CN109147791A - A kind of shorthand system and method - Google Patents
A kind of shorthand system and method Download PDFInfo
- Publication number
- CN109147791A CN109147791A CN201710461300.3A CN201710461300A CN109147791A CN 109147791 A CN109147791 A CN 109147791A CN 201710461300 A CN201710461300 A CN 201710461300A CN 109147791 A CN109147791 A CN 109147791A
- Authority
- CN
- China
- Prior art keywords
- data
- server
- voice
- text
- label
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/04—Segmentation; Word boundary detection
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/02—Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers
- G11B27/031—Electronic editing of digitised analogue information signals, e.g. audio or video signals
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
- G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
- G11B27/10—Indexing; Addressing; Timing or synchronising; Measuring tape travel
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
A kind of shorthand system, comprising: request is identified to receiving voice data on response to network, is converted to the server of lteral data;For acquiring voice data and with networked data transmission unit by the interview device of voice data transmission to the server;For communicating to connect the server, and the editing device for receiving the text complex data with voice from the server and it being handled, wherein, the complex data includes the lteral data and voice data for having segmentation markers between time sequence saves, when showing that editor lteral data while showing the segmentation markers over the display, when detecting that the segmentation markers choose click by the pointer device, corresponding voice data is read from complex data packet and is reset with sound by loudspeaker so as to text checking treatment.Implement system of the invention, provide a kind of approach being quickly modified to converting text mistake, solves the problems, such as the low efficiency, at high cost of desk checking.
Description
Technical field
The present invention relates to speech recognition technologies, and in particular to a kind of pair of speech recognition result, which is modified, to be allowed to be combined into
A kind of feasible shorthand system and method.
Background technique
Speech recognition is exactly the process the speech recognition of people at text, since the pronunciation of people may inaccuracy, it is also possible to
Due to other problems such as playback environ-ments, so that the result of speech recognition is directly brought as shorthand result, there may be many mistakes
Accidentally.In the case where there is identification error situation, if for identifying text user no longer scene or not remembeing the voice of speaker
In the case where, it can not identify and correct the identification of these mistakes.When the capacity of shorthand is big, the case where the cacoepy of speaker
Under, it can not fast obtain the shorthand result that correctly can be used.
Summary of the invention
The invention solves technical problems to be, provides a kind of pair of speech recognition result and carries out off line or/and non-at-scene people
The modified shorthand system and method for member, system and method through the invention, the tradition shorthand for allowing machine transcription to be possibly realized
Alternative.
Above-mentioned technical problem of the present invention solves in this way, constructs a kind of shorthand system, comprising:
Request is identified to receiving voice data on response to network, is converted to the server of lteral data;
For acquiring voice data and with networked data transmission unit by voice data transmission to institute with voice collection device
State the interview device of server;
For communicating to connect the server, and the text complex data with voice and to it is received from the server
The editing device handled is connected with display, pointer device and loudspeaker, wherein the complex data includes time sequence
There are the lteral data and voice data of segmentation markers between saving, edits lteral data when show over the display while showing institute
Segmentation markers are stated, when detecting that the segmentation markers choose click by the pointer device, the reading pair from complex data packet
The voice data answered simultaneously is reset with sound by loudspeaker so as to text checking treatment.
In the above-mentioned shorthand system of the present invention, the server is unit multiple according to the time span that raw tone is recorded
It closes and generates label in data, the time span was greater than 2 seconds, less than 30 seconds.
In the above-mentioned shorthand system of the present invention, the server goes out generated text/character according in speech recognition
It is divided into be spaced on complex data between length and generates label, be divided into 5-30 character between the length.
In the above-mentioned shorthand system of the present invention, the server is in the speech interval of original recording, in complex data pair
It answers and generates label on time point.
In the above-mentioned shorthand system of the present invention, each interview device (200) has an ID, and each editing device has one
ID records its ID and corresponding editing device ID on the server for the interview device of each registration.
According to a kind of stenography method provided by the invention, comprising the following steps:
Voice signal is acquired, server is transmitted to;
Server will receive voice signal and identify in chronological order, generate lteral data;
According to predetermined way on the voice text data of generation setting flag, while in the position of corresponding lteral data
Upper setting flag, there is unique corresponding relation between the two;
Download from a server lteral data and voice data comprising tape label;
The lteral data of tape label is shown over the display;
When label is by pointing operation, one section of voice is reset from correspondence markings from voice data and is come out from loudspeaker;
Lteral data is edited and modified according to the voice of playback.
In the above-mentioned stenography method of the present invention, the predetermined way is the time that the server is recorded according to raw tone
Length is that unit generates label on complex data, and the time span was greater than 2 seconds, less than 30 seconds.
In the above-mentioned stenography method of the present invention, the predetermined way is the server according to produced by speech recognition goes out
Text/character length between be divided into be spaced on complex data and generate label, be divided into 5-30 character between the length.
In the above-mentioned stenography method of the present invention, the predetermined way is speech interval of the server in original recording
In, it is corresponded in complex data and generates label on time point.
In the above-mentioned stenography method of the present invention, each interview device has an ID, and each editing device has an ID, in institute
It states on server, records its ID and corresponding editing device ID for the interview device of each registration.
Implement shorthand system and method provided by the invention, overcomes manually hearing memory of the existing technology and carry out
In time the problem of modified at high cost, low efficiency, a kind of approach being quickly modified to converting text mistake is provided, in language
Sound identification it cannot be guaranteed that 100% it is correct under the premise of, solve the problems, such as the low efficiency, at high cost of desk checking.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of shorthand system first embodiment of the present invention;
Fig. 2 is the structural schematic diagram of second of terminal device 300 in present invention shorthand system embodiment;
Specific embodiment
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
In the embodiment that Fig. 1 shows present system, comprising: server 100 can be the cloud service on network
Device receives voice number to from the first terminal device 200 for requesting on response to network from the first terminal device 200
According to speech recognition is carried out, provides voice data to pattern-recognition and be converted to lteral data, wherein this conversion process is preset
The languages of good voice data and the languages of lteral data, languages are not constituted simultaneously and are converted into separately from a kind of voice data of language
A kind of translation process of the lteral data of voice.The present embodiment only considers that the voice data of language of the same race is converted to lteral data
Process, for server, what is inputted from the first terminal equipment in communication is from the language for connecting the first terminal device 200
Sound data carry out speech recognition to the voice data received and generate text/character data, and in the present system, server 100 can
Recognition result to be stored on cloud server, the request of second of terminal device 300 is responded, to second of terminal device
The data of 300 transmission further include the primary voice data by label other than including identification/shorthand formation lteral data.
In the present embodiment of such as Fig. 1, the first terminal device 200 can be a kind of interview device, this interview device
200 include the networked data transmission unit 210 communicated to connect with server 100, the microphone 220 for acquiring shorthand voice, back
It scape noise reduction processing unit 250, DSP compress speech markers processing unit 240 and connects and controls networked data transmission unit 210
With the Audio Processing Unit 230 of microphone 220, processing unit 230 includes or external voice memory unit.In other words, device is interviewed
Processing unit be used for by microphone 220 acquire by background noise reduction and the voice data of DSP compression processing 250 by networked data
Transmission unit 210 passes through network communication mode for voice data transmission to preset server 100.
In the present embodiment, second of terminal device 300 can be editing device, this editing device 300 such as Fig. 2 institute
Show, contains or be connected with display 310, pointer device 320 and loudspeaker 330 and connection control aforementioned display device 310, gives directions
Equipment 320, loudspeaker 330, networked data transmission unit 340 processing unit 350, wherein pointer device 320 and display
310 can be combined into touch screen, apply on portable terminal;When being applied to non-portable device, indication/input equipment 320 can be with
It is Genius mouse and keyboard, wherein networked data transmission unit 340 is for wirelessly communicating connected reference server 100.In other words,
Processing unit 350 in editing device 300 is used to communicate to connect server 100 by networked data transmission unit 340, and from institute
State on server 100 receive the text complex data with voice and can to the lteral data shown on display 310 by give directions/
Input equipment 340 carries out editing and processing, and modified lteral data is saved, and is stored in processing unit 350 and includes or external
In ability storage unit.
In the above embodiment of the present invention, interview device 200 is sent after connecting server 100 for acquiring voice data
Voice data is to server 100, and the language data that 100 pairs of server interview devices 200 acquire identifies, the text that will identify that
Digital data and voice data are combined into complex data, and editing device 300 is waited to download.Since server 100 is to from interview dress
The speech recognition for setting 200 voice data is automatically processed by server 100, without desk checking, lteral data and existing
Record under voice data or there are mistakes.In the present embodiment, the lteral data that server 100 identifies is by editing device
300 carry out desk checking, and specifically, editing device 300 is multiple from the downloading of server 100 by networked data transmission unit 340
Data are closed, text/character data in complex data is shown on the display 310 of editing device 300, present system
Core feature is on display 310 other than showing text/character itself, can also be in text/character of the bunchiness of display
Middle distribution shows marker character, when user has found mistake or unclear and coherent text, can be clicked and be corresponded to by pointer device 320
The marker character of position, herein, processing unit 350 recall the phonological component in complex data, are reset accordingly by loudspeaker 330
Voice allows the verifier of editing device 300 to carry out manual amendment to the file of marker field according to the voice of playback and edits, realizes just
The shorthand amendment of benefit and perfect, entire text/character check is completed, and is saved up to the stenograph Jing Guo desk checking.
Server 100 provide complex data in, including time sequence save between have segmentation markers lteral data and
Voice data, when showing editor's lteral data display segment label simultaneously on 300 display 310 of editing device, when detecting
The segmentation markers are read from complex data packet and are corresponded to by when click is chosen in point touching on the pointer device such as mouse or touch screen
Voice data and reset with sound so as to text checking treatment by loudspeaker 330.
In second embodiment of the invention, editing device 300 can be one on smart phone with interview device 200
APP is realized, at this point, microphone 220, loudspeaker 330 are exactly microphone and loudspeaker on smart phone, is interviewed in device 200
The networked data transmission unit 340 of networked data transmission unit 210 and editing device 300 can be all the communication on smart phone
Module, for example, local networked data transmission unit WiFi or 3G or 4G mobile communication module.The display 310 of editing device 300
It is realized with indication/input equipment 320 by the touch screen on smart phone.In other words, 350 He of processing unit of editing device 300
The function to be realized of processing unit 230 of interview device 200 is realized by the APP in smart phone.
In another embodiment, the time span that server can record according to raw tone is unit multiple
It closes and generates label in data, for example, an additional label every 10 seconds;It can also go out according in speech recognition, the text of generation/
The length of character is to be spaced on complex data to generate label, for example, the additional label of every 10 text/characters;It is another
The mode for generating label is label to be generated on complex data, for example, people's meeting when speaking in the speech interval of original recording
There is interval, label can be added when in certain intervals without sound on complex data.
In another embodiment of the invention, each interview device 200 has an ID, and each editing device 300 has one
ID, on server 100, the interview device for each registration records its ID and allows the corresponding editing device ID of downloading.
In this manner it is ensured that the safety of shorthand content.
Stenography method of the present invention in embodiment, comprising the following steps:
Voice signal is acquired by one or more microphones 220, after collecting voice signal progress background noise reduction process
Server is transmitted to by networked data transmission unit;
Server 100 will receive voice signal and carry out speech recognition in chronological order, generate lteral data;
According to predetermined way on the voice text data of generation setting flag, while in the position of corresponding lteral data
Upper setting flag has unique corresponding relation between the two, wherein the time label can by the DSP processing unit in interview device into
Row setting;
Editing device 300 downloads lteral data and voice data comprising tape label from server 100;
The lteral data of tape label is shown on display 310, at this point it is possible on text direction of travel uniformly or not
The label of such as loudspeaker figure is equably set, is clicked convenient for pointer device;
When seeming the text strings of logic error or meaning mistake, the label of a nearest such as loudspeaker is referred to
When point device 320 (mouse or touch screen) pointing operation, program can be right from voice data corresponding to the signified wrong text strings of label
It answers mark to reset one section of voice, is come out from the playback of loudspeaker 330;
When user hears recording, lteral data can be edited and be modified according to the voice of playback, not caught such as,
It can again tap on, repetition is listened, and help modifies to text.
After text modification is correct, cloud synchronization can be carried out or/and cloud is shared.
Wherein, predetermined way is unit on complex data one is the time span that server is recorded according to raw tone
Label is generated, time span is greater than 2 seconds, and less than 30 seconds, corresponding label can also be produced in interview equipment;Predetermined way is another
It is a kind of to be also possible to server or interview equipment to be divided into interval according between the length that speech recognition goes out generated text/character
Label is generated on complex data, is divided into 5-30 character between the length;The predetermined way can also be the server
In the speech interval of original recording, is corresponded in complex data and generate label on time point.
Wherein, each interview device 200 has an ID, and each editing device has an ID, is every on the server
The interview device of a registration records its ID and corresponding editing device ID.By carrying out rights management to downloading ID, guarantee number
According to safety.
The embodiment of the present invention is described with above attached drawing, but the invention is not limited to above-mentioned specific
Embodiment, the above mentioned embodiment is only schematical, rather than restrictive, those skilled in the art
Under the inspiration of the present invention, without breaking away from the scope protected by the purposes and claims of the present invention, it can also make very much
Form, all of these belong to the protection of the present invention.
Claims (10)
1. a kind of shorthand system characterized by comprising
Request is identified to receiving voice data on response to network, is converted to the server (100) of lteral data;
For with voice collection device (220) acquire voice data and with networked data transmission unit without (210) by voice data
It is transferred to the interview device (200) of the server (100);
For communicating to connect (340) described server (100), and the text with voice is received from the server (100) and is answered
The editing device (300) for closing data and being handled it, is connected with display (310), indication/input equipment (320) and raises
Sound device (330), wherein the complex data includes the lteral data and voice data for having segmentation markers between time sequence saves,
When showing editor's lteral data on display (310) while showing the segmentation markers, when detecting the segmentation markers quilt
When indication/the input equipment (320) chooses click, corresponding voice data is read from complex data packet and is passed through with sound
Loudspeaker (330) is reset so as to text checking treatment.
2. taking down in short-hand system according to claim 1, which is characterized in that the server is long according to the time that raw tone is recorded
Degree is that unit generates label on complex data, and the time span was greater than 2 seconds, less than 30 seconds.
3. taking down in short-hand system according to claim 2, which is characterized in that the server is generated according to going out in speech recognition
It is divided into be spaced on complex data between text/character length and generates label, be divided into 5-30 character between the length.
4. taking down in short-hand system according to claim 1, which is characterized in that the server in the speech interval of original recording,
It is corresponded in complex data and generates label on time point.
5. system is taken down in short-hand described in any one of -4 according to claim 1, which is characterized in that each interview device (200) has one
A ID, each editing device has an ID, on the server, records its ID and correspondence for the interview device of each registration
Editing device ID.
6. a kind of stenography method, which comprises the following steps:
Voice signal is acquired, server is transmitted to;
Server will receive voice signal and identify in chronological order, generate lteral data;
According to predetermined way on the voice text data of generation setting flag, while being set on the position of corresponding lteral data
Tagging has unique corresponding relation between the two;
Download from a server lteral data and voice data comprising tape label;
The lteral data of tape label is shown over the display;
When label is by pointing operation, one section of voice is reset from correspondence markings from voice data and is come out from loudspeaker;
Lteral data is edited and modified according to the voice of playback.
7. stenography method according to claim 6, which is characterized in that the predetermined way is the server according to original
The time span of voice recording is that unit generates label on complex data, and the time span was greater than 2 seconds, less than 30 seconds.
8. stenography method according to claim 6, which is characterized in that the predetermined way is the server according in voice
It identifies to be divided between the length of generated text/character to be spaced on complex data and generates label, be divided into 5- between the length
30 characters.
9. stenography method according to claim 6, which is characterized in that the predetermined way is the server in original recording
Speech interval in, complex data correspond on time point generate label.
10. according to stenography method described in any one of claim 6-9, which is characterized in that each interview device (200) has one
A ID, each editing device has an ID, on the server, records its ID and correspondence for the interview device of each registration
Editing device ID.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710461300.3A CN109147791A (en) | 2017-06-16 | 2017-06-16 | A kind of shorthand system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710461300.3A CN109147791A (en) | 2017-06-16 | 2017-06-16 | A kind of shorthand system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109147791A true CN109147791A (en) | 2019-01-04 |
Family
ID=64804172
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710461300.3A Pending CN109147791A (en) | 2017-06-16 | 2017-06-16 | A kind of shorthand system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109147791A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110265026A (en) * | 2019-06-19 | 2019-09-20 | 安徽声讯信息技术有限公司 | A kind of meeting shorthand system and meeting stenography method |
CN110264998A (en) * | 2019-06-19 | 2019-09-20 | 安徽声讯信息技术有限公司 | A kind of audio localization method for meeting shorthand system |
CN110265027A (en) * | 2019-06-19 | 2019-09-20 | 安徽声讯信息技术有限公司 | A kind of audio frequency transmission method for meeting shorthand system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1965349A (en) * | 2004-06-02 | 2007-05-16 | 美国联机股份有限公司 | Multimodal disambiguation of speech recognition |
JP2007329794A (en) * | 2006-06-09 | 2007-12-20 | Yamaha Corp | Voice recording device |
CN102956125A (en) * | 2011-08-25 | 2013-03-06 | 骅钜数位科技有限公司 | Cloud digital phonetic teaching recording system |
CN104702791A (en) * | 2015-03-13 | 2015-06-10 | 安徽声讯信息技术有限公司 | Smart phone recording sound for a long time and synchronously transliterating text, information processing method thereof |
CN105895134A (en) * | 2016-05-10 | 2016-08-24 | 安徽声讯信息技术有限公司 | Recording device with remote recording and cloud transliteration control functions and implementation method thereof |
CN106057193A (en) * | 2016-07-13 | 2016-10-26 | 深圳市沃特沃德股份有限公司 | Conference record generation method based on telephone conference and device |
CN106294646A (en) * | 2016-08-02 | 2017-01-04 | 乐视控股(北京)有限公司 | Data processing method based on audio frequency and device |
CN106383902A (en) * | 2016-09-29 | 2017-02-08 | 安徽声讯信息技术有限公司 | Immediate storing and publishing method and system of on-the-spot interview news |
-
2017
- 2017-06-16 CN CN201710461300.3A patent/CN109147791A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1965349A (en) * | 2004-06-02 | 2007-05-16 | 美国联机股份有限公司 | Multimodal disambiguation of speech recognition |
JP2007329794A (en) * | 2006-06-09 | 2007-12-20 | Yamaha Corp | Voice recording device |
CN102956125A (en) * | 2011-08-25 | 2013-03-06 | 骅钜数位科技有限公司 | Cloud digital phonetic teaching recording system |
CN104702791A (en) * | 2015-03-13 | 2015-06-10 | 安徽声讯信息技术有限公司 | Smart phone recording sound for a long time and synchronously transliterating text, information processing method thereof |
CN105895134A (en) * | 2016-05-10 | 2016-08-24 | 安徽声讯信息技术有限公司 | Recording device with remote recording and cloud transliteration control functions and implementation method thereof |
CN106057193A (en) * | 2016-07-13 | 2016-10-26 | 深圳市沃特沃德股份有限公司 | Conference record generation method based on telephone conference and device |
CN106294646A (en) * | 2016-08-02 | 2017-01-04 | 乐视控股(北京)有限公司 | Data processing method based on audio frequency and device |
CN106383902A (en) * | 2016-09-29 | 2017-02-08 | 安徽声讯信息技术有限公司 | Immediate storing and publishing method and system of on-the-spot interview news |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110265026A (en) * | 2019-06-19 | 2019-09-20 | 安徽声讯信息技术有限公司 | A kind of meeting shorthand system and meeting stenography method |
CN110264998A (en) * | 2019-06-19 | 2019-09-20 | 安徽声讯信息技术有限公司 | A kind of audio localization method for meeting shorthand system |
CN110265027A (en) * | 2019-06-19 | 2019-09-20 | 安徽声讯信息技术有限公司 | A kind of audio frequency transmission method for meeting shorthand system |
CN110264998B (en) * | 2019-06-19 | 2021-07-27 | 安徽声讯信息技术有限公司 | Audio positioning method for conference shorthand system |
CN110265026B (en) * | 2019-06-19 | 2021-07-27 | 安徽声讯信息技术有限公司 | Conference shorthand system and conference shorthand method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103137129B (en) | Audio recognition method and electronic installation | |
US7366979B2 (en) | Method and apparatus for annotating a document | |
CN102842306B (en) | Sound control method and device, voice response method and device | |
CN105632498A (en) | Method, device and system for generating conference record | |
GB2362745A (en) | Transcription of text from computer voice mail | |
CN104010267A (en) | Method and system for supporting a translation-based communication service and terminal supporting the service | |
WO2018130173A1 (en) | Dubbing method, terminal device, server and storage medium | |
CN104702791A (en) | Smart phone recording sound for a long time and synchronously transliterating text, information processing method thereof | |
CN107710322A (en) | Information providing system, information providing method and computer readable recording medium storing program for performing | |
TW201624467A (en) | Meeting minutes device and method thereof for automatically creating meeting minutes | |
CN105810207A (en) | Meeting recording device and method thereof for automatically generating meeting record | |
CN104978145A (en) | Recording realization method and apparatus and mobile terminal | |
TW201624468A (en) | Meeting minutes device and method thereof for automatically creating meeting minutes | |
CN109147791A (en) | A kind of shorthand system and method | |
TW201624470A (en) | Meeting minutes device and method thereof for automatically creating meeting minutes | |
CN109346057A (en) | A kind of speech processing system of intelligence toy for children | |
CN109599115A (en) | Minutes method and apparatus for audio collecting device and user terminal | |
CN114514577A (en) | Method and system for generating and transmitting a text recording of a verbal communication | |
CN108320761B (en) | Audio recording method, intelligent recording device and computer readable storage medium | |
CN106847256A (en) | A kind of voice converts chat method | |
CN104202458A (en) | Method and intelligent terminal for automatically storing contact information | |
CN105810206A (en) | Meeting recording device and method thereof for automatically generating meeting record | |
CN103026697A (en) | Service server device, service provision method, and service provision program | |
CN108228543A (en) | A kind of court trial notes labeling system, method and storage medium | |
CN111563182A (en) | Voice conference record storage processing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190104 |
|
RJ01 | Rejection of invention patent application after publication |