CN208368162U - A kind of intelligent sound case - Google Patents

Abstract

The utility model belongs to field of computer technology, disclose a kind of intelligent sound case, dc power interface, USB interface, HDMI input interface, HDMI output interface, audio output interface, linear input interface are housed, mainboard is bolted on the inside of shell before the rear end of shell；Mainboard is connect by signal wire with dc power interface, USB interface, HDMI input interface, HDMI output interface, audio output interface, linear input interface.The terminal intelligent equipment of the utility model designs small and exquisite, standard interface, can connect with common Universal peripheral；It is cheap, it is powerful, artificial simultaneous interpretation is overturned, the artificial simultaneous interpretation expense of great number is saved；It can be applied to various news conference scenes, it is flexibly and easily, unrestricted.

Description

A kind of intelligent sound case

Technical field

The utility model belongs to field of computer technology more particularly to a kind of intelligent sound case.

Background technique

Currently, the prior art commonly used in the trade is such that Intelligent hardware is that a science and technology after smart phone is general It reads, by way of software and hardware combining, traditional equipment is transformed, and then it is allowed to possess intelligentized function.Intelligence Afterwards, hardware has the ability of connection, realizes the load of Internet service, forms the typical architecture of " cloud+end ", has big data Etc. surcharges.

In conclusion problem of the existing technology is:

Hardware device is not smart enough, needs through the artificial simultaneous interpretation cooperating of interpreter, artificial simultaneous interpretation somewhat expensive；Originally Equipment price is expensive, and dependence is strong, and installation is complicated；Mechanical translation quality is poor；Speech recognition, TTS effect are bad.

Solve the difficulty and meaning of above-mentioned technical problem:

Elevator turns over, speech recognition and TTS, needs the parallel corpus data of a large amount of, multi-lingual, multi-field high quality and audio number According to the data acquisition of this high quality is more difficult；It also needs algorithm neural network based to support simultaneously, optimizes boosting algorithm It is also a crucial step.

Support a variety of Peripheral Interfaces, it is general as far as possible, realize that multiplex roles are general on the box of a very little, it is also very in distress Degree.

Artificial simultaneous interpretation somewhat expensive, needs to solve, and reduces simultaneous interpretation cost, such as improves machine translation, TTS, speech recognition quality, Gradually make technical treatment close to artificial treatment；

It is strong to solve equipment interface dependence, challenge is installed, realizes general；

Based on neural network machine translation algorithm, pass through multi-field a large amount of corpus datas, training machine translation model；

Utility model content

In view of the problems of the existing technology, the utility model provides a kind of intelligent sound case.

The utility model is realized in this way a kind of intelligent sound case, the intelligent sound case is provided with

Shell；

Before the rear end of the shell equipped with dc power interface, USB interface, HDMI input interface, HDMI output interface, Audio output interface, linear input interface；

Mainboard is bolted on the inside of the shell；

The mainboard by signal wire and dc power interface, USB interface, HDMI input interface, HDMI output interface, Audio output interface, the connection of linear input interface.

Further, the shell includes: upper cover and bottom.

Further, the mainboard be integrated with CPU, memory, network support WIFI, USB interface, HDMI IN, HDMI OUT, Mike, USB interface Mike, 3.5mm interface Mike and wireless microphone, 3.5mm audio output, bluetooth, infrared remote control.

In conclusion the advantages of the utility model and good effect are as follows:

Hardware device and hand fit are realized the mode of simultaneous interpretation business scenario by the utility model, become will have Intelligent hardware Equipment is completed, and not only liberation is artificial, reduces cost, but also improve work efficiency.

The terminal intelligent equipment of the utility model designs small and exquisite, standard interface, can connect with common Universal peripheral；Price is low It is honest and clean, it is powerful, artificial simultaneous interpretation is overturned, the artificial simultaneous interpretation expense of great number is saved；The design of smart machine can be applied to various publications Meeting scene, it is flexibly and easily, unrestricted.

For the utility model by evaluation and test, the machine that equipment uses, which turns over, turns over effect also than Baidu, Google's machine in part verbal direction It is better；The utility model major part language voice recognition accuracy reaches 99%；The utility model TTS voice broadcast has connect Person of modern times's work is read aloud；The utility model terminal device supports common external equipment, and supporting rate is high.

Detailed description of the invention

Fig. 1 is intelligent sound box structure schematic diagram provided by the embodiment of the utility model；

Fig. 2 is dc power interface provided by the embodiment of the utility model, USB interface, HDMI input interface, HDMI output Interface, audio output interface, linear input interface schematic diagram；

In figure: 1, shell；2, dc power interface；3, USB interface；4, HDMI input interface；5, HDMI output interface；6, Audio output interface；7, linear input interface；8, mainboard.

Fig. 3 is mainboard structure schematic diagram provided by the embodiment of the utility model.

Specific embodiment

In order to make the purpose of the utility model, technical solutions and advantages more clearly understood, with reference to embodiments, to this Utility model is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain that this is practical It is novel, it is not used to limit the utility model.

As depicted in figs. 1 and 2, intelligent sound case provided by the embodiment of the utility model includes: that shell 1, DC power supply connect Mouth 2, USB interface 3, HDMI input interface 4, HDMI output interface 5, audio output interface 6, linear input interface 7, mainboard 8.

Before the rear end of shell 1 equipped with dc power interface 2, USB interface 3, HDMI input interface 4, HDMI output interface 5, Audio output interface 6, linear input interface 7, mainboard 8 are bolted on the inside of shell 1；Mainboard 8 by signal wire with Dc power interface 2, USB interface 3, HDMI input interface 4, HDMI output interface 5, audio output interface 6, linear input connect Mouth 7 connects.8 model pk3288 of mainboard.

Shell 1 includes: upper cover and bottom；Upper cover is plastic shell；Bottom is full aluminium outsole.

Dc power interface 2 is 1*5V DC power supply, and audio output interface 6 is 3.5mm audio output, linear input interface 7 be 3.5mm LineIn.

CPURockchip3288 chip, memory 2G DDR3, onboard storage 16G eMMC are also integrated on mainboard 8 FLASH, operating system Android 5.1, display resolution 1080P/4K, network support WIFI (2.4G/5G double frequency), 1 road USB connect Mouthful, 1 road HDMI IN, resolution ratio 1080P, 1 road HDMI OUT resolution ratio 1080P/4K, built-in Mike, USB interface Mike, 3.5mm interface Mike and wireless microphone (can allow multiple wireless microphones), 1 road 3.5mm audio output, bluetooth, infrared remote control.

The intelligent sound case outer dimension that the embodiments of the present invention provide is no more than 88*88*88mm；Outer casing upper cover table The high light processing in face, black；Full aluminium outsole, appearance is magnificent, and can auxiliary heat dissipation, have both functional and ornamental value；Top surface printing LanguageBox brand LOGO enhances built-in Mike's radio reception effect.Support a variety of audio input modes: built-in Mike, USB connect Mouth Mike, 3.5mm interface LineIn or wireless microphone.Development interface is provided, can choose audio input mode, and get use The audio stream of family input, to carry out speech recognition.It supports HDMI input, development interface is provided, can separate in HDMI input Audio and video, so as to audio therein carry out speech recognition.It supports HDMI input, development interface, mainboard handle is provided Video and translation result splicing in HDMI input, and large-size screen monitors are output to by HDMI OUT.It supports remote controller operation, for example selects Select speech recognition languages, human translation and machine translation, calling manual service etc..

The scalability requirement of the utility model: 1) HDMI output resolution ratio is defaulted as 1080P, can be extended to 4K resolution Rate.2) 2.4G/5G double frequency WIFI built in, scalable radio screen projection function.3) built Bluetooth module, expansible blue tooth wireless communication Function.

Intelligent sound case provided by the embodiment of the utility model, the following steps are included: preparation, is arranged terminal when operation Device parameter, such as language direction, wifi；News conference scene audio-video is collected by video and audio collecting device；Acquisition Audio/video flow is passed to terminal device by HDMI interface；Terminal device system identification audio stream and video flowing；By the audio of identification It spreads and gives object language speech recognition interface；The text that speech recognition goes out is transmitted to machine translation service interface, carries out machine and turns over It translates；Text after machine translation combines the video flowing of identification, handles the video flowing of anamorphic zone subtitlen；Text after machine translation Word is transmitted to TTS interface service, changes into translation voice flow；Audio is exported by HDMI interface and gives news conference field control station equipment； Video and audio are used to throw screen display and simultaneous interpretation earphone by news conference field control station.Intelligence provided by the embodiment of the utility model The hardware of voice case should ensure that advance, the ease for use of product, the controllability of volume production cost, the stability of system, reliability, can Maintainability, scalability and safety meet the overall construction requirements of IT product.

The above is only the preferred embodiment of the utility model only, is not intended to limit the utility model, all at this Made any modifications, equivalent replacements, and improvements etc., should be included in the utility model within the spirit and principle of utility model Protection scope within.

Claims (3)

1. a kind of intelligent sound case, which is characterized in that the intelligent sound case is provided with

Shell；

It is defeated equipped with dc power interface, USB interface, HDMI input interface, HDMI output interface, audio before the rear end of the shell Outgoing interface, linear input interface；

Mainboard is bolted on the inside of the shell；

The mainboard is defeated by signal wire and dc power interface, USB interface, HDMI input interface, HDMI output interface, audio Outgoing interface, the connection of linear input interface.

2. intelligent sound case as described in claim 1, which is characterized in that the shell includes: upper cover and bottom.

3. intelligent sound case as described in claim 1, which is characterized in that the mainboard is integrated with CPU, memory, network support WIFI, USB interface, HDMI IN, HDMI OUT, Mike, USB interface Mike, 3.5mm interface Mike and wireless microphone, 3.5mm Audio output, bluetooth, infrared remote control.