereof | |
| CN105100521A (en) | Method and server for realizing ordered speech in teleconference | |
| US8762138B2 (en) | Method of editing a noise-database and computer device | |
| US8750461B2 (en) | Elimination of typing noise from conference calls | |
| CN111199751B (en) | Microphone shielding method and device and electronic equipment | |
| CN108696641A (en) | Call reminding method, device, storage medium and mobile terminal | |
| CN110971681A (en) | Voice interaction method, intelligent loudspeaker box, background server and system | |
| CN104851423B (en) | Sound information processing method and device | |
| CN113271430B (en) | Anti-interference method, system, equipment and storage medium in network video conference | |
| US20210312143A1 (en) | Real-time call translation system and method | |
| US10924608B1 (en) | Communication volume level change detection | |
| CN110265038B (en) | Processing method and electronic equipment | |
| CN113301291B (en) | Anti-interference method, system, equipment and storage medium in network video conference | |
| WO2016045446A1 (en) | Voice reminding information generation and voice reminding method and device | |
| CN111028837B (en) | Voice conversation method, voice recognition system and computer storage medium | |
| CN113259620B (en) | Video conference data synchronization method and device | |
| CN112565668B (en) | Method for sharing sound in network conference | |
| US11783837B2 (en) | Transcription generation technique selection | |
| US20200184973A1 (en) | Transcription of communications | |
| CN111800700B (en) | Method and device for prompting object in environment, earphone equipment and storage medium | |
| CN109559760B (en) | Emotion analysis method and system based on voice information | |
| CN105592226B (en) | Method and device for processing data in call process | |
| TWI519123B (en) | Method of processing telephone voice output, software product processing telephone voice, and electronic device with phone function | |
| CN113194021B (en) | Electronic device, message play control system and message play control method | |
| CN112822249A (en) | WebRTC-based real-time voice acquisition method |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220927 Address after: No. 011, Building 11, No. 7 Lijiafen, Chaoyang District, Beijing 100000 Applicant after: Jieyuntong (Beijing) Technology Co.,Ltd. Address before: 215400 room 04, shop 13a, 376 Zhenghe Middle Road, Chengxiang Town, Taicang City, Suzhou City, Jiangsu Province Applicant before: TAICANG QINFENG ADVERTISING MEDIA CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |