CN207690495U - A kind of high sensitivity speech recognition system - Google Patents
A kind of high sensitivity speech recognition system Download PDFInfo
- Publication number
- CN207690495U CN207690495U CN201820065972.2U CN201820065972U CN207690495U CN 207690495 U CN207690495 U CN 207690495U CN 201820065972 U CN201820065972 U CN 201820065972U CN 207690495 U CN207690495 U CN 207690495U
- Authority
- CN
- China
- Prior art keywords
- circuit
- voice
- speech recognition
- speech
- interface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Landscapes
- Mobile Radio Communication Systems (AREA)
Abstract
The utility model discloses a kind of highly sensitive speech recognition systems, include voice collecting circuit, speech recognition circuit, radio communication circuit, local interface, speech processing circuit and voice transmission circuit including the highly sensitive speech recognition system, the radio communication circuit is wirelessly connected with high in the clouds, the high in the clouds includes speech database, the radio communication circuit also receives client wireless with external voice and connect, and the local interface is connected with local device.The utility model realizes the function integrations services such as speech recognition, phonetic synthesis and voice transfer, can support multistage entry identification function, has and automatically selects and handoff functionality；With higher accuracy of identification and recognition efficiency；Use scope is wide, can be communicated with high in the clouds.
Description
Technical field
The utility model belongs to technical field of voice recognition more particularly to a kind of highly sensitive speech recognition system.
Background technology
Speech recognition technology mainly can make one to be exchanged with computer, by the language conversion of the mankind at computer capacity
The language enough identified, to realize the application functions such as human speech control computer, speech recognition technology is in industry, household electrical appliances, logical
The every field such as letter, automotive electronics, medical treatment, home services, consumption electronic product can access extensive utilization.
There are many more insurmountable problems for existing speech recognition system, such as：Speech recognition, language can not be provided simultaneously with
Sound synthesizes and the functions such as voice transfer, and multistage entry cannot be supported to identify；Accuracy of identification is poor, and recognition efficiency is low；Universal performance
Difference, and use scope has limitation.
Utility model content
In order to overcome the shortcomings of art methods, the purpose of this utility model is that proposing that a kind of highly sensitive voice is known
Other system enough realizes the function integrations services such as speech recognition, phonetic synthesis and voice transfer, and multistage entry can be supported to identify
Function has and automatically selects and handoff functionality；With higher accuracy of identification and recognition efficiency；Use scope is wide, can be with cloud
End is communicated.
In order to achieve the above object, the utility model is using technical solution：A kind of high sensitivity speech recognition system, including
Voice collecting circuit, speech recognition circuit, radio communication circuit, local interface, speech processing circuit and voice transmission circuit, institute
Predicate sound Acquisition Circuit, speech recognition circuit, speech processing circuit and voice transmission circuit are sequentially connected, the speech recognition electricity
Road and voice transmission circuit are connected to radio communication circuit, and the radio communication circuit is connected with each other with speech processing circuit,
Local interface is also associated on the voice transmission circuit, the speech processing circuit is additionally coupled to voice collecting circuit；It is described
Radio communication circuit and high in the clouds are wirelessly connected, and the high in the clouds includes speech database, the radio communication circuit also with outside
Phonetic incepting client wireless connects, and the local interface is connected with local device.
Further, the voice collecting circuit includes reception antenna, receiving interface, Mai Xin, switch unit, denoising list
Member and amplifying unit, the receiving interface, reception antenna and wheat core are connected to switch unit side by side, and the switch unit is connected to
Denoising unit, the denoising unit are connected to amplifying unit；Local voice signal is received by receiving interface, passes through reception antenna
Radio audio signals are received, real-Time Speech Signals are received by wheat core；To realize multiport access and selection, it is logical to improve system
The property used.
Further, to realize the switching and conversion of multiport multi-standard, enhance the versatility of system；The voice hair
Power transmission road includes the signal adapter being connected with each other and sends switching circuit, passes through the system of signal adapter converting speech data
Formula switches the method for salary distribution of voice data by sending switching circuit.
Further, the speech recognition circuit is voice recognition chip, the radio communication circuit is 3G4G circuits
Or Wi-Fi circuit, the local interface are USB interface, serial line interface, parallel interface or bluetooth module, the speech processes electricity
Road is embedded microprocessor.
Using the advantageous effect of the technical program：
The utility model has the functions such as speech recognition, phonetic synthesis and voice transfer, supports multistage entry identification, has
It automatically selects and handoff functionality, universal performance is higher；
The utility model can effectively improve accuracy of identification by establishing artificial nerve network model, improve recognition efficiency,
There is higher discrimination under hybrid language environment；
The utility model expands use scope, and there are high in the clouds speech recognition platforms to have open interface, can pass through high in the clouds
Realize the adjustment to speech recognition system and data transmission.
Description of the drawings
Fig. 1 is a kind of structural schematic diagram of highly sensitive speech recognition system in the utility model embodiment one；
Fig. 2 is the structural schematic diagram of voice collecting circuit in the utility model embodiment two；
Fig. 3 is the structural schematic diagram of voice transmission circuit in the utility model embodiment three.
Specific implementation mode
In order to keep the purpose, technical scheme and advantage of utility model clearer, below in conjunction with the accompanying drawings to the utility model
It is further elaborated.
It is shown in Figure 1 in the present embodiment one, the utility model proposes a kind of highly sensitive speech recognition system,
Electricity is sent including voice collecting circuit, speech recognition circuit, radio communication circuit, local interface, speech processing circuit and voice
Road, the voice collecting circuit, speech recognition circuit, speech processing circuit and voice transmission circuit are sequentially connected, the voice
Identification circuit and voice transmission circuit are connected to radio communication circuit, and the radio communication circuit and speech processing circuit are mutual
It connects, is also associated with local interface on the voice transmission circuit, the speech processing circuit is additionally coupled to voice collecting circuit；
The radio communication circuit and high in the clouds are wirelessly connected, and the high in the clouds includes speech database, the radio communication circuit also with
External voice receives client wireless connection, and the local interface is connected with local device.
In embodiment two, on the basis of embodiment one, as shown in Fig. 2, the voice collecting circuit includes receiving day
Line, receiving interface, Mai Xin, switch unit, denoising unit and amplifying unit, the receiving interface, reception antenna and wheat core are arranged side by side
It is connected to switch unit, the switch unit is connected to denoising unit, and the denoising unit is connected to amplifying unit；Pass through reception
Interface local voice signal, radio audio signals are received by reception antenna, and real-Time Speech Signals are received by wheat core；From
And realize multiport access and selection, improve system versatility.
In embodiment three, on the basis of embodiment two, as shown in figure 3, for realize multiport multi-standard switching and
Conversion, enhances the versatility of system；The voice transmission circuit includes the signal adapter and transmission switching circuit of interconnection,
By the standard of signal adapter converting speech data, switch the method for salary distribution of voice data by sending switching circuit.
As the prioritization scheme of above-described embodiment, the speech recognition circuit is voice recognition chip, the wireless communication
Circuit be 3G4G circuits or Wi-Fi circuit, the local interface be USB interface, serial line interface, parallel interface or bluetooth module,
The speech processing circuit is embedded microprocessor.
In order to be better understood from the utility model, primary complete description is made to the operation principle of the utility model below：
First, voice collecting circuit acquires voice signal, and carries out denoising and amplification to voice signal, obtains pretreatment language
Sound signal；
Secondly, by speech recognition circuit, the pretreatment voice signal is subjected to multistage entry decomposition and establishes audio frame
Matrix transfers corresponding speech recognition modeling according to the audio frame matrix in the high in the clouds speech database；Know in voice
Corresponding phonetic element is matched in other model, obtains voice recognition data；
Then, voice recognition data is carried out to multistage entry combination in speech processing circuit, obtains voice data；
Finally, after voice data is converted and distributed by voice transmission circuit signal, local is transferred to by local interface
Equipment or by radio communication circuit transmission receive client to external voice.
Basic principles, main features, and advantages of the present invention has been shown and described above.One's own profession
The technical staff of industry is it should be appreciated that the present utility model is not limited to the above embodiments, described in above embodiments and description
Only illustrate the principles of the present invention, on the premise of not departing from the spirit and scope of the utility model, the utility model is also
It will have various changes and improvements, these various changes and improvements fall within the scope of the claimed invention.The utility model
Claimed range is defined by the appending claims and its equivalent thereof.
Claims (4)
1. a kind of high sensitivity speech recognition system, which is characterized in that including voice collecting circuit, speech recognition circuit, wireless
Telecommunication circuit, local interface, speech processing circuit and voice transmission circuit, the voice collecting circuit, speech recognition circuit, language
Sound processing circuit and voice transmission circuit are sequentially connected, and the speech recognition circuit and voice transmission circuit are connected to channel radio
Believe that circuit, the radio communication circuit are connected with each other with speech processing circuit, local is also associated on the voice transmission circuit
Interface, the speech processing circuit are additionally coupled to voice collecting circuit；The radio communication circuit is wirelessly connected with high in the clouds, described
High in the clouds includes speech database, and the radio communication circuit also receives client wireless with external voice and connect, the local
Interface is connected with local device.
2. a kind of highly sensitive speech recognition system according to claim 1, which is characterized in that the voice collecting circuit
Including reception antenna, receiving interface, Mai Xin, switch unit, denoising unit and amplifying unit, the receiving interface, reception antenna
It is connected to switch unit side by side with wheat core, the switch unit is connected to denoising unit, and it is single that the denoising unit is connected to amplification
Member.
3. a kind of highly sensitive speech recognition system according to claim 2, which is characterized in that the voice transmission circuit
Signal adapter including interconnection and transmission switching circuit.
4. a kind of highly sensitive speech recognition system according to any one of claim 1-3, which is characterized in that described
Speech recognition circuit is voice recognition chip, and the radio communication circuit is 3G4G circuits or Wi-Fi circuit, the local interface
For USB interface, serial line interface, parallel interface or bluetooth module, the speech processing circuit is embedded microprocessor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820065972.2U CN207690495U (en) | 2018-01-16 | 2018-01-16 | A kind of high sensitivity speech recognition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820065972.2U CN207690495U (en) | 2018-01-16 | 2018-01-16 | A kind of high sensitivity speech recognition system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN207690495U true CN207690495U (en) | 2018-08-03 |
Family
ID=62991736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201820065972.2U Expired - Fee Related CN207690495U (en) | 2018-01-16 | 2018-01-16 | A kind of high sensitivity speech recognition system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN207690495U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108022593A (en) * | 2018-01-16 | 2018-05-11 | 成都福兰特电子技术股份有限公司 | A kind of high sensitivity speech recognition system and its control method |
-
2018
- 2018-01-16 CN CN201820065972.2U patent/CN207690495U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108022593A (en) * | 2018-01-16 | 2018-05-11 | 成都福兰特电子技术股份有限公司 | A kind of high sensitivity speech recognition system and its control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN205792848U (en) | The portable power source of band digital intercom module based on intelligent mobile terminal | |
| CN207690495U (en) | A kind of high sensitivity speech recognition system | |
| CN107071603A (en) | A kind of microphone and system for Real-time speech recognition | |
| CN105406883A (en) | Wireless communication device | |
| CN208000328U (en) | A kind of electric energy meter system of wireless blue tooth output | |
| CN108022593A (en) | A kind of high sensitivity speech recognition system and its control method | |
| CN104835301A (en) | Wireless data transmission device for medical equipment | |
| CN211531083U (en) | Artificial intelligence pronunciation transfer device and USB artificial intelligence pronunciation transfer device | |
| CN212543775U (en) | Wireless conference system for large-scale meeting place | |
| CN205160805U (en) | Radio communication gateway | |
| CN206894637U (en) | Bluetooth and Wifi communication relay devices | |
| CN105243036A (en) | Signal conversion apparatus and method | |
| CN204390466U (en) | Operational order collection plate | |
| CN103139879B (en) | A kind of wireless personal local area network communication system | |
| CN103136924B (en) | A kind of multifunction remote-controller | |
| CN208971545U (en) | A kind of asset management gateway apparatus and the asset management system | |
| CN105897894A (en) | Internet of things universal acquisition device integrator | |
| CN201750567U (en) | 3G multi-card multi-mode high-speed wireless collecting and transmitting device | |
| CN206331386U (en) | Wireless mouse control system based on zigBee communication | |
| CN202206495U (en) | Intelligent wireless digital transmission command system | |
| CN205510048U (en) | Radio communication of multisystem forwards device | |
| CN206183242U (en) | Skin moisture oil content detection device and detecting system based on acoustic wave transmission | |
| CN203414162U (en) | Electronic scale using audio frequency to transmit data | |
| CN201499168U (en) | Mobile terminal infra-ray circuit and mobile terminal for connecting SIM card | |
| CN109586746A (en) | A kind of Multifunctional English intercom in tourist attraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180803 Termination date: 20190116 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |