CN110931001B - Anti-noise audio transmission device facing voice recognition - Google Patents
Anti-noise audio transmission device facing voice recognition Download PDFInfo
- Publication number
- CN110931001B CN110931001B CN201910838418.2A CN201910838418A CN110931001B CN 110931001 B CN110931001 B CN 110931001B CN 201910838418 A CN201910838418 A CN 201910838418A CN 110931001 B CN110931001 B CN 110931001B
- Authority
- CN
- China
- Prior art keywords
- audio
- signal
- signals
- telephone
- box
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 22
- 239000003990 capacitor Substances 0.000 claims abstract description 5
- 230000005236 sound signal Effects 0.000 claims description 32
- 238000013518 transcription Methods 0.000 claims description 20
- 230000035897 transcription Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 10
- 238000000926 separation method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 239000013078 crystal Substances 0.000 claims description 2
- 238000002955 isolation Methods 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 9
- 239000000463 material Substances 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 235000009754 Vitis X bourquina Nutrition 0.000 description 1
- 235000012333 Vitis X labruscana Nutrition 0.000 description 1
- 240000006365 Vitis vinifera Species 0.000 description 1
- 235000014787 Vitis vinifera Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
Images
Classifications
-
- 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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
-
- 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
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses an anti-noise audio transmission device facing voice recognition, which transmits a loudspeaker signal S generated by sound source equipmentsConverted into a microphone signal S that can be recognized by the TRRS interface of the mobile devicem. The TRRS end of the mobile equipment receives S generated by the electret microphonemThe signal needs to use its built-in amplifying circuit to drive the electret microphone, because the work of the audio box module is to simulate the microphone signal, in order to eliminate the driving current of the receiving end to SsUsing 2 sets of active capacitors C in the module2、C1The drive current from the drive side is filtered out. The TRRS side of the mobile device detects the accessed device to determine that the device is a TRS type or a TRRS type, and some mobile devices perform impedance matching on the accessed device. The sound box has the advantages of simple structure, convenience and flexibility in use, and the anti-noise transmission function is realized in the mode that the sound box can only be placed beside a sound box for recording through a mobile phone.
Description
Technical Field
The invention comprises a system and a device, and firstly relates to software integration of artificial intelligence mature technology, in particular to analysis engines such as voice real-time transcription and voice file transcription; secondly relate to an intelligence audio transmission leading device, especially relate to a noise resistant audio transmission leading device towards speech recognition. The invention belongs to the technical fields of software development, artificial intelligence, electric appliance control and the like.
Background
The journalist can not leave the work of arranging the recording materials in the process of news creation. In the face of a large amount of precious recording materials collected in the interview process, the course of the precious recording materials is removed, news inspiration and clues are refined, and arrangement work such as repeated playback of recording and information checking is needed. Meanwhile, various large and small conferences can be developed by part of units every day, and in the process of the conferences, the organization conditions and specific contents of the conferences are mostly recorded to form conference records. Some important meetings need to be recorded and transmitted with meeting conditions and agreed matters, and are arranged into a meeting summary.
In order to reduce the working strength and difficulty of interview materials or conference recording audio arrangement colleagues and improve the working efficiency and the accuracy of work results, research and development of a set of recording, transferring and listening tools supporting multiple languages is urgent. The tool needs to realize the function of arranging the recording data, simultaneously supports the alignment and linkage of the recording identification result and the time frame, and can enable a user to freely edit and download the identification result. Meanwhile, in practical application, the mobile phone recording function can collect the sound of the television and pick up the noise around the mobile phone to influence the recognition and transcription service of the voice service, so that the design of a prepositive device capable of realizing audio transmission is very necessary.
Disclosure of Invention
Aiming at the problems that the repeated labor is large when a reporter edits materials such as a news recording and a meeting record in daily life, and the like, an artificial intelligence mature technology is subjected to software integration, and a device with a voice character transferring function is developed and embedded in a reporter station report commanding client.
Aiming at the problems of environmental noise and the like commonly existing in mobile phone recording, the invention provides an anti-noise audio transmission prepositive device facing voice recognition, which has the advantages of simple structure and convenient and flexible use in the implementation mode, and has the anti-noise transmission function in the mode that the mobile phone can only be placed beside a sound box for recording originally.
The technical scheme adopted by the invention is as follows:
aiming at the HDMI digital television, the device comprises three combined modules which are respectively an HDMI conversion distributor module, an HDMI audio-video separation module and an audio signal conversion processing module. The HDMI conversion distributor module is used for copying an original HDMI signal, one path of signal is transmitted to video playing equipment such as a television, a display and the like for normal program showing and watching, the other path of signal passes through the HDMI audio and video separation module, an audio signal is separated out and is accessed to the audio signal conversion processing module, and the audio signal conversion processing module is used for performing subsequent processing such as voice conversion of characters and the like on the signal output to the mobile client.
For an analog telephone or an IP digital telephone, the audio box module is connected into a 4-core wire of a telephone handle in a parallel mode by using a 4P4C port. The 4 core wires of the telephone handle are respectively defined as a microphone signal, a ground wire a, a loudspeaker signal and a ground wire b, and the analog telephone and the loudspeaker signal comprise signal feedback to a microphone of the telephone, so that audio signals of the two parties are directly acquired through the audio box module. For the IP digital telephone, the signals of the microphone and the speaker need to be intercepted through two circuit lines, and then the signals are accessed to the mobile client for subsequent processing.
The audio box module is used for generating a loudspeaker signal S from an audio source devicesConverted into a microphone signal S that can be recognized by the TRRS interface of the mobile devicem. The TRRS end of the mobile equipment receives S generated by the electret microphonemThe signal needs to use its built-in amplifying circuit to drive the electret microphone, because the work of the audio box module is to simulate the microphone signal, in order to eliminate the driving current of the receiving end to SsUsing 2 sets of active capacitors C in the module2、C1The drive current from the drive side is filtered out. Meanwhile, the TRRS terminal of the mobile device detects the accessed device to judge that the device is a TRS type (earphone) or a TRRS type (earphone), and part of the mobile device performs impedance matching on the accessed device, so that a resistor R is used in the module3So that the module can be correctly identified as a microphone. On the moduleIn the use scene of (2), the accessed loudspeaker sound channel signal is subjected to primary attenuation on the signal through a first-stage resistor R1, the potential is kept consistent with the input end through a pull-down resistor R2, the signal is filtered through a capacitor to filter out direct current quantity possibly existing in a receiving end, then the potential is kept consistent through a pull-down resistor R4, impedance matching is carried out on the signal and a TRRS interface of a mobile end through a resistor R3, and the signal is input into the mobile end as a microphone signal to be processed. If the multi-channel signal comprises stereo signal input and digital telephone handle end access, a corresponding number of circuit channels are added, and the mobile end is accessed through a tail R3 resistor.
For a single signal line, signal current
Assuming that the output voltage is Um, the input signal voltage is Us signal potential difference may be
The power attenuation of the module for the overall input signal is
Compared with the traditional recording device, the invention has the following technical effects:
1. the method is effectively integrated with a reporter station report commanding client, a combination point is found between a voice transcription technology and a news gathering and editing service, and the work efficiency of news production and daily office processes can be further improved.
2. When the audio frequency of the digital signal television is transcribed, the audio frequency in the television signal can be picked up when the television is normally played and is not influenced by the interference of live speaking sound.
3. After signals of a microphone and a loudspeaker of a telephone handle are intercepted, filtering attenuation is carried out, the signals are connected with a voice transcription character service of the mobile phone through a cable, and conversation contents are directly transcribed into characters.
Drawings
FIG. 1 is a software and hardware flow diagram according to the present invention.
Fig. 2 is a flow chart of the story director client audio function.
Fig. 3 is an assembly view of the use of the tv edition audio box.
Fig. 4 is an assembly view of the use of the landline audio cartridge.
Fig. 5 is a television set box circuit.
Fig. 6 is a landline box subcircuit.
Detailed Description
The invention mainly comprises two parts: the device is based on the voice-to-text function of the report commanding client, is based on the international advanced multilingual voice recognition technology, and is developed by combining with the customization of editing scenes; and secondly, by utilizing a 3D printing technology, a voice recognition-oriented audio transmission hardware device is developed, so that the noise problem caused by external noise can be eliminated.
The audio transmission hardware device specifically realizes a voice transcription function as an audio transmission device under the following three scenarios:
1. audio acquisition of television signals identifies transcription. The method comprises the steps of picking up audio signals aiming at a channel which is obtained from an HDMI signal source and is currently played by a television, and identifying audio to be converted into characters in real time through audio service.
2. And video and audio signals are collected, identified and transcribed in mobile terminals such as mobile phones and tablet computers. When a mobile phone plays a video or a segment of audio, the audio signal in the mobile phone can be picked up and transmitted into the mobile phone with the 'audio' service of the report command APP, and the audio is identified in real time and converted into characters.
3. And audio signals of a microphone and a receiver in the fixed-line telephone are collected, identified and transcribed. When the collecting and editing personnel carry out telephone interview through the telephone fixed-line telephone, the hardware is connected to a mobile phone which is provided with the 'audio' service of the report commanding APP, and meanwhile, the speaking sounds of both parties of the call are captured, and the transcription is identified.
In the two former scenes, in order to enable the 'audio signal' service of the report commanding client to receive high-quality audio signals, the audio signal box adopts an electric signal mode to carry out signal propagation, so that on one hand, the method avoids the attenuation of analog waveforms during propagation in natural media, and greatly reduces the interference of environmental sounds to the signals; on the other hand, the user can perform uninterrupted voice communication with the outside while operating. The box is connected with a sound source through a 3.5 mm TRS earphone interface, performs sound mixing on left and right sound channels of a stereo sound source, performs processing work such as direct current isolation, signal noise reduction, signal decay and the like, converts signals into input signals which can be identified by various electronic equipment with audio collecting and releasing functions, and can conveniently perform subsequent signal processing. Aiming at audio output and input interfaces of a large number of handheld mobile devices with different standards, the audio box self-defines a TRRS socket at an input end so as to adapt to wider use scenes, and the output end simplifies the connection mode of the socket and radically cuts off signal interference from the output of a receiving end. And the audio box reserves a double-phase monitoring function interface, which can not only meet the current audio signal recording function, but also expand the monitoring function of input and output signals.
For the audio box of the fixed telephone version, because the definitions of the common analog telephone and the multifunctional network telephone on the handle interface and the structure are different, the audio box develops a printed circuit bottom board with high compatibility, the functions of the analog telephone and the network telephone which can be simultaneously adapted to one circuit bottom board are realized through different element access modes, and two types of equipment, namely a box specially aiming at the analog telephone and a box specially used for the network telephone, are developed by the audio box depending on the use scene of the fixed telephone. The audio box of the telephone version intercepts two-way audio signals through a telephone handle, and performs audio mixing on the audio signals of a microphone and a loudspeaker of a user side, namely voice information signals of both parties of a call are obtained, the signals are converted into input signals which can be received and adopted by a mobile equipment client after being processed by the audio box, and the input signals are subsequently processed by the mobile equipment, and the method is realized by using two 4P4C and corresponding crystal heads and 4 core wires to jump out a handle wire of a fixed telephone. For most analog telephones on the market, the two central lines are processed loudspeaker signals and contain microphone signals of the telephone itself, and for most digital IP telephones, the two central lines are microphone signals and the two sides are microphone signals. The signals in pairs are output as microphone signals which can be identified by a TRRS terminal of the mobile phone through voltage division and capacitance filtering of a resistor, are simulated into a microphone input device at a mobile phone end, and are transcribed into characters through an application program at the mobile phone end.
The attached drawing of the television message box is a connection structure, as shown in figure 3, the system uses an HDMI one-to-two device to copy audio and video signals, one part of the signals are normally output to a television, the other part of the signals use an HDMI audio and video separation device to strip out audio signals, and the audio signals are processed through the message box and connected with the transcription text service of a mobile phone client.
The connection mode of the fixed telephone box is shown in fig. 4, the telephone main body and the handle connecting line are separated from the telephone end and are connected into the audio box, and the box outputs signals to the transcription text service of the mobile phone client.
The following functions are mainly realized:
the invention integrates the related technology of a unified authentication platform in the report commanding client, and realizes the authentication and safety protection of user login.
The task of real-time transcription of 'audio' voice is started. As a modern communication society of the world, reporters spread important news and major emergencies at home and abroad authoritatively, accurately and timely over more than 100 countries and regions of the world. By combining with the actual editing requirements, the invention integrates the voice transcription technology of 9 languages such as Chinese, English, Western, French, Russian, Arabic, grape, Japanese, Korean and the like in the report commanding client, and the reporter editing user can quickly analyze the voice in real time by means of the voice transcription function of the client.
And performing operations such as fast editing of characters, issuance of manuscripts of the acquisition and editing system of Xinhua community and the like. The report commanding client is used as a mobile phone end form of the Xinhua community all-media gathering, editing and distributing platform, and can realize news production functions such as manuscript gathering, editing and distributing operation, report commanding, instant messaging and the like. Compared with professional shorthand, the voice transcription technology has a certain error rate, so that the invention effectively embeds the multilingual voice recognition technology into the client and realizes the function of editing and modifying the transcribed words. In order to enhance the user experience, the client communicates with the new acquisition and editing manuscript issuing interface, and the invention realizes the functions of one-key manuscript creating, issuing and the like of the transcription result characters and the recording.
Claims (8)
1. An apparatus for noise immune audio transmission oriented to speech recognition, characterized by: the device is an audio box module and is used for generating a loudspeaker signal S of sound source equipmentsConverted into a microphone signal S that can be recognized by the TRRS interface of the mobile devicem(ii) a The TRRS end of the mobile equipment receives S generated by the electret microphonemThe signal needs to use its built-in amplifying circuit to drive the electret microphone, because the work of the audio box module is to simulate the microphone signal, in order to eliminate the driving current of the receiving end to SsUsing 2 sets of active capacitors C in the module2、C1Filtering out the driving current from the driving end; meanwhile, the TRRS terminal of the mobile equipment detects the accessed equipment to judge that the equipment is of a TRS type or a TRRS type, and part of the mobile equipment performs impedance matching on the accessed equipment, so that the module is correctly identified as a microphone by using a resistor;
aiming at an HDMI digital television, the device comprises three combined modules, namely an HDMI conversion distributor module, an HDMI audio-video separation module and an audio signal conversion processing module; the method comprises the following steps that an HDMI conversion distributor module is used for copying original HDMI signals, one path of signals are transmitted to video playing equipment such as a television and a display to be displayed and watched normally, the other path of signals pass through an HDMI audio and video separation module to separate audio signals, the audio signals are connected to an audio signal conversion processing module, and the audio signal conversion processing module is used for carrying out voice conversion character subsequent processing on signals output to a mobile client;
aiming at an analog telephone or an IP digital telephone, a 4P4C port is used, and the audio box module is connected into a 4-core wire of a telephone handle in a parallel mode; the 4 core wires of the telephone handle are respectively defined as a microphone signal, a ground wire a, a loudspeaker signal and a ground wire b, and the analog telephone and the loudspeaker signal contain signal feedback to a microphone of the telephone, so that audio signals of the two parties are directly obtained through the audio box module; for the IP digital telephone, the signals of the microphone and the speaker need to be intercepted through two circuit lines, and then the signals are accessed to the mobile client for subsequent processing.
2. An apparatus for noise resistant audio transmission for speech recognition according to claim 1, wherein:
in a using scene of the module, an accessed loudspeaker sound channel signal carries out primary attenuation on the signal through a first-stage resistor R1, the potential is kept consistent with an input end through a pull-down resistor R2, the signal passes through a capacitor, a direct current quantity possibly existing in a receiving end is filtered, then the potential is kept consistent through a pull-down resistor R4, impedance matching is carried out on the signal and a TRRS interface of a mobile end through a resistor R3, and the signal is input into the mobile end as a microphone signal to be processed.
3. An apparatus for noise resistant audio transmission for speech recognition according to claim 2, wherein:
if the multi-channel signal comprises stereo signal input and digital telephone handle end access, a corresponding number of circuit channels are added, and the mobile end is accessed through a tail R3 resistor.
4. An apparatus for noise resistant audio transmission for speech recognition according to claim 2, wherein:
for a single signal line, signal current
Assuming that the output voltage is Um, the input signal voltage is Us signal potential difference may be
The power attenuation of the module for the overall input signal is
5. An apparatus for noise resistant audio transmission for speech recognition according to claim 1, wherein: the audio transmission hardware device specifically realizes a voice transcription function as an audio transmission device under the following three scenarios:
audio acquisition, identification and transcription of television signals; aiming at a channel which is obtained from an HDMI signal source and is currently played by a television, audio signals are picked up, and audio is identified to be converted into characters in real time through 'audio signal' service;
collecting, identifying and transcribing video and audio signals in the mobile terminal; when a mobile phone plays a video or a segment of audio, the audio signal in the mobile phone can be picked up and transmitted into the mobile phone with the 'audio' service of the report command APP, and the audio is identified in real time and converted into characters;
collecting, identifying and transcribing audio signals of a microphone and a receiver in the fixed-line telephone set; when the collecting and editing personnel carry out telephone interview through the telephone fixed-line telephone, the hardware is connected to a mobile phone which is provided with the 'message' service of the report commanding APP, and simultaneously, the speaking sounds of both parties of the call are captured to identify the transcription;
the audio box adopts an electric signal mode to carry out signal propagation, the box is connected with a sound source through a 3.5 mm TRS earphone interface to carry out sound mixing of left and right channels on a stereo sound source, and the direct current isolation, signal noise reduction and signal decay processing work are carried out, so that signals are converted into input signals which can be identified by various electronic equipment with audio receiving and releasing functions, and subsequent signal processing is carried out; aiming at audio output and input interfaces of a large number of handheld mobile devices with different standards, the audio box self-defines a TRRS socket at an input end, and the output end fundamentally cuts off signal interference from the output of a receiving end; and the audio box reserves a double-phase monitoring function interface, which can not only meet the current audio signal recording function, but also expand the monitoring function of input and output signals.
6. An apparatus for noise resistant audio transmission for speech recognition according to claim 1, wherein: for the audio box of the fixed telephone version, because the definitions of the common analog telephone and the multifunctional network telephone on the handle interface and the structure are different, the audio box develops a printed circuit bottom board with high compatibility, realizes that one circuit bottom board can be simultaneously adapted to the functions of the analog telephone and the network telephone through different element access modes, and develops two types of equipment, namely a box specially aiming at the analog telephone and a box specially used for the network telephone, according to the use scene of the fixed telephone; the audio box of the telephone version intercepts two-way audio signals through a telephone handle, and performs audio mixing on audio signals of a microphone and a loudspeaker of a user side, namely voice information signals of both parties of a call are obtained, the signals are converted into input signals received and adopted by a mobile equipment client after being processed by the audio box, and the mobile equipment performs subsequent processing, and the implementation method is that two 4P4C and corresponding crystal heads and 4 core wires are used, and a handle wire of a fixed telephone is jumped out; for an analog telephone, the central two lines are processed loudspeaker signals and comprise microphone signals of the telephone, and for most digital IP telephones, the central two lines are microphone signals and the two sides are microphone signals; the signals in pairs are output as microphone signals which can be identified by a TRRS terminal of the mobile phone through voltage division and capacitance filtering of a resistor, are simulated into a microphone input device at a mobile phone end, and are transcribed into characters through an application program at the mobile phone end.
7. An apparatus for noise resistant audio transmission for speech recognition according to claim 6, wherein: in the connection of the audio box of the television, the audio and video signals are copied by using the HDMI one-to-two device, one part of the signals are normally output to the television, the other part of the signals are stripped by using the HDMI audio and video separating device, and the audio signals are processed by the audio box and connected with the transcription character service of the mobile phone client.
8. An apparatus for noise resistant audio transmission for speech recognition according to claim 6, wherein: in the fixed telephone box connection, the telephone main body and the handle connecting line are separated from the telephone end and are connected into the audio box, and the box outputs signals to the transcription text service of the mobile phone client.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910838418.2A CN110931001B (en) | 2019-09-05 | 2019-09-05 | Anti-noise audio transmission device facing voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910838418.2A CN110931001B (en) | 2019-09-05 | 2019-09-05 | Anti-noise audio transmission device facing voice recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110931001A CN110931001A (en) | 2020-03-27 |
| CN110931001B true CN110931001B (en) | 2022-05-17 |
Family
ID=69848716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910838418.2A Active CN110931001B (en) | 2019-09-05 | 2019-09-05 | Anti-noise audio transmission device facing voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110931001B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201307929D0 (en) * | 2013-05-02 | 2013-06-12 | Incus Lab Ltd | Interconnecting Electronic Host Devices and Accessories |
| CN105975466A (en) * | 2015-11-04 | 2016-09-28 | 新华通讯社 | Method and device for machine manuscript writing aiming at short newsflashes |
| CN107071603A (en) * | 2017-06-30 | 2017-08-18 | 广州音书科技有限公司 | A kind of microphone and system for Real-time speech recognition |
| CN207070253U (en) * | 2017-08-21 | 2018-03-02 | 原点私人有限公司 | A kind of mobile terminal, ear-micro phone and its Electret condenser microphone circuit |
| CN107889085A (en) * | 2016-09-30 | 2018-04-06 | 亚旭电脑股份有限公司 | Voice signal is input to method, electronic installation and the computer of intelligent apparatus |
| KR101849229B1 (en) * | 2017-08-25 | 2018-05-24 | (주)비전정보통신 | CCTV video monitoring system using voice recognition |
| CN108551514A (en) * | 2018-03-21 | 2018-09-18 | 上海工程技术大学 | A kind of telephone device of complete acoustic control |
| JP2019056893A (en) * | 2017-09-19 | 2019-04-11 | 和田 弘 | Conversation apparatus |
| CN109791529A (en) * | 2016-07-25 | 2019-05-21 | 思睿逻辑国际半导体有限公司 | Connector for data transmission |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9800721B2 (en) * | 2010-09-07 | 2017-10-24 | Securus Technologies, Inc. | Multi-party conversation analyzer and logger |
| US8781824B2 (en) * | 2010-12-31 | 2014-07-15 | Eldon Technology Limited | Offline generation of subtitles |
| US20180176638A1 (en) * | 2016-12-15 | 2018-06-21 | Arris Enterprises Llc | Language-based signaling of secondary audio |
-
2019
- 2019-09-05 CN CN201910838418.2A patent/CN110931001B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201307929D0 (en) * | 2013-05-02 | 2013-06-12 | Incus Lab Ltd | Interconnecting Electronic Host Devices and Accessories |
| CN105975466A (en) * | 2015-11-04 | 2016-09-28 | 新华通讯社 | Method and device for machine manuscript writing aiming at short newsflashes |
| CN109791529A (en) * | 2016-07-25 | 2019-05-21 | 思睿逻辑国际半导体有限公司 | Connector for data transmission |
| CN107889085A (en) * | 2016-09-30 | 2018-04-06 | 亚旭电脑股份有限公司 | Voice signal is input to method, electronic installation and the computer of intelligent apparatus |
| CN107071603A (en) * | 2017-06-30 | 2017-08-18 | 广州音书科技有限公司 | A kind of microphone and system for Real-time speech recognition |
| CN207070253U (en) * | 2017-08-21 | 2018-03-02 | 原点私人有限公司 | A kind of mobile terminal, ear-micro phone and its Electret condenser microphone circuit |
| KR101849229B1 (en) * | 2017-08-25 | 2018-05-24 | (주)비전정보통신 | CCTV video monitoring system using voice recognition |
| JP2019056893A (en) * | 2017-09-19 | 2019-04-11 | 和田 弘 | Conversation apparatus |
| CN108551514A (en) * | 2018-03-21 | 2018-09-18 | 上海工程技术大学 | A kind of telephone device of complete acoustic control |
Non-Patent Citations (2)
| Title |
|---|
| CWDM based HDMI cable using passively aligned optical interconnect modules;Hak-Soon Lee;《IEEE Photonic Society 24th Annual Meeting》;20111222;672-673 * |
| 基于HDMI的实时视频/音频传输系统设计;丁铁夫;《微计算机信息》;20090115;180-182 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110931001A (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101459717B (en) | Wireless terminal and method for implementing multi-channel multiplexing | |
| CN107527623B (en) | Screen transmission method and device, electronic equipment and computer readable storage medium | |
| CN103312912B (en) | A kind of mixer system and method | |
| JP2002504273A (en) | Method and apparatus for recording and indexing audio and multimedia conferences | |
| CN108616800A (en) | Playing method and device, storage medium, the electronic device of audio | |
| CN108460120A (en) | Data saving method and device, terminal equipment and storage medium | |
| CN103795834A (en) | Recording method capable of uploading conversation recording file of smart phone and dedicated recording apparatus | |
| CN101277338A (en) | Method for recording downstream voice signal of communication terminal as well as the communication terminal | |
| CN110931001B (en) | Anti-noise audio transmission device facing voice recognition | |
| CN106507242A (en) | A kind of audio devices and terminal | |
| CN111787169A (en) | Three-party call terminal for mobile man-machine cooperation calling robot | |
| CN109495814B (en) | Audio connector, audio signal processing method and audio signal processing system | |
| CN211529610U (en) | Voice transcription processing device with role separation function | |
| WO2020037746A1 (en) | Microphone equipped with smart conversion interface and implementation method | |
| CN201467263U (en) | Television interactive with mobile phone | |
| CN210053486U (en) | Teleconference sound receiving device | |
| CN204377136U (en) | A kind of holographic audio frequency gathers playback reproducer | |
| CN201114207Y (en) | 3D commercial information telephone set | |
| CN100428766C (en) | A seat telephone traffic recording system and method for telephone traffic recording using same system | |
| CN216531604U (en) | Projector and projection kit | |
| CN206542539U (en) | A kind of recording and broadcasting system | |
| CN207399486U (en) | A kind of microphone device extended by ear microphone jack | |
| CN110767235A (en) | Voice transcription processing device with role separation function and control method | |
| CN105682209A (en) | Method for reducing conversation power consumption of mobile terminal and mobile terminal | |
| CN213638147U (en) | Earphone set |
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 |