CN104796751A - Television signal recognition method and device - Google Patents
Television signal recognition method and device Download PDFInfo
- Publication number
- CN104796751A CN104796751A CN201510195507.1A CN201510195507A CN104796751A CN 104796751 A CN104796751 A CN 104796751A CN 201510195507 A CN201510195507 A CN 201510195507A CN 104796751 A CN104796751 A CN 104796751A
- Authority
- CN
- China
- Prior art keywords
- television
- signal
- vocal print
- voice
- channel
- 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
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention relates to a television signal recognition method and device. The method includes: a user controls a television end to record the voice signals of a current channel; the television end extracts the vocal print signals of the recorded channel voice signals, uploads the vocal print signals to a network server through a network, and matches the vocal print signals with the vocal print library in the network server; the vocal print signals are returned to the television end and displayed on the screen of the television end. The device comprises the channel voice collecting module of the television end, the vocal print extracting module of the television end, the vocal print library of the server end and a matching module. The television signal recognition method and device has the advantages that television behaviors are controlled by intelligent voices, the voice signals of a playing television program are recognized by the aid of the vocal print recognition technology and fed back to the user in real time, the method and device provides humanized interaction of the user and a television, the device is an intelligent device combining Internet cloud and the vocal print recognition and voice recognition technology, and good use experience and fun are brought to the user.
Description
Technical field
The present invention relates to intelligent television field, particularly a kind of TV signal knows method for distinguishing and device.
Background technology
In recent years along with the development of intelligent TV set, people used the frequency of intelligent TV set more and more higher, and the rich content of network machine top box and traditional closed-circuit television more and more selects then to user.But meanwhile, in the face of increasing TV information, user also can run into a large amount of unknown content, such as unacquainted star, the film etc. be ignorant of, now can only be inquired about by other modes such as inquiry or web search.These modes are bringing a lot of drawback, as time delay and nonautonomy to user to unknown content inquiry.
Sound groove recognition technology in e, is a technology according to speech waveform determination speech source uniqueness, automatically can identifies the technology of speaker and source of sound.If we can collect the television channel source of sound that user needs to carry out inquiring about, user just can be helped automatically to carry out searching for and inquire corresponding result.Independence is mutual in terms of content greatly can to improve user and television.
Summary of the invention
A kind of contributing to is the object of the present invention is to provide to solve user and TV signal end mutual blind area in terms of content, for user provides larger TV to use the TV signal of enjoyment to know method for distinguishing and device.
For achieving the above object, technical scheme of the present invention is: a kind of TV signal knows method for distinguishing, comprises the steps,
Step S1: user carries out the recording of current channel voice signal by controlling television;
Step S2: the vocal print signal of the channel voice signal that television extraction step S1 records, is uploaded to the webserver by this vocal print signal by network, and mate with the sound vocal print storehouse in this webserver;
Step S3: the matching result of vocal print signal is returned television, and is shown on the screen of television.
In embodiments of the present invention, the specific implementation step of described step S1 is as follows,
Step S11: user gathers user speech control signal by the voice acquisition module on remote controller;
Step S12: described user speech control signal is sent to television by remote controller, and carry out voice match by the sound bank that television is sent to network high in the clouds;
Step S13: network high in the clouds sends voice match result to television, and then control the recording of current channel voice signal.
In embodiments of the present invention, before described step S2, also need the channel voice signal to step S1 records to carry out preliminary treatment, comprise stress release treatment and voice signal amplification process.
In embodiments of the present invention, the recording of described channel voice signal realizes in the following manner: directly carry out channel speech signal collection or utilize putting end outside television and carrying out channel speech signal collection at the phonetic entry end of the Set Top Box of television.
In embodiments of the present invention, before described step S2, the Set Top Box of described television first can send current channel number, the webserver can list program featured performer list according to existing time and channel program list correspondence, and then the webserver searches out vocal print signal corresponding to sound vocal print storehouse in advance according to featured performer list.
Present invention also offers a kind of device of TV signal identification, comprise television and network server end, described television comprises the channel voice acquisition module for carrying out the recording of channel voice signal and recorded frequency voice signal is carried out to the voiceprint extraction module of vocal print signal extraction, and described network server end comprises the voice print matching module that the vocal print storehouse that stores vocal print signal and the vocal print signal for uploading voiceprint extraction module mate.
In embodiments of the present invention, also comprise a remote controller and network high in the clouds, described remote controller comprise to user speech control signal carry out gathering voice acquisition module with for realizing remote controller that remote controller communicates with television and television communication module, described network high in the clouds comprises sound bank and the voice match module for match user audio controls.
Compared to prior art, the present invention has following beneficial effect: decrease the search time of user for TV programme unknown content, adds interactivity and the experience of user and intelligent television.
Accompanying drawing explanation
Fig. 1 is the particular flow sheet that method of the present invention is implemented.
Fig. 2 is the sub-module figure of device scheme one of the present invention.
Fig. 3 is the sub-module figure of device scheme two of the present invention.
Fig. 4 is time m-programme corresponding to channel that the present invention mentions.
High priest's list of Fig. 5 position programme of the present invention.
Embodiment
Below in conjunction with accompanying drawing, technical scheme of the present invention is specifically described.
The present invention relates to a kind of TV signal and know method for distinguishing, as shown in Figure 1, carry out as follows:
A, user control by remote controller key the voice signal that television carries out current channel and record, and remote controller can control realization start and stop, thus admission set time voice signal.
The Set Top Box of B, television sends current channel number, the webserver can list program featured performer list (or occurring personage) according to existing time and channel program list correspondence, and the webserver searches out the corresponding voiceprint in vocal print storehouse in advance according to list.
C, television extract record the vocal print signal of channel voice.
D, the vocal print signal of extraction is uploaded to the webserver in television by network, carry out retrieval with sound vocal print storehouse in server and mate.
E, the matching result of vocal print returned television and is presented at video screen.
Below in conjunction with specific embodiment, above-mentioned steps is described in detail.
While carrying out steps A, we can select two kinds of modes to control the speech signal collection of television, mode one: communicate with television with conclusion button with the beginning of remote controller, control the regular length collection that television carries out channel voice signal.Mode two: utilize the remote controller of built-in voice acquisition module to carry out user speech collection, user says facing to remote controller and starts and terminate, and is sent to television after remote control acquires signal.Need after user speech collection to carry out the dry process that disappears, prevent background sound interference signal.
After above-mentioned steps completes, television can control the current channel number of transmitter top box to the webserver, server mates according to channel and channel time-programme (Fig. 4) that current time is obtaining, obtain actual program, high priest's list (Fig. 5) according to program filters out voiceprint in list, such as first mating the program of this period by Hunan platform is happy base camp, then what Gui the personage listing happy base camp has, Xie Na, Du Haitao, Wu Xin, Li Weijia, Deng Chao, Sun Li.Then what Gui, Xie Na, Du Haitao, Wu Xin, Li Weijia, Deng Chao is first listed in vocal print storehouse, the voiceprint of grandson pari.This step can increase follow-up vocal print search time and matching precision.
Control TV after carrying out step A and carry out channel speech signal collection, first can carry out preliminary treatment to voice signal, comprise background and disappear dry, wave volume regulates (if too little meeting increases), ensures that the source of sound carrying out voiceprint extraction is good.Next vocal print signal extraction can be carried out to voice signal according to the algorithm preset.
After obtaining vocal print signal, we are sent to server end by network vocal print signal, how mate with the program high priest voiceprint obtained, what such as suppose that user just now gathers is the voiceprint of Xie Na, so our Gui that just can obtain in advance, Xie Na, Du Haitao, Wu Xin, Li Weijia, Deng Chao, arrives with the voice print matching of thanking to Na in the voiceprint of grandson pari.
Finally we send back television by mating the information obtained, and are finally shown on the large-screen of television, complete final user's inquiry.
Based on the recognition methods of above-mentioned TV signal, present invention also offers a kind of device of TV signal identification.This device can be realized by two kinds of modes, and if accompanying drawing 2 is devices one, accompanying drawing 3 is devices two.
In device one: television channel voice acquisition module T1 is for gathering the current voice signal broadcasted, the remote controller of user can the beginning of control T1 and end.
Voiceprint extraction module T2 is that the voice signal for sending T1 carries out preliminary treatment, comprises disappear dry and volume of background and promotes (setting minimal volume threshold value, is less than threshold value and carries out lifting volume).Then can carry out voiceprint extraction with the algorithm preset in module to voice signal, obtain one section of vocal print signal.
Server vocal print storehouse and matching module T3 are that the vocal print signal for sending T2 mates in the vocal print storehouse of server, if the match is successful, return matching result to television, if unsuccessful, return null value.
In device two: remote controller voice acquisition module S1, for gathering the said order of user, comprises and starts and terminate.Change into voice signal and carry out the dry process that disappears.
The communication module S2 of remote controller and TV is used for the receiving terminal voice signal that S1 gathers being sent to television.
The voice signal that network high in the clouds sound bank and matching module S3 are used for television transmits mates with the signal of sound bank, if the match is successful, returns matching result to television, if do not have pool to return null value.
The collection of the voice signal play before the laggard trade of matching result that television channel voice acquisition module S4 obtains S3, then carries out disappear dry and volume of background to voice signal and promotes (setting minimal volume threshold value, is less than threshold value and carries out lifting volume).
Voiceprint extraction module S5 can carry out voiceprint extraction with the algorithm preset in module to voice signal, obtains one section of vocal print signal.
Server vocal print storehouse and matching module S6 are used for mating in the vocal print storehouse of server the vocal print signal that T2 sends, if the match is successful, return matching result to television, if unsuccessful, return null value.
Be more than preferred embodiment of the present invention, all changes done according to technical solution of the present invention, when the function produced does not exceed the scope of technical solution of the present invention, all belong to protection scope of the present invention.
Claims (7)
1. TV signal knows a method for distinguishing, it is characterized in that: comprise the steps,
Step S1: user carries out the recording of current channel voice signal by controlling television;
Step S2: the vocal print signal of the channel voice signal that television extraction step S1 records, is uploaded to the webserver by this vocal print signal by network, and mate with the sound vocal print storehouse in this webserver;
Step S3: the matching result of vocal print signal is returned television, and is shown on the screen of television.
2. a kind of TV signal according to claim 1 knows method for distinguishing, it is characterized in that: the specific implementation step of described step S1 is as follows,
Step S11: user gathers user speech control signal by the voice acquisition module on remote controller;
Step S12: described user speech control signal is sent to television by remote controller, and carry out voice match by the sound bank that television is sent to network high in the clouds;
Step S13: network high in the clouds sends voice match result to television, and then control the recording of current channel voice signal.
3. a kind of TV signal according to claim 1 knows method for distinguishing, it is characterized in that: before described step S2, also needs the channel voice signal to step S1 records to carry out preliminary treatment, comprises stress release treatment and voice signal amplification process.
4. a kind of TV signal according to claim 1 knows method for distinguishing, it is characterized in that: the recording of described channel voice signal realizes in the following manner: directly carry out channel speech signal collection or utilize putting end outside television and carrying out channel speech signal collection at the phonetic entry end of the Set Top Box of television.
5. a kind of TV signal according to claim 1 knows method for distinguishing, it is characterized in that: before described step S2, the Set Top Box of described television first can send current channel number, the webserver can list program featured performer list according to existing time and channel program list correspondence, and then the webserver searches out vocal print signal corresponding to sound vocal print storehouse in advance according to featured performer list.
6. the device of a TV signal identification, comprise television and network server end, it is characterized in that: described television comprises the channel voice acquisition module for carrying out the recording of channel voice signal and recorded frequency voice signal carried out to the voiceprint extraction module of vocal print signal extraction, described network server end comprises the voice print matching module that the vocal print storehouse that stores vocal print signal and the vocal print signal for uploading voiceprint extraction module mate.
7. the device of a kind of TV signal identification according to claim 6, it is characterized in that: also comprise a remote controller and network high in the clouds, described remote controller comprise to user speech control signal carry out gathering voice acquisition module with for realizing remote controller that remote controller communicates with television and television communication module, described network high in the clouds comprises sound bank and the voice match module for match user audio controls.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510195507.1A CN104796751A (en) | 2015-04-23 | 2015-04-23 | Television signal recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510195507.1A CN104796751A (en) | 2015-04-23 | 2015-04-23 | Television signal recognition method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104796751A true CN104796751A (en) | 2015-07-22 |
Family
ID=53561205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510195507.1A Pending CN104796751A (en) | 2015-04-23 | 2015-04-23 | Television signal recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104796751A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106254939A (en) * | 2016-09-30 | 2016-12-21 | 北京小米移动软件有限公司 | Information cuing method and device |
| CN107293293A (en) * | 2017-05-22 | 2017-10-24 | 深圳市搜果科技发展有限公司 | A kind of voice instruction recognition method, system and robot |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102833617A (en) * | 2012-09-20 | 2012-12-19 | 北京十分科技有限公司 | Method for synchronously displaying affiliated information of multimedia program, system and terminal |
| CN103607609A (en) * | 2013-11-27 | 2014-02-26 | Tcl集团股份有限公司 | Voice switching method and device for TV set channels |
| US20140181877A1 (en) * | 2012-12-20 | 2014-06-26 | Hulu, LLC | Device Activation Using Encoded Representation |
| CN104023247A (en) * | 2014-05-29 | 2014-09-03 | 腾讯科技（深圳）有限公司 | Methods and devices for obtaining and pushing information and information interaction system |
-
2015
- 2015-04-23 CN CN201510195507.1A patent/CN104796751A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102833617A (en) * | 2012-09-20 | 2012-12-19 | 北京十分科技有限公司 | Method for synchronously displaying affiliated information of multimedia program, system and terminal |
| US20140181877A1 (en) * | 2012-12-20 | 2014-06-26 | Hulu, LLC | Device Activation Using Encoded Representation |
| CN103607609A (en) * | 2013-11-27 | 2014-02-26 | Tcl集团股份有限公司 | Voice switching method and device for TV set channels |
| CN104023247A (en) * | 2014-05-29 | 2014-09-03 | 腾讯科技（深圳）有限公司 | Methods and devices for obtaining and pushing information and information interaction system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106254939A (en) * | 2016-09-30 | 2016-12-21 | 北京小米移动软件有限公司 | Information cuing method and device |
| CN107293293A (en) * | 2017-05-22 | 2017-10-24 | 深圳市搜果科技发展有限公司 | A kind of voice instruction recognition method, system and robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2018214121B2 (en) | Real-time digital assistant knowledge updates | |
| US9491517B2 (en) | Systems and methods for broadcast audience interaction and participation | |
| CN105120304B (en) | Information display method, apparatus and system | |
| CN104091423B (en) | A kind of method for transmitting signals and family's order programme | |
| US10166472B2 (en) | Methods and systems for determining a reaction time for a response and synchronizing user interface(s) with content being rendered | |
| CN102520789A (en) | Method and equipment for realizing voice control of controlled equipment | |
| CN104778946A (en) | Voice control method and system | |
| CN105227979B (en) | Audio frequency playing method and device based on smart television | |
| CN111741369B (en) | Smart television set top box based on voice recognition | |
| CN103607609A (en) | Voice switching method and device for TV set channels | |
| CN103618916A (en) | Internet video playing method based on smart television terminal | |
| CN110047497B (en) | Background audio signal filtering method and device and storage medium | |
| CN105897686A (en) | Smart television user account speech management method and smart television | |
| CN103945234A (en) | Video-related information providing method and device | |
| CN108551629A (en) | A kind of control method and system of Split intelligent speaker | |
| CN104796751A (en) | Television signal recognition method and device | |
| CN107657469A (en) | A kind of method for pushing of advertising message, device and set top box | |
| CN109237740A (en) | A kind of control method of electric appliance, device, storage medium and electric appliance | |
| CN104157279A (en) | Enhanced KTV song demand system with camera | |
| CN109979495B (en) | Audio progress intelligent following playing method and system based on face recognition | |
| CN103024581A (en) | Smart television and program interaction implementation method and program interaction implementation system thereof | |
| JP6433273B2 (en) | Terminal device, server device, and program | |
| WO2017008498A1 (en) | Method and device for searching program | |
| US20160275077A1 (en) | Method and apparatus for automatically sending multimedia file, mobile terminal, and storage medium | |
| CN110418243A (en) | A kind of intelligent sound box control system and control method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150722 |