CN102685151A - Method for filtering and transmitting speech - Google Patents
Method for filtering and transmitting speech Download PDFInfo
- Publication number
- CN102685151A CN102685151A CN2012101808740A CN201210180874A CN102685151A CN 102685151 A CN102685151 A CN 102685151A CN 2012101808740 A CN2012101808740 A CN 2012101808740A CN 201210180874 A CN201210180874 A CN 201210180874A CN 102685151 A CN102685151 A CN 102685151A
- Authority
- CN
- China
- Prior art keywords
- voice
- service end
- system service
- speech
- filtering
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 6
- 238000012217 deletion Methods 0.000 claims description 5
- 230000037430 deletion Effects 0.000 claims description 5
- 238000007493 shaping process Methods 0.000 claims description 5
- 238000001228 spectrum Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 4
- 230000006855 networking Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 6
- 238000012552 review Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003999 initiator Substances 0.000 description 1
Images
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention relates to the technical field of speech recognition and internet and discloses a method for filtering and transmitting speech. The method comprises the following steps that a system client side A acquires and transmits original speech voice data, speech transmission time, a speech transmission mode and information of a system client side B for receiving the speech to a system server side; the system server side performs speech recognition and converts acquired original speech voice data into corresponding speech text information; and the system server side transmits effective speech text information converted from the original speech voice data to the specified system client side B at specified time through a specified transmission mode. The method for filtering and transmitting the speech has the advantages of effectively improving examining and verifying efficiency of the speech voice data, ensuring effectiveness of the speech voice data and increasing broadcast coverage of effective speech.
Description
Technical field
The present invention relates to voice security control and voice and transmit the field, relate in particular to the method for a kind of voice filtering and forwarding.
Background technology
Voice call is meant through sound and by the communication way of transmission medium, and common have telephone relation, a voice-over-net chat etc.Existing voice call is directly to pass to the conversation recipient to raw tone from the conversation initiator through single transmission medium.Invalid words such as the unhealthy word that exists in the voice, sensitive word are not supervised in the process of above-mentioned this voice call; And can not converse based on multiple transmission medium simultaneously; So can't guarantee the validity and healthy communication environment of voice audio data, limit the propagation coverage rate of voice simultaneously.
Summary of the invention
In order to solve technical problem of the prior art, the invention discloses the method for a kind of voice filtering and forwarding, voice audio data sends problem single and that the voice data review efficiency is lower in the prior art in order to solve.
The invention discloses the method for a kind of voice filtering and forwarding, may further comprise the steps:
System client A obtain transmitting time, the voice of raw tone voice data, voice send mode, receive the information of the system client B of voice, and send to the system service end;
The system service end carries out speech recognition and converts the raw tone voice data that gets access to corresponding speech text information;
Whether comprise invalid word in the text after the system service end carries out invalid word analysis and judges conversion;
If comprise invalid word, then the state of system service end raw tone voice data be set to invalid;
If do not comprise invalid word, then the state of system service end raw tone voice data is set to effectively;
The system service end is in the time of appointment, through the send mode of appointment, sends to the speech text information after the effective raw tone voice data conversion of being set to the system client B of appointment.
Said system service end is being stored the speech recognition modeling data.
As further improvement of the present invention: said system service end carries out the processing of frequency spectrum shaping stationarity, Filtering Processing, the invalid redundant frame of deletion and obtains revising voice audio data the raw tone voice data that said system client A sends.
As further improvement of the present invention: the speech recognition modeling data of the voice audio data of said correction voice audio data and the storage of said system service end are carried out pattern matching and are resolved, revising the text that voice audio data converts correspondence to.
As further improvement of the present invention: said invalid word is stored in the invalid word storehouse in the said system service end.
As further improvement of the present invention: the information of said system client B comprises a kind of in the user account of telephone number, e-mail address and client at least.
As further improvement of the present invention: the send mode of said appointment is the mode of phone: the system service end uses VOIP (the Voice over Internet Protocol) networking telephone; Be packaged into packet to the speech text information that is set to after effective raw tone voice data is changed; And on the IP data network, transmit in real time, realize calling to system client B.
As further improvement of the present invention: the send mode of said appointment is the mode of note, Email or client software: the link that the system service end is set to the memory address of the speech text information after the effective raw tone voice data conversion sends to system client B through note, Email or client software.
As further improvement of the present invention: said system service end comprises: voice filtering and repeater system service end software unit, the webserver; Said system client comprises: terminal, portable terminal, Internet-browser software and mobile client software unit; Said voice filtering and repeater system service end software unit operate in the webserver; The communication network passage that provides through the Internet, mobile Internet, telephone network; With the Internet-browser that operates in terminal; And the mobile client software unit that operates in the portable terminal carries out information interaction, realization voice filtering and forwarding.
The invention has the beneficial effects as follows: the method that automatic judgement voice audio data validity is provided in the process that voice are transmitted; Provide again through different send modes; Send the method for efficient voice simultaneously to a plurality of clients; Not only effectively improve the review efficiency of voice audio data, guaranteed the validity of voice audio data, and increased the propagation coverage rate of efficient voice.
[description of drawings]
Fig. 1 is the flow chart of the method for voice filtering of the present invention and forwarding;
Fig. 2 is the speech recognition flow chart in the method for voice filtering of the present invention and forwarding;
Fig. 3 is the system construction drawing of the method for voice filtering of the present invention and forwarding.
[embodiment]
Below in conjunction with description of drawings and embodiment the present invention is further specified.
The method of a kind of voice filtering and forwarding may further comprise the steps:
System client A obtain transmitting time, the voice of raw tone voice data, voice send mode, receive the information of the system client B of voice, and send to the system service end;
The system service end carries out speech recognition and converts the raw tone voice data that gets access to corresponding speech text information;
Whether comprise invalid word in the text after the system service end carries out invalid word analysis and judges conversion;
If comprise invalid word, then the state of system service end raw tone voice data be set to invalid;
If do not comprise invalid word, then the state of system service end raw tone voice data is set to effectively;
The system service end is in the time of appointment, through the send mode of appointment, sends to the speech text information after the effective raw tone voice data conversion of being set to the system client B of appointment.
Said system service end is being stored the speech recognition modeling data.
Said system service end carries out the processing of frequency spectrum shaping stationarity, Filtering Processing, the invalid redundant frame of deletion and obtains revising voice audio data the raw tone voice data that said system client A sends.
The speech recognition modeling data of the voice audio data of said correction voice audio data and the storage of said system service end are carried out the pattern matching parsing, convert corresponding text to revising voice audio data.
Said invalid word is stored in the invalid word storehouse in the said system service end.
The information of said system client B comprises a kind of in the user account of telephone number, e-mail address and client at least.
The send mode of said appointment is the mode of phone: the system service end uses VOIP (the Voice over Internet Protocol) networking telephone; Be packaged into packet to the speech text information that is set to after effective raw tone voice data is changed; And on the IP data network, transmit in real time, realize calling to system client B.
The send mode of said appointment is the mode of note, Email or client software: the link that the system service end is set to the memory address of the speech text information after the effective raw tone voice data conversion sends to system client B through note, Email or client software.
Said system service end comprises: voice filtering and repeater system service end software unit, the webserver; Said system client comprises: terminal, portable terminal, Internet-browser software and mobile client software unit; Said voice filtering and repeater system service end software unit operate in the webserver; The communication network passage that provides through the Internet, mobile Internet, telephone network; With the Internet-browser that operates in terminal; And the mobile client software unit that operates in the portable terminal carries out information interaction, realization voice filtering and forwarding.
In one embodiment, like Fig. 1,101 system client A obtain transmitting time, the voice of raw tone voice data, voice send mode, receive the information of the system client B of voice, and send to the system service end;
102 system service ends carry out speech recognition and convert the raw tone voice data that gets access to corresponding speech text information; In one embodiment; Before the system service end is converting speech text information to; Said system service end carries out the processing of frequency spectrum shaping stationarity, Filtering Processing, the invalid redundant frame of deletion and obtains revising voice audio data the raw tone voice data that said system client A sends; The speech recognition modeling data of the voice audio data of said then correction voice audio data and the storage of said system service end are carried out the pattern matching parsing, convert corresponding text to revising voice audio data.
Whether comprise invalid word in the text after 103 system service ends carry out invalid word analysis and judge conversion;
If 104 comprise invalid word, then the state of system service end raw tone voice data be set to invalid;
If 105 do not comprise invalid word, then the state of system service end raw tone voice data is set to effectively;
106 system service ends are in the time of appointment; Send mode through appointment; Send to the speech text information after the conversion of effective raw tone voice data of being set to the system client B of appointment; The mode of wherein sending can select phone to send according to actual conditions, and perhaps the mode of note, Email or client software is sent.Greatly facilitate the filtration and the forwarding of voice audio data like this.
When the system service end carries out speech recognition, adopt following scheme to realize usually: as shown in Figure 2, be the embodiment flow chart of a speech recognition,
201 system service ends are stored the voice recognition data model;
202 system service ends are handled the voice audio data that obtains, and adopt the mode voice audio data of the processing of frequency spectrum shaping stationarity, Filtering Processing, the invalid redundant frame of deletion to handle;
203 system service ends carry out pattern matching to the speech recognition modeling data of voice audio data after handling and storage resolves, and converts voice audio data into corresponding text.
The identification and the conversion of speech data have been realized through above these steps.
In order this method to be applied to practice; Special a kind of voice filtering and the repeater system made; Comprise; System service end 310 and system client 320, wherein system service end 310 comprises voice filtering and repeater system service end software unit 311, the webserver 312, wherein voice filtering and repeater system service end software unit 311 are installed in the webserver 312.Said system client 320 includes but not limited to terminal 321, portable terminal 322, Internet-browser software 323 and mobile client software unit 324; Said voice filtering and repeater system service end software unit 311 operate in the webserver 312; Through network channel 330 (the communication network passage that provides like the Internet, mobile Internet, telephone network); With the Internet-browser that operates in terminal; And the mobile client software unit that operates in the portable terminal carries out information interaction, realization voice filtering and forwarding.
Above content is to combine concrete preferred implementation to the further explain that the present invention did, and can not assert that practical implementation of the present invention is confined to these explanations.For the those of ordinary skill of technical field under the present invention, under the prerequisite that does not break away from the present invention's design, can also make some simple deduction or replace, all should be regarded as belonging to protection scope of the present invention.
Claims (9)
1. the method for voice filtering and forwarding is characterized in that, may further comprise the steps:
(101) system client A obtain transmitting time, the voice of raw tone voice data, voice send mode, receive the information of the system client B of voice, and send to the system service end;
(102) the system service end carries out speech recognition and converts the raw tone voice data that gets access to corresponding speech text information;
(103) whether comprise invalid word in the text after the system service end carries out invalid word analysis and judges conversion;
(104) if comprise invalid word, then the state of system service end raw tone voice data be set to invalid;
(105) if do not comprise invalid word, then the state of system service end raw tone voice data is set to effectively;
(106) the system service end is in the time of appointment, through the send mode of appointment, sends to the speech text information after the effective raw tone voice data conversion of being set to the system client B of appointment.
2. according to the method for said voice filtering of claim 1 and forwarding, it is characterized in that: said system service end is being stored the speech recognition modeling data.
3. according to the method for said voice filtering of claim 1 and forwarding, it is characterized in that: said system service end carries out the processing of frequency spectrum shaping stationarity, Filtering Processing, the invalid redundant frame of deletion and obtains revising voice audio data the raw tone voice data that said system client A sends.
4. according to the method for said voice filtering of claim 3 and forwarding; It is characterized in that: the speech recognition modeling data of the voice audio data of said correction voice audio data and the storage of said system service end are carried out the pattern matching parsing, convert corresponding text to revising voice audio data.
5. according to the method for said voice filtering of claim 1 and forwarding, it is characterized in that: said invalid word is stored in the invalid word storehouse in the said system service end.
6. according to the method for said voice filtering of claim 1 and forwarding, it is characterized in that: the information of said system client B comprises a kind of in the user account of telephone number, e-mail address and client at least.
7. according to the method for said voice filtering of claim 1 and forwarding; It is characterized in that: the send mode of said appointment is the mode of phone: the system service end uses VOIP (the Voice over Internet Protocol) networking telephone; Be packaged into packet to the speech text information that is set to after effective raw tone voice data is changed; And on the IP data network, transmit in real time, realize calling to system client B.
8. according to the method for said voice filtering of claim 1 and forwarding, it is characterized in that: the send mode of said appointment is the mode of note, Email or client software: the link that the system service end is set to the memory address of the speech text information after the effective raw tone voice data conversion sends to system client B through note, Email or client software.
9. according to the method for said voice filtering of claim 1 and forwarding, it is characterized in that: said system service end comprises: voice filtering and repeater system service end software unit, the webserver; Said system client comprises: terminal, portable terminal, Internet-browser software and mobile client software unit; Said voice filtering and repeater system service end software unit operate in the webserver; The communication network passage that provides through the Internet, mobile Internet, telephone network; With the Internet-browser that operates in terminal; And the mobile client software unit that operates in the portable terminal carries out information interaction, realization voice filtering and forwarding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101808740A CN102685151A (en) | 2012-06-05 | 2012-06-05 | Method for filtering and transmitting speech |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101808740A CN102685151A (en) | 2012-06-05 | 2012-06-05 | Method for filtering and transmitting speech |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102685151A true CN102685151A (en) | 2012-09-19 |
Family
ID=46816514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101808740A Pending CN102685151A (en) | 2012-06-05 | 2012-06-05 | Method for filtering and transmitting speech |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102685151A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766508A (en) * | 2018-12-28 | 2019-05-17 | 广州华多网络科技有限公司 | Signal auditing method, device and electronic equipment |
| CN112992141A (en) * | 2021-02-23 | 2021-06-18 | 北京百度网讯科技有限公司 | Communication method and device under voice recognition scene |
| US12159649B2 (en) | 2021-07-15 | 2024-12-03 | Lemon Inc. | Multimedia processing method and apparatus, electronic device, and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1322981A (en) * | 2000-05-04 | 2001-11-21 | 国际商业机器公司 | Continuous sound identifying technique provided to equipment with limited handling ability |
| CN1792082A (en) * | 2003-04-22 | 2006-06-21 | 斯皮沃克斯有限公司 | Text entry display for intelligent transcription of voicemail into text message |
| CN1929513A (en) * | 2005-09-06 | 2007-03-14 | 中兴通讯股份有限公司 | Short message filtration method |
| CN101415159A (en) * | 2008-12-02 | 2009-04-22 | 腾讯科技（深圳）有限公司 | Method and apparatus for intercepting junk mail |
| CN102546992A (en) * | 2011-12-12 | 2012-07-04 | 华为技术有限公司 | Junk voice message filtering method, filtering device and filtering system |
-
2012
- 2012-06-05 CN CN2012101808740A patent/CN102685151A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1322981A (en) * | 2000-05-04 | 2001-11-21 | 国际商业机器公司 | Continuous sound identifying technique provided to equipment with limited handling ability |
| CN1792082A (en) * | 2003-04-22 | 2006-06-21 | 斯皮沃克斯有限公司 | Text entry display for intelligent transcription of voicemail into text message |
| CN1929513A (en) * | 2005-09-06 | 2007-03-14 | 中兴通讯股份有限公司 | Short message filtration method |
| CN101415159A (en) * | 2008-12-02 | 2009-04-22 | 腾讯科技（深圳）有限公司 | Method and apparatus for intercepting junk mail |
| CN102546992A (en) * | 2011-12-12 | 2012-07-04 | 华为技术有限公司 | Junk voice message filtering method, filtering device and filtering system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766508A (en) * | 2018-12-28 | 2019-05-17 | 广州华多网络科技有限公司 | Signal auditing method, device and electronic equipment |
| CN109766508B (en) * | 2018-12-28 | 2021-09-21 | 广州华多网络科技有限公司 | Information auditing method and device and electronic equipment |
| CN112992141A (en) * | 2021-02-23 | 2021-06-18 | 北京百度网讯科技有限公司 | Communication method and device under voice recognition scene |
| US12159649B2 (en) | 2021-07-15 | 2024-12-03 | Lemon Inc. | Multimedia processing method and apparatus, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7885187B2 (en) | System and method for providing unified messaging system service using voice over internet protocol | |
| CN102572799A (en) | Method for acquiring network connection information of client terminal accessing Wi-Fi spot and terminal | |
| CN102281213A (en) | Instant messaging method and system for supporting voice and video message | |
| 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 | |
| CN102685151A (en) | Method for filtering and transmitting speech | |
| CN104618616B (en) | Videoconference participant identification system and method based on speech feature extraction | |
| CN204669388U (en) | ROIP Digital Clustering IAD | |
| CN103684970A (en) | Transmission method and thin terminals for media data streams | |
| CN102158615A (en) | LINUX-based media server in (Voice Over Internet Protocol) system and playback method of media server | |
| JP2007019767A (en) | Ip telephone set | |
| US20070129037A1 (en) | Mute processing apparatus and method | |
| CN220359182U (en) | Converged scheduling communication system based on IP network | |
| CN105657149B (en) | A kind of voice communication method, system and communication terminal | |
| KR200462920Y1 (en) | Internet protocol equipment for improving sound quality of melodyring | |
| CN101127772B (en) | Method for distributed processing of real time transfer of protocol signaling | |
| CN102802197A (en) | Method and device for transmitting application data | |
| CN100452778C (en) | Multimedia content interaction system based on instantaneous communication and its realizing method | |
| CN102932566B (en) | Method for reducing voice distortion in VOIP (Voice over Internet Protocol) phone call under VDI (Virtual Desktop Infrastructure) environment | |
| CN105553935B (en) | A kind of data package processing method, device and terminal | |
| CN104703152B (en) | A kind of short message processing method and device | |
| CN101753731B (en) | Fixed telephone terminal | |
| CN101610321A (en) | The implementation method of function of training telephone operators in a kind of call center system | |
| EP2359562B1 (en) | Digital telecommunications system, program product for, and method of managing such a system | |
| CN101998003B (en) | Call holding method for voice over internet protocol (VoIP) based on session initiation protocol (SIP) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120919 |