CN115623132A - Intelligent conference system - Google Patents

Intelligent conference system Download PDF

Info

Publication number
CN115623132A
CN115623132A CN202211442190.3A CN202211442190A CN115623132A CN 115623132 A CN115623132 A CN 115623132A CN 202211442190 A CN202211442190 A CN 202211442190A CN 115623132 A CN115623132 A CN 115623132A
Authority
CN
China
Prior art keywords
name
option
user
speaker
conference
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
Application number
CN202211442190.3A
Other languages
Chinese (zh)
Other versions
CN115623132B (en
Inventor
刘丹
汤跃忠
杨静波
陈龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Third Research Institute Of China Electronics Technology Group Corp
Beijing Zhongdian Huisheng Technology Co ltd
Original Assignee
Third Research Institute Of China Electronics Technology Group Corp
Beijing Zhongdian Huisheng Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Third Research Institute Of China Electronics Technology Group Corp, Beijing Zhongdian Huisheng Technology Co ltd filed Critical Third Research Institute Of China Electronics Technology Group Corp
Priority to CN202211442190.3A priority Critical patent/CN115623132B/en
Publication of CN115623132A publication Critical patent/CN115623132A/en
Application granted granted Critical
Publication of CN115623132B publication Critical patent/CN115623132B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/53—Centralised arrangements for recording incoming messages, i.e. mailbox systems
    • H04M3/5322—Centralised arrangements for recording incoming messages, i.e. mailbox systems for recording text messages
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/06—Decision making techniques; Pattern matching strategies
    • G10L17/14—Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/22—Interactive procedures; Man-machine interfaces
    • 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
    • H04M3/563—User guidance or feature selection
    • H04M3/566—User guidance or feature selection relating to a participants right to speak
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The invention discloses an intelligent conference system. The intelligent conference system includes: the text display box is used for displaying a conference record, and the conference record is provided with a plurality of marks for distinguishing speeches corresponding to different speakers; each mark corresponds to one name setting module, and the name setting module is set to pop up an option box when a user executes a first trigger action; the option box comprises a plurality of name options which are suitable for being triggered by a second trigger action of the user, and when a certain name option is triggered, the name option replaces the corresponding mark of the option box. By adopting the invention, the name of the speaker can be set quickly, the early voiceprint recording step is saved, and the working efficiency is greatly improved. The text can be corresponding to the name of the speaker in time during subsequent voice recognition, and the name of the speaker can be corrected at any time before, during or after the conference is started and when the problem of machine recognition is found, so that the voiceprint and the name can be matched and corrected.

Description

Intelligent conference system
Technical Field
The invention relates to the technical field of conference recording, in particular to an intelligent conference system.
Background
The conference system applies the voice recognition technology, and can convert voice into characters to form a conference record. The conference system can usually distinguish different speakers according to a microphone array or a voiceprint recognition technology, when one speaker starts to talk, a mark is added in front of the content of the talk by the intelligent conference system, such as 'speaker 1' and 'speaker 2', but the mark cannot directly correspond to the name of the person, the memory load of a user is increased in the process of arranging the summary of the conference, the speakers cannot be quickly positioned, the workload of arranging the conference records is large, and the efficiency is low.
In the related art, in order to realize the purpose of matching the speech with the name, a user needs to input a section of speech in advance according to a preset text, input the name and complete voiceprint input, namely voiceprint acquisition is carried out on all participants in advance.
Disclosure of Invention
The embodiment of the invention provides an intelligent conference system, which is used for solving the problem of low feasibility of matching names with conference records in the prior art.
The intelligent conference system according to the embodiment of the invention comprises:
the system comprises a text display frame and a conference recording display frame, wherein the text display frame is used for displaying a conference record, and the conference record is provided with a plurality of marks used for distinguishing speeches corresponding to different speakers;
the name setting modules correspond to the marks respectively, and are arranged to pop up an option box when a user executes a first trigger action;
the option box comprises a plurality of name options which are suitable for being triggered by a second trigger action of the user, and when a certain name option is triggered, the name option replaces the corresponding mark of the option box.
According to some embodiments of the invention, the intelligent conference system further comprises:
and the participant function module is used for inputting and storing names of participants and synchronizing the names of the participants to option boxes of all the name setting modules so as to form name options in the option boxes.
According to some embodiments of the invention, any utterance in the conference recording is suitable for being selected by a third trigger action of the user;
after the user selects a certain utterance, the user is suitable for triggering any one of the names of the participants listed in the participant function module through a fourth trigger action so as to display the names of the participants before the utterance.
According to some embodiments of the invention, any one of the names listed in the participant function module is arranged to set the name setting module for the utterance while the name of the participant is displayed before the utterance.
According to some embodiments of the invention, any utterance in the conference recording is displayed when selected differently from other unselected utterances.
According to some embodiments of the invention, the name option in the option box is generated by a user entering a store in the option box.
According to some embodiments of the invention, the mark comprises a moderator mark and a speaker mark;
the name setting module comprises a host name setting module and a speaker name setting module;
all the host marks correspond to one host name setting module, and each speaker mark corresponds to one speaker name setting module.
According to some embodiments of the present invention, the option box of the speaker name setting module further comprises a current option and a full-text option, both the current option and the full-text option being adapted to be triggered by a fifth trigger action of the user;
when the user triggers the current option and a certain name option, replacing the mark corresponding to the option frame with the name option;
and when the full-text option and a certain name option are triggered by a user, uniformly replacing the same mark in the conference record as the mark corresponding to the option box with the name option.
By adopting the embodiment of the invention, the names of speakers can be quickly set by using a proper man-machine operation mode before the conference starts, in the process and after the conference is finished, so that the voice print recording step in the early stage is omitted, and the working efficiency is greatly improved. The text can be corresponding to the name of the speaker in time during subsequent voice recognition, and the name of the speaker can be corrected at any time before, during or after the conference is started and when the problem of machine recognition is found, so that the voiceprint and the name can be matched and corrected.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. In the drawings:
FIG. 1 is a schematic diagram of a name input interface of a participant function module in an embodiment of the invention;
FIG. 2 is a schematic diagram of a name display interface of a function module of a participant according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a local interface of an intelligent conference system in an embodiment of the invention;
FIG. 4 is a schematic diagram of a local interface of an intelligent conference system in an embodiment of the invention;
FIG. 5 is a schematic diagram of a local interface of an intelligent conference system in an embodiment of the invention;
fig. 6 is a schematic diagram of a local interface of the intelligent conference system in the embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Additionally, in some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
The intelligent conference system according to the embodiment of the invention comprises:
and the text display box is used for displaying a conference record, and the conference record is provided with a plurality of marks for distinguishing speeches corresponding to different speakers.
The conference system applies the voice recognition technology, and can convert voice into characters to form a conference record. At present, a conference system can usually distinguish different speakers according to a microphone array or a voiceprint recognition technology, and each time one speaker starts to speak, the conference system adds a mark, such as "speaker 1" or "speaker 2", before the speaking content to distinguish the speakers corresponding to the speaking. Each tag may correspond to one or more utterances, and two adjacent tags may not be the same, but two non-adjacent tags may be the same, for example, the tags may be "speaker 1", "speaker 2", and "speaker 1" in sequence.
And each mark corresponds to one name setting module, and the name setting modules are set to pop up option boxes when a user executes a first trigger action.
The option box comprises a plurality of name options which are suitable for being triggered by a second trigger action of the user, and when a certain name option is triggered, the name option replaces the corresponding mark of the option box.
The first trigger action may be a preset action, such as a single click, a double click, or a right click, and is not specifically limited herein. Similarly, the second trigger action may also be a preset action such as a single click, a double click, or a right click, and the second trigger action is not specifically limited in the same way and may be set according to the habit of the user.
It will be appreciated that the name setting module pops up an option box whenever the user triggers the name setting module. In other words, the user executing the first trigger action is equivalent to issuing a control instruction to the name setting module, and the name setting module executes the action of popping up the option box according to the control instruction. The option frame is provided with a plurality of name options which are set in advance, the second trigger action executed by the user is equivalent to sending an instruction to the name setting module, and the name setting module further executes the action of modifying the corresponding mark into the selected name according to the instruction.
Whole operation process is simple, and the user neither need record in advance, also does not need the artificial speaker name of setting up for every speech next in later stage yet, very big promotion conference system's intelligence and feasibility, can satisfy the record demand of current meeting to guarantee the accuracy of meeting record.
The invention can solve the problem that how to quickly match and store the speeches and the names in the intelligent conference system, and is convenient for the system to display the correct name of the speaker according to the input voice. The invention can realize the voiceprint storage with name labels only by inputting names of the participants. The early voiceprint recording step is omitted, and the working efficiency is greatly improved. The text can also be timely mapped to the speaker name during subsequent speech recognition. And before, during or after the conference, when the problem of machine identification is found, the name of the speaker can be corrected at any time, and the matching and the modification of the voiceprint and the name can be carried out. The moderator name may also be selected by pulling down a menu. After the conference is finished, a text file containing information such as a participant, a host, a speaker, speech content and the like can be exported for backtracking of the conference and summary arrangement of the conference.
On the basis of the above-described embodiment, various modified embodiments are further proposed, and it is to be noted herein that, in order to make the description brief, only the differences from the above-described embodiment are described in the various modified embodiments.
According to some embodiments of the invention, the intelligent conference system further comprises:
and the participant function module is used for inputting and storing names of participants and synchronizing the names of the participants to the option boxes of all the name setting modules so as to form name options in the option boxes. It will be appreciated that the participant function module has a name entry interface through which a user can enter names of participants, and the participant function module can save the names of the participants and synchronize those names to all name setting modules to form name options in the option boxes of all name setting modules. Therefore, the situation that the user sets the option boxes of the name setting module independently one by one is avoided, the flow is simplified, and the efficiency is improved. For example, as shown in FIG. 1, a schematic diagram of a name entry interface is shown through which a user may enter names of participants. After a user inputs names of participants through the name input interface and triggers a storage button arranged on the name input interface, the participant function module can be automatically adjusted to a name display interface from the name input interface, fig. 2 is a name display interface schematic diagram, and in the interface, each name is constructed into a unit module which can be triggered.
According to some embodiments of the invention, any utterance in the conference recording is suitable for being selected by a third trigger action of the user;
after the user selects a certain utterance, the user is suitable for triggering any one of the names of the participants listed in the participant function module through a fourth trigger action so as to display the names of the participants before the utterance. The fourth trigger action may be a preset action, such as a single click, a double click, or a right click, and is not specifically limited herein.
Therefore, when the conference system has recognition errors, two speakers actually speak, but the conference system recognizes the speech of one speaker, the user can correct the speech through the mechanism, so that the accuracy of conference recording is ensured, and bugs existing in the recognition mechanism are compensated.
According to some embodiments of the invention, any one of the names listed in the participant function module is arranged to set the name setting module for the utterance while the name of the participant is displayed before the utterance. Thus, after the name is modified independently for a certain utterance, the user can modify the name again through the name setting module when finding the setting error of the user later. For example, as shown in fig. 5 and 6, the word "AAAAAAAA" is spoken. The utterance "recognized as" speaker 2 "is actually the utterance" korean XX ", and therefore, the user can modify it by adopting the mechanism of the present invention.
According to some embodiments of the invention, any utterance in the conference recording is displayed when selected differently from other unselected utterances. For example, selected utterances may be displayed in a font color that is distinct from other unselected utterances, as shown in fig. 5, where selected utterances are displayed in gray and unselected utterances are uniformly black. Of course, other ways of highlighting may be used, such as bolding, tilting, font shading, and the like, and all ways are not listed here, as long as the selected utterance can be distinguished from the unselected utterances.
According to some embodiments of the invention, the name option in the option box is generated by a user entering a store in the option box. It is to be understood that the name options in the option box of the name setting module may be configured in advance by the user in the name setting module. For example, the option box of each name setting module may be provided with a configuration window for facilitating the user to add a name, and the name setting module may set it as a name option in the option box according to the user's input.
According to some embodiments of the invention, the marks comprise a moderator mark and a speaker mark;
the name setting module comprises a moderator name setting module and a speaker name setting module;
all the host marks correspond to one host name setting module, and each speaker mark corresponds to one speaker name setting module.
For example, as shown in FIG. 3, an inverted triangle placed next to the word "moderator" sets the module for the moderator's name. As shown in fig. 4, an inverted triangle placed next to the word "speaker 2" is a speaker name setting module.
According to some embodiments of the present invention, the option box of the speaker name setting module further comprises a current option and a full-text option, both the current option and the full-text option being adapted to be triggered by a fifth trigger action of the user;
when the user triggers the current option and a certain name option, replacing the mark corresponding to the option frame with the name option;
when the user triggers the full text option and a certain name option, the same mark in the conference record corresponding to the option box is uniformly replaced by the name option.
For example, as shown in fig. 4, the current option and the full-text option may be selected alternatively by the user through a fifth trigger action trigger, and then the user triggers the name option to complete name replacement.
Therefore, the user can uniformly replace all the same marks through full-text options, and the working efficiency is greatly improved. Meanwhile, the user can independently replace a certain name through the current option, so that the condition of identification error can be independently modified, and the accuracy of the conference record is improved.
The intelligent conference system according to the present invention will be described in detail in one specific embodiment with reference to the accompanying drawings. It is to be understood that the following description is only exemplary in nature and should not be taken as a specific limitation on the invention.
The intelligent conference system is not only a voice recognition recording tool, but also a tool for assisting in arranging conference summary, and the intelligent conference system is designed as a whole task flow. The invention designs a function of storing voiceprint information only by inputting the name of a speaker in the conference based on the current voice recognition technology, voiceprint recognition technology and microphone array technology. This mode can save the time of vocal print entering before the meeting, can store vocal print information sooner, makes the speech recognition text correspond the speaker name fast, when deriving the meeting brief and meeting reprint content simultaneously, directly derives moderator, participant, speaker information, makes the meeting brief arrangement efficiency show the improvement.
In detail, the intelligent conference system according to the embodiment of the present invention includes: the system comprises a participant function module, a text display box and a plurality of name setting modules.
As shown in fig. 1 and 2, the participant function module is used for inputting and storing names of participants. The names of the participants can be presented on the display interface of the functional module of the participants in the form of unit modules for the operation of users.
As shown in fig. 4, a text display box is used to display the meeting minutes. The conference system can distinguish different speakers according to a microphone array or a voiceprint recognition technology, and when one speaker starts speaking, the conference system converts the speaker into a text-form speech and marks the speech before, such as 'speaker 1' and 'speaker 2', so as to distinguish the speakers corresponding to the speech.
As shown in fig. 3-6, a name setting module is located next to each tag. The marks comprise a moderator mark and a speaker mark; the name setting module comprises a moderator name setting module and a speaker name setting module; all host marks correspond to one host name setting module, and each speaker mark corresponds to one speaker name setting module. For example, an inverted triangle next to "speaker 2". An inverted triangle next to the "presenter".
As shown in fig. 4, the name setting module is arranged to pop up an option box when the user performs the first trigger action; the option box includes a plurality of name options adapted to be triggered by a second triggering action of the user. The participant function module may synchronize the names of the participants to the option boxes of all name setting modules to form name options in the option boxes. When a name option is triggered, the name option replaces the mark corresponding to the option box.
As shown in fig. 4, the option box of the speaker name setting module further includes a current option and a full-text option, and both the current option and the full-text option are suitable for being triggered by a fifth trigger action of the user; when a user triggers a current option and a certain name option, replacing a mark corresponding to the option frame with the name option; when the user triggers the full text option and a certain name option, the name option is uniformly replaced by the same mark in the conference record as the mark corresponding to the option box.
As shown in fig. 5 and 6, any utterance in the conference record is suitable for being selected by the third trigger action of the user; after the user selects a certain utterance, the user is suitable for triggering any one of the names of the participants listed in the participant function module through a fourth trigger action so as to display the names of the participants before the utterance. Any one of the names listed in the participant function module is set to be displayed before the utterance, and a name setting module is set for the utterance at the same time. Any utterance in the conference recording is displayed when selected differently from other unselected utterances.
In the process of using the intelligent conference system of the embodiment of the invention, a user can input names of participants in the text boxes of the participant function modules, wherein each line contains one participant, as shown in fig. 1. After the input is finished, the 'save' button is clicked, namely, the storage of the names of the participants is finished, the function modules of the participants are changed into button types, and as shown in fig. 2, each name of the participants is a button. These names may be synchronized to all name setting modules at the same time. Clicking a button of the inverted triangle beside the host to pop up a pull-down menu, and selecting the name of the participant just stored in the pull-down menu to complete the change of the name of the host, as shown in fig. 3. Clicking the inverted triangle button beside the speaker in the conference record can also pop up a pull-down menu, selecting the name of the participant in the pull-down menu, and selecting to modify the current speaker or the full-text speaker, as shown in fig. 4. And selecting the corresponding relation between the voiceprint and the name which is not influenced by the current speaker, storing the voiceprint by selecting the full-text speaker, and calling the name of the voiceprint contrast when the next voiceprint matching is successful. Clicking the text content of the voice recognition, when the sentence words turn grey, clicking the left participant name button, as shown in fig. 5, starting another line of the current text, and displaying the name of the participant above the words, as shown in fig. 6. After the transfer is finished, the conference content can be exported, and information such as names of participants and names of hosts can be synchronously exported.
By adopting the embodiment of the invention, after the participants are input in batch and stored, the names of the participants appear in a button form and can be used as functional buttons when the roles are inserted. The speaker name may be modified by the names of the participants saved in the drop down menu. The moderator name may be modified by the names of the participants saved in the drop down menu. When the name of the speaker is modified, the current or full text can be selected to be modified, and when the full text is selected, the voiceprint and the name are matched and stored. The whole process can be completed only by simple operation of a user, and the working efficiency is high and the intelligent degree is high.
It should be noted that the above-mentioned embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention, and those skilled in the art can make various modifications and changes. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
In addition, those matters not described in detail in the present specification are well known to those skilled in the art.

Claims (8)

1. An intelligent conferencing system, comprising:
the system comprises a text display frame and a conference recording display frame, wherein the text display frame is used for displaying a conference record, and the conference record is provided with a plurality of marks used for distinguishing speeches corresponding to different speakers;
a plurality of name setting modules, each of the marks corresponding to one of the name setting modules, the name setting modules being configured to pop up an option box when a user performs a first trigger action;
the option box comprises a plurality of name options which are suitable for being triggered by a second trigger action of the user, and when a certain name option is triggered, the name option replaces the corresponding mark of the option box.
2. The intelligent conferencing system of claim 1, wherein the intelligent conferencing system further comprises:
and the participant function module is used for inputting and storing names of participants and synchronizing the names of the participants to the option boxes of all the name setting modules so as to form name options in the option boxes.
3. The intelligent conference system according to claim 2, wherein any utterance in the conference recording is adapted to be selected by a third triggering action of the user;
after the user selects a certain utterance, the user is suitable for triggering any one of the names of the participants listed in the participant function module through a fourth trigger action so as to display the names of the participants before the utterance.
4. The intelligent conferencing system of claim 3, wherein any listed participant name in the participant function module is set to the name setting module for the utterance while the participant name is displayed prior to the utterance.
5. The intelligent conferencing system of claim 3, wherein any utterance in the conference recording is displayed when selected differently from other unselected utterances.
6. The intelligent conferencing system of claim 1, wherein the name option in the option box is generated by a user entering a store in the option box.
7. The intelligent conferencing system of claim 1, wherein the tags include a moderator tag and a speaker tag;
the name setting module comprises a moderator name setting module and a speaker name setting module;
all the host marks correspond to one host name setting module, and each speaker mark corresponds to one speaker name setting module.
8. The intelligent conferencing system of claim 7, wherein the option box of the speaker name setting module further comprises a current option and a full-text option, both the current option and the full-text option being adapted to be triggered by a fifth triggering action of the user;
when the user triggers the current option and a certain name option, replacing the mark corresponding to the option frame with the name option;
and when the full-text option and a certain name option are triggered by a user, uniformly replacing the same mark in the conference record as the mark corresponding to the option box with the name option.
CN202211442190.3A 2022-11-18 2022-11-18 Intelligent conference system Active CN115623132B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211442190.3A CN115623132B (en) 2022-11-18 2022-11-18 Intelligent conference system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211442190.3A CN115623132B (en) 2022-11-18 2022-11-18 Intelligent conference system

Publications (2)

Publication Number Publication Date
CN115623132A true CN115623132A (en) 2023-01-17
CN115623132B CN115623132B (en) 2023-04-04

Family

ID=84879085

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211442190.3A Active CN115623132B (en) 2022-11-18 2022-11-18 Intelligent conference system

Country Status (1)

Country Link
CN (1) CN115623132B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101661512A (en) * 2009-09-25 2010-03-03 万斌 System and method for identifying traditional form information and establishing corresponding Web form
US8781841B1 (en) * 2011-06-07 2014-07-15 Cisco Technology, Inc. Name recognition of virtual meeting participants
CN106486116A (en) * 2015-08-26 2017-03-08 重庆西线科技有限公司 A kind of online generation method of on-the-spot meeting summary
CN106657865A (en) * 2016-12-16 2017-05-10 联想(北京)有限公司 Method and device for generating conference summary and video conference system
CN109388701A (en) * 2018-08-17 2019-02-26 深圳壹账通智能科技有限公司 Minutes generation method, device, equipment and computer storage medium
CN110677614A (en) * 2019-10-15 2020-01-10 广州国音智能科技有限公司 Information processing method, device and computer readable storage medium
CN114373464A (en) * 2021-12-31 2022-04-19 Oppo广东移动通信有限公司 Text display method and device, electronic equipment and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101661512A (en) * 2009-09-25 2010-03-03 万斌 System and method for identifying traditional form information and establishing corresponding Web form
US8781841B1 (en) * 2011-06-07 2014-07-15 Cisco Technology, Inc. Name recognition of virtual meeting participants
CN106486116A (en) * 2015-08-26 2017-03-08 重庆西线科技有限公司 A kind of online generation method of on-the-spot meeting summary
CN106657865A (en) * 2016-12-16 2017-05-10 联想(北京)有限公司 Method and device for generating conference summary and video conference system
CN109388701A (en) * 2018-08-17 2019-02-26 深圳壹账通智能科技有限公司 Minutes generation method, device, equipment and computer storage medium
CN110677614A (en) * 2019-10-15 2020-01-10 广州国音智能科技有限公司 Information processing method, device and computer readable storage medium
CN114373464A (en) * 2021-12-31 2022-04-19 Oppo广东移动通信有限公司 Text display method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN115623132B (en) 2023-04-04

Similar Documents

Publication Publication Date Title
RU2379767C2 (en) Error correction for speech recognition systems
US20220059096A1 (en) Systems and Methods for Improved Digital Transcript Creation Using Automated Speech Recognition
US9711145B2 (en) Word-level correction of speech input
US20180144747A1 (en) Real-time caption correction by moderator
US20180143956A1 (en) Real-time caption correction by audience
US7912700B2 (en) Context based word prediction
JP4987623B2 (en) Apparatus and method for interacting with user by voice
US8290775B2 (en) Pronunciation correction of text-to-speech systems between different spoken languages
US20070100619A1 (en) Key usage and text marking in the context of a combined predictive text and speech recognition system
JP3880163B2 (en) Method and system for displaying a variable number of alternative words during speech recognition
US6839669B1 (en) Performing actions identified in recognized speech
US20090326938A1 (en) Multiword text correction
US20180060282A1 (en) User interface for dictation application employing automatic speech recognition
US7720316B2 (en) Constraint-based correction of handwriting recognition errors
US7243069B2 (en) Speech recognition by automated context creation
US20120016671A1 (en) Tool and method for enhanced human machine collaboration for rapid and accurate transcriptions
CN109817210B (en) Voice writing method, device, terminal and storage medium
EP3779971A1 (en) Method for recording and outputting conversation between multiple parties using voice recognition technology, and device therefor
CN101840300A (en) Methods and systems for receiving input of text on a touch-sensitive display device
WO2003025904A1 (en) Correcting a text recognized by speech recognition through comparison of phonetic sequences in the recognized text with a phonetic transcription of a manually input correction word
US11228681B1 (en) Systems for summarizing contact center calls and methods of using same
US20080002886A1 (en) Adapting a neural network for individual style
JPH11161464A (en) Japanese sentence preparing device
CN109215661A (en) Speech-to-text method, apparatus equipment and storage medium
CN115623132B (en) Intelligent conference system

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
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Liu Dan

Inventor after: Tang Yuezhong

Inventor after: Yang Jingbo

Inventor after: Chen Long

Inventor after: Wang Lei

Inventor before: Liu Dan

Inventor before: Tang Yuezhong

Inventor before: Yang Jingbo

Inventor before: Chen Long