CN104618616B - Videoconference participant identification system and method based on speech feature extraction - Google Patents
Videoconference participant identification system and method based on speech feature extraction Download PDFInfo
- Publication number
- CN104618616B CN104618616B CN201510022211.XA CN201510022211A CN104618616B CN 104618616 B CN104618616 B CN 104618616B CN 201510022211 A CN201510022211 A CN 201510022211A CN 104618616 B CN104618616 B CN 104618616B
- Authority
- CN
- China
- Prior art keywords
- meeting
- participant
- cloud server
- videoconference
- feature extraction
- 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.)
- Expired - Fee Related
Links
Abstract
The invention discloses a kind of videoconference participant identification system and method based on speech feature extraction, system includes the mobile telephone exchange network and internet of meeting Cloud Server, multiple participant terminals, multiple connection participant terminals and meeting Cloud Server, the meeting Cloud Server includes the comparison module of the memory module of the received pronunciation characteristic signal of a storage member, an extraction module that feature extraction is carried out to real-time phonetic, a standard of comparison phonetic feature signal and real-time phonetic characteristic signal, and the participant terminal includes a microphone.The present invention prestores participant's received pronunciation characteristic signal, and server carries out feature extraction to participant's real-time phonetic during each meeting, analyzes whether its sound is me, if it does not match, the automatic shield participant, it is ensured that the security of conferencing information.
Description
Technical field
The present invention relates to a kind of videoconference participant identification system and method based on speech feature extraction.
Background technology
So-called videoconference, is exactly generally by the use of telephone set as instrument, is opened by the use of telephone wire as carrier
The new conference model of meeting.It is rapid with meeting schedule compared with traditional meeting, it is low-cost without time, territory restriction
The features such as.Compared with the point-to-point telephone service of tradition, functionally, the boundary of 2 sides can only be confined to by breaking call, can be with
Meet more than 3 sides（According to the product of different providers, highest can realize that 300 sides converse at the same time）The ditch that can not be realized with phone
It is logical more smooth, the features such as information is truer, and scope is more extensive.Majority, which is limited, be subject to rate is applied to the daily work of enterprise
In work.In order to realize communication efficiency, information distortion is avoided, videoconference market is rapidly growing in recent years, in various types of enterprises
It is widely used in industry.
But the security of existing videoconference is not high, all use with telephone terminal can add per family；I.e.
Make that there is certain examination outpost of the tax office, its effect also unobvious.
The content of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of videoconference based on speech feature extraction
Participant's identification system and method, server carries out feature extraction to participant's real-time phonetic during each meeting, analyzes it
Whether sound is me, solves the problems, such as that the security of existing telephone conferencing information is not high.
The purpose of the present invention is what is be achieved through the following technical solutions：Videoconference and meeting based on speech feature extraction
Person's identification system, it includes meeting Cloud Server, multiple participant terminals, multiple connection participant terminals and meeting Cloud Server
Mobile telephone exchange network and internet, the meeting Cloud Server includes the received pronunciation characteristic signal of a storage member
Memory module, one the extraction module of feature extraction, a standard of comparison phonetic feature signal and immediately are carried out to real-time phonetic
The comparison module of phonetic feature signal, the participant terminal include a microphone.
The participant terminal includes a host and meeting terminal and at least one participant and meeting terminal.
The participant terminal includes non-intelligent mobile terminal, intelligent mobile terminal and PC terminals, the non intelligent shifting
Dynamic terminal is connected by GSM/CDMA/WCDMA with the first mobile telephone exchange network, and the first mobile telephone exchange network passes through SMTP/SMGP
It is connected with meeting Cloud Server；The intelligent mobile terminal is connected by 2G/3G/TCP.IP with the second mobile telephone exchange network,
Second mobile telephone exchange network passes through TCP/IP and is connected with meeting Cloud Server, and the intelligent mobile terminal also passes through WIFI/
TCP.IP is connected with internet, and internet passes through TCP/IP and is connected with meeting Cloud Server；The PC terminals are by WEB and mutually
Networking connection, internet passes through TCP/IP and is connected with meeting Cloud Server.
The recognition methods of videoconference participant's identification system based on speech feature extraction, it includes following step
Suddenly：
S1：The member of videoconference to be participated in sends membership application；
S2：Host receives membership application, and role's authentication, including following sub-step are carried out to member：
S21：Host receives membership application, and authentication instruction is sent to the member of videoconference to be participated in；
S22：The member of videoconference to be participated in passes through Mike's wind direction meeting Cloud Server and sends real-time phonetic；
S23：Meeting Cloud Server carries out feature extraction to real-time phonetic, and the received pronunciation feature of the member with prestoring is believed
Number it is compared and matches, analyzes whether its sound is me：
（1）If sound mismatches, the meeting Cloud Server automatic shield member, send and notify to the member APP, and tie
Beam；
（2）If Sound Match, enters step S3；
S3：Whether meeting Cloud Server judges member in meeting：
（1）If in meeting, notice result is to host；
（2）If the member is not added into videoconference, notifies all participant members to have member to add in meeting, meeting Cloud Server
Enter, while according in member type synchronous regime to member's mobile phone.
Videoconference participant's personal identification method based on speech feature extraction, further includes a pre-stored voice feature letter
Number step：Before videoconference is participated in, server can prestore participant's received pronunciation characteristic signal all users.
The microphone is mobile phone microphone or External microphone.
The member type includes mobile phone member and APP member.
Described carries according in member type synchronous regime to member's mobile phone including being sent by office side's short message exchange network
Show that short message is prompted to member's mobile phone and cell phone application.
The beneficial effects of the invention are as follows：（1）The present invention prestores participant's received pronunciation characteristic signal, and when each meeting services
Device carries out feature extraction to participant's real-time phonetic, analyzes whether its sound is me, if it does not match, automatic shield should be with
Meeting person, it is ensured that the security of conferencing information；（2）By using meeting Cloud Server so that the present invention can be suitable for synchronous at the same time
Voice conference call and the asynchronous meeting of fragmentation；（3）The present invention is suitable for the cross-reference of multiple terminal, is not limited to one kind.
Brief description of the drawings
Fig. 1 is block diagram of the present invention；
Fig. 2 is the method for the present invention flow chart.
Embodiment
Technical scheme is described in further detail below in conjunction with the accompanying drawings：As shown in Figure 1, it is based on speech feature extraction
Videoconference participant's identification system, it include meeting Cloud Server, multiple participant terminals, it is multiple connection participant terminal
With the mobile telephone exchange network and internet of meeting Cloud Server, the meeting Cloud Server includes the standard of a storage member
The memory module of phonetic feature signal, extraction module, a standard of comparison voice that feature extraction is carried out to real-time phonetic
The comparison module of characteristic signal and real-time phonetic characteristic signal, the participant terminal include a microphone.
The participant terminal includes a host and meeting terminal and at least one participant and meeting terminal.
The participant terminal includes non-intelligent mobile terminal, intelligent mobile terminal and PC terminals, the non intelligent shifting
Dynamic terminal is connected by GSM/CDMA/WCDMA with the first mobile telephone exchange network, and the first mobile telephone exchange network passes through SMTP/SMGP
It is connected with meeting Cloud Server；The intelligent mobile terminal is connected by 2G/3G/TCP.IP with the second mobile telephone exchange network,
Second mobile telephone exchange network passes through TCP/IP and is connected with meeting Cloud Server, and the intelligent mobile terminal also passes through WIFI/
TCP.IP is connected with internet, and internet passes through TCP/IP and is connected with meeting Cloud Server；The PC terminals are by WEB and mutually
Networking connection, internet passes through TCP/IP and is connected with meeting Cloud Server.
As shown in Fig. 2, the recognition methods of videoconference participant's identification system based on speech feature extraction, it is wrapped
Include following steps：
S1：The member of videoconference to be participated in sends membership application；
S2：Host receives membership application, and role's authentication, including following sub-step are carried out to member：
S21：Host receives membership application, and authentication instruction is sent to the member of videoconference to be participated in；
S22：The member of videoconference to be participated in passes through Mike's wind direction meeting Cloud Server and sends real-time phonetic；
S23：Meeting Cloud Server carries out feature extraction to real-time phonetic, and the received pronunciation feature of the member with prestoring is believed
Number it is compared and matches, analyzes whether its sound is me：
（1）If sound mismatches, the meeting Cloud Server automatic shield member, send and notify to the member APP, and tie
Beam；
（2）If Sound Match, enters step S3；
S3：Whether meeting Cloud Server judges member in meeting：
（1）If in meeting, notice result is to host；
（2）If the member is not added into videoconference, notifies all participant members to have member to add in meeting, meeting Cloud Server
Enter, while according in member type synchronous regime to member's mobile phone.
Videoconference participant's personal identification method based on speech feature extraction, further includes a pre-stored voice feature letter
Number step：Before videoconference is participated in, server can prestore participant's received pronunciation characteristic signal all users.
The microphone is mobile phone microphone or External microphone.
The member type includes mobile phone member and APP member.
Described carries according in member type synchronous regime to member's mobile phone including being sent by office side's short message exchange network
Show that short message is prompted to member's mobile phone and cell phone application.
Claims (1)
- A kind of 1. recognition methods of videoconference participant's identification system based on speech feature extraction, it is characterised in that：The corresponding videoconference participant's identification system based on speech feature extraction of the recognition methods, including meeting cloud Server, multiple participant terminals, multiple mobile telephone exchange networks and internet for connecting participant terminal and meeting Cloud Server, it is described Meeting Cloud Server include one storage member received pronunciation characteristic signal memory module, one to real-time phonetic carry out The comparison module of the extraction module of feature extraction, a standard of comparison phonetic feature signal and real-time phonetic characteristic signal, it is described Participant terminal include a microphone；The participant terminal includes a host and meeting terminal and at least one participant and meeting terminal；The participant terminal includes non-intelligent mobile terminal, intelligent mobile terminal and PC terminals, and described is non intelligent mobile whole End is connected by GSM/CDMA/WCDMA with the first mobile telephone exchange network, and the first mobile telephone exchange network passes through SMTP/SMGP and meeting Discuss Cloud Server connection；The intelligent mobile terminal is connected by 2G/3G/TCP.IP with the second mobile telephone exchange network, and second Mobile telephone exchange network passes through TCP/IP and is connected with meeting Cloud Server, and the intelligent mobile terminal also passes through WIFI/TCP.IP It is connected with internet, internet passes through TCP/IP and is connected with meeting Cloud Server；The PC terminals are connected by WEB and internet Connect, internet passes through TCP/IP and is connected with meeting Cloud Server；The recognition methods comprises the following steps：S1：The member of videoconference to be participated in sends membership application；S2：Host receives membership application, and role's authentication, including following sub-step are carried out to member：S21：Host receives membership application, and authentication instruction is sent to the member of videoconference to be participated in；S22：The member of videoconference to be participated in passes through Mike's wind direction meeting Cloud Server and sends real-time phonetic；S23：Meeting Cloud Server carries out feature extraction to real-time phonetic, with the received pronunciation characteristic signal of the member that prestores into Row relatively with matching, analyzes whether its sound is me：（1）If sound mismatches, the meeting Cloud Server automatic shield member, send and notify to the member APP, and terminate；（2）If Sound Match, enters step S3；S3：Whether meeting Cloud Server judges member in meeting：（1）If in meeting, notice result is to host；（2）If the member is not added videoconference, notifies all participant members to have member's addition in meeting, meeting Cloud Server, At the same time according in member type synchronous regime to member's mobile phone；The recognition methods further includes a pre-stored voice characteristic signal step：All users are before videoconference is participated in, service Device can prestore participant's received pronunciation characteristic signal；The microphone is mobile phone microphone or External microphone；The member type includes mobile phone member and APP member；Described is short by the transmission prompting of office side's short message exchange network according to including in member type synchronous regime to member's mobile phone Believe member's mobile phone and cell phone application prompting；By using meeting Cloud Server so that the present invention can be suitable for simultaneous voice videoconference and the asynchronous meeting of fragmentation at the same time View.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510022211.XA CN104618616B (en) | 2015-01-16 | 2015-01-16 | Videoconference participant identification system and method based on speech feature extraction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510022211.XA CN104618616B (en) | 2015-01-16 | 2015-01-16 | Videoconference participant identification system and method based on speech feature extraction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104618616A CN104618616A (en) | 2015-05-13 |
| CN104618616B true CN104618616B (en) | 2018-04-13 |
Family
ID=53152884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510022211.XA Expired - Fee Related CN104618616B (en) | 2015-01-16 | 2015-01-16 | Videoconference participant identification system and method based on speech feature extraction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104618616B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105827616A (en) * | 2016-04-25 | 2016-08-03 | 四川联友电讯技术有限公司 | Video information secure sending and receiving method of fragment asynchronous conference |
| CN107170452A (en) * | 2017-04-27 | 2017-09-15 | 广东小天才科技有限公司 | The Adding Way and device of a kind of electronic meeting |
| CN107993665B (en) * | 2017-12-14 | 2021-04-30 | 科大讯飞股份有限公司 | Method for determining role of speaker in multi-person conversation scene, intelligent conference method and system |
| CN110348011A (en) * | 2019-06-25 | 2019-10-18 | 武汉冠科智能科技有限公司 | A kind of with no paper meeting shows that object determines method, apparatus and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101291239A (en) * | 2008-05-20 | 2008-10-22 | 华为技术有限公司 | Method and apparatus for enhancing effect of meeting |
| KR101681321B1 (en) * | 2009-11-17 | 2016-11-30 | 엘지전자 주식회사 | Method for user authentication, video communication apparatus and display apparatus thereof |
| CN102630004B (en) * | 2012-04-12 | 2015-03-11 | 华为技术有限公司 | Authentication method for video conference and related device |
-
2015
- 2015-01-16 CN CN201510022211.XA patent/CN104618616B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN104618616A (en) | 2015-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10356239B1 (en) | Transcribing audio communication sessions | |
| CN104618616B (en) | Videoconference participant identification system and method based on speech feature extraction | |
| CN104601835A (en) | Face recognition based teleconference and conventioneer identification system and method | |
| US9311920B2 (en) | Voice processing method, apparatus, and system | |
| NO20083109L (en) | Delivery of short messages on networks of type DO and 1x | |
| CN104573460A (en) | Fingerprint recognition based teleconference and participant identity recognition system and method | |
| CN102447782A (en) | Phone terminal capable of presenting phone conversation in conversation in real time | |
| CN104579710B (en) | The asynchronous conference system of fragmentation | |
| CN104580765A (en) | Telephone conference system conventioner off-line reconnection identity authentication method | |
| CN103188411A (en) | VOIP telephone real-time monitoring system and monitoring method based on recording | |
| CN101778485A (en) | Method and device for building circuit switch link of WiFi handheld equipment | |
| CN103067188A (en) | Network phone conference system and implementation method thereof | |
| CN107888544B (en) | A kind of method and system depending on establishing communication between networked terminals and communication apparatus | |
| CN104580231A (en) | Fragmentation asynchronous conference system | |
| CN104579712A (en) | Method for conference member to issue character information in fragmentation asynchronous conference system | |
| CN104618615B (en) | A kind of TeleConference Bridge meeting summary method for pushing based on short message | |
| CN104580778B (en) | The method that the asynchronous conference system conference member of fragmentation issues pictorial information | |
| CN103684970B (en) | The transmission method of media data flow and thin terminal | |
| CN104579715A (en) | High-communication-quality teleconference system and method | |
| CN104469254A (en) | Conference roll-call processing method and device and conference system | |
| CN103581452B (en) | A kind of method and system that videoconference is carried out by cdma mobile terminal | |
| CN104618613A (en) | Method for telephone conference system presenter to shield high-noise participants | |
| CN112583973B (en) | Method for preventing conversation between Bluetooth headset and Bluetooth terminal from entering narrow band | |
| CN102752405A (en) | Conversation system and method between internet and telephone | |
| CN105208233A (en) | Network telephone system capable of prompting incoming call notification and realization method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200922 Address after: Room 412, block B, national advertising industrial park, Beijing East Road, Jiujiang District, Wuhu City, Anhui Province 241000 Patentee after: Song Qinggang Address before: No. 11 Gaopeng Avenue, Chengdu hi tech Development Zone of Sichuan province 610041 Patentee before: SICHUAN UCS COMMUNICATIONS TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201106 Address after: 610000 4 complex building 1325, Tianfu two street, Chengdu high tech Zone, Sichuan Patentee after: SICHUAN JUNCHENG INTERACTIVE TECHNOLOGY Co.,Ltd. Address before: Room 412, block B, national advertising industrial park, Beijing East Road, Jiujiang District, Wuhu City, Anhui Province 241000 Patentee before: Song Qinggang |
|
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180413 Termination date: 20220116 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |