CN103561303A - Television interaction device and method based on audio fingerprints - Google Patents

Television interaction device and method based on audio fingerprints Download PDF

Info

Publication number
CN103561303A
CN103561303A CN201310512978.1A CN201310512978A CN103561303A CN 103561303 A CN103561303 A CN 103561303A CN 201310512978 A CN201310512978 A CN 201310512978A CN 103561303 A CN103561303 A CN 103561303A
Authority
CN
China
Prior art keywords
audio
frequency fingerprint
television
frequency
interaction
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
Application number
CN201310512978.1A
Other languages
Chinese (zh)
Inventor
李学生
吴文杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201310512978.1A priority Critical patent/CN103561303A/en
Publication of CN103561303A publication Critical patent/CN103561303A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The invention discloses a television interaction device and method based on audio fingerprints. The device comprises a cell phone client unit and a television program unit. The cell phone client unit is connected to the television program unit through a broadcast television network. The method comprises a television interaction method and a cell phone interaction method. The television interaction method comprises the working processes of program dotting, audio decoding, audio preprocessing, audio characteristic analysis, audio characteristic extraction, audio fingerprint generation, and audio fingerprint storage. The cell phone interaction method comprises the working processes of audio recording, audio preprocessing, audio characteristic analysis, audio characteristic extraction, audio fingerprint generation, audio fingerprint uploading search, and interaction content obtaining. An encoder extracts the audio characteristics of a planned interaction period in television programs and then places the audio characteristics into an audio fingerprint database. After programs are played through a television, software of the cell phone side collects seconds of audio samples, extracts characteristics, searches the position of fingerprints of the samples in the audio fingerprint database through a search engine, and returns the fingerprints to the cell phone through ID.

Description

A kind of TV interaction device and method based on audio-frequency fingerprint
Technical field
The invention belongs to television interaction method technical field, relate in particular to a kind of TV interaction device and method based on audio-frequency fingerprint.
Background technology
Television interaction method is the Generation Tv based on Digital Television and broadband network technology, it is the perfect adaptation of TV science and technology and fashionable life, can provide can program request highly personalized and the interactive highlight of having, bring the brand-new experience of watching, allow spectator really become the owner of TV.Voice data information can easily be not associated with interaction content information.
Summary of the invention
The object of the present invention is to provide a kind of TV interaction device and method based on audio-frequency fingerprint, be intended to solve the problem that voice data information and interaction content information can easily be not associated.
The present invention is achieved in that a kind of TV interaction device based on audio-frequency fingerprint, and this device comprises mobile phone customer unit, TV programme unit.Mobile phone customer unit is by CHINA RFTCOM Co Ltd connecting TV program cells.
Further, mobile phone customer unit is provided with apparatus for processing audio.
Further, TV programme unit is provided with encoder.
Another object of the present invention is to provide a kind of television interaction method based on audio-frequency fingerprint, the method comprises television interaction method and mobile phone interactive approach.The workflow of television interaction method is: program is got ready, audio decoder, and audio frequency preliminary treatment, Audio feature analysis, audio feature extraction, audio-frequency fingerprint generates, audio-frequency fingerprint warehouse-in; The workflow of mobile phone interactive approach is: audio sound-recording, and audio frequency preliminary treatment, Audio feature analysis, audio feature extraction, audio-frequency fingerprint generates, and audio-frequency fingerprint is uploaded search, and interaction content obtains.
Further, audio frequency preliminary treatment mainly comprise audio preemphasis, postemphasis, digital filtering, voice enhancing etc.
Further, Audio feature analysis method relates generally to Short Time Fourier Transform analysis, wavelet transformation domain analysis, cepstral analysis, linear prediction analysis, Fractal Analysis etc.
Further, audio feature extraction, the method based on energy spectrum peak, first carries out digital filtering processing to every frame data in sound spectrograph, then, according to the energy dependence between frame and frame, extracts local maximum, as audio frequency characteristics point.
Further, audio-frequency fingerprint generates, and characteristic point is done to quick Hash and process, the index value using cryptographic Hash as audio-frequency fingerprint database.
TV interaction device and method based on audio-frequency fingerprint provided by the invention, encoder is putting into audio-frequency fingerprint database after the audio feature extraction of interactive time period of plan in TV programme, and to this time period interactive event.Such as ID and the content of prize drawing, ballot, advertisement etc. are put into interaction content database.After program through television broadcasts, the audio sample of mobile phone terminal software collection several seconds, extract after feature, by search engine, search for the position of this section of sample fingerprint in audio-frequency fingerprint database, get the corresponding audio frequency ID of this section audio, and then get interactive event ID and the interaction content that audio frequency ID is corresponding, be back to mobile phone.
Accompanying drawing explanation
Fig. 1 is a kind of TV interaction equipment mechanism schematic diagram based on audio-frequency fingerprint provided by the invention;
Fig. 2 is a kind of television interaction method flow chart based on audio-frequency fingerprint provided by the invention;
Fig. 3 is encoder inter-work flow chart provided by the invention;
Fig. 4 is mobile phone terminal inter-work flow chart provided by the invention;
In figure: 1, mobile phone customer unit; 2, TV programme unit.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with embodiment, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Fig. 1 is a kind of TV interaction equipment mechanism schematic diagram based on audio-frequency fingerprint provided by the invention, and this device comprises mobile phone customer unit 1 and TV programme unit 2.Mobile phone customer unit 1 is by CHINA RFTCOM Co Ltd connecting TV program cells 2.
Mobile phone customer unit 1 is provided with apparatus for processing audio, apparatus for processing audio is recorded to television audio, obtain the sample sound of several seconds, then carry out noise suppression preprocessing, Audio feature analysis, feature extraction and fingerprint generate and are all consistent with encoder-side, after the fingerprint of sample sound generates, by network, be uploaded to search engine, in audio-frequency fingerprint database, according to each cryptographic Hash in sample fingerprint, search out corresponding movable ID, and then get corresponding interaction content, be shown to user.TV programme unit 2 is provided with encoder, and encoder is putting into audio-frequency fingerprint database after the audio feature extraction of interactive time period of plan in TV programme, and the ID of this time period interactive event and content are put into interaction content database.
Fig. 2 is a kind of television interaction method flow chart based on audio-frequency fingerprint provided by the invention, and the method comprises television interaction method and mobile phone interactive approach.The workflow of television interaction method is: program is got ready, audio decoder, and audio frequency preliminary treatment, Audio feature analysis, audio feature extraction, audio-frequency fingerprint generates, audio-frequency fingerprint warehouse-in; The workflow of mobile phone interactive approach is: audio sound-recording, and audio frequency preliminary treatment, Audio feature analysis, audio feature extraction, audio-frequency fingerprint generates, and audio-frequency fingerprint is uploaded search, and interaction content obtains.
Fig. 3 is encoder inter-work flow chart provided by the invention, and Fig. 4 is mobile phone terminal inter-work flow chart provided by the invention.Audio frequency preliminary treatment mainly comprises audio preemphasis, postemphasises, digital filtering, voice enhancing etc.Audio feature analysis method relates generally to Short Time Fourier Transform analysis, wavelet transformation domain analysis, cepstral analysis, linear prediction analysis, Fractal Analysis etc.Audio feature extraction, the method based on energy spectrum peak, first carries out digital filtering processing to every frame data in sound spectrograph, then, according to the energy dependence between frame and frame, extracts local maximum, as audio frequency characteristics point.Audio-frequency fingerprint generates, and characteristic point is done to quick Hash and process, the index value using cryptographic Hash as audio-frequency fingerprint database.
Interaction is the method based on audio-frequency fingerprint, audio frequency characteristics is that the method based on energy spectrum peak is chosen, audio-frequency fingerprint adopts the generation method based on quick Hash, fingerprint database and interaction content database are based on cloud framework, interaction content and movable ID are mutually related with fingerprint database, this interactive approach, not only for TV, is also used audio frequency as the occasion of the information transmission channel for broadcasting station, Public Media etc.
TV interaction device and method based on audio-frequency fingerprint provided by the invention, encoder is putting into audio-frequency fingerprint database after the audio feature extraction of interactive time period of plan in TV programme, and to this time period interactive event.Such as ID and the content of prize drawing, ballot, advertisement etc. are put into interaction content database.After program through television broadcasts, the audio sample of mobile phone terminal software collection several seconds, extract after feature, by search engine, search for the position of this section of sample fingerprint in audio-frequency fingerprint database, get the corresponding audio frequency ID of this section audio, and then get interactive event ID and the interaction content that audio frequency ID is corresponding, be back to mobile phone.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.

Claims (8)

1. the television interaction method based on audio-frequency fingerprint, is characterized in that, the method comprises television interaction method and mobile phone interactive approach; The workflow of television interaction method is: program is got ready, audio decoder, and audio frequency preliminary treatment, Audio feature analysis, audio feature extraction, audio-frequency fingerprint generates, audio-frequency fingerprint warehouse-in; The workflow of mobile phone interactive approach is: audio sound-recording, and audio frequency preliminary treatment, Audio feature analysis, audio feature extraction, audio-frequency fingerprint generates, and audio-frequency fingerprint is uploaded search, and interaction content obtains.
2. the television interaction method based on audio-frequency fingerprint as claimed in claim 1, is characterized in that, audio frequency preliminary treatment mainly comprises audio preemphasis, postemphasises, digital filtering, voice strengthen.
3. the television interaction method based on audio-frequency fingerprint as claimed in claim 1, is characterized in that, Audio feature analysis method relates generally to Short Time Fourier Transform analysis, wavelet transformation domain analysis, cepstral analysis, linear prediction analysis, Fractal Analysis.
4. the television interaction method based on audio-frequency fingerprint as claimed in claim 1, it is characterized in that, audio feature extraction, method based on energy spectrum peak, first every frame data in sound spectrograph are carried out to digital filtering processing, then according to the energy dependence between frame and frame, extract local maximum, as audio frequency characteristics point.
5. the television interaction method based on audio-frequency fingerprint as claimed in claim 1, is characterized in that, audio-frequency fingerprint generates, and characteristic point is done to quick Hash and process, the index value using cryptographic Hash as audio-frequency fingerprint database.
6. the TV interaction device based on audio-frequency fingerprint, is characterized in that, this device comprises mobile phone customer unit, TV programme unit; Mobile phone customer unit is by CHINA RFTCOM Co Ltd connecting TV program cells.
7. the TV interaction device based on audio-frequency fingerprint as claimed in claim 1, is characterized in that, mobile phone customer unit is provided with apparatus for processing audio.
8. the TV interaction device based on audio-frequency fingerprint as claimed in claim 1, is characterized in that, TV programme unit is provided with encoder.
CN201310512978.1A 2013-10-28 2013-10-28 Television interaction device and method based on audio fingerprints Pending CN103561303A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310512978.1A CN103561303A (en) 2013-10-28 2013-10-28 Television interaction device and method based on audio fingerprints

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310512978.1A CN103561303A (en) 2013-10-28 2013-10-28 Television interaction device and method based on audio fingerprints

Publications (1)

Publication Number Publication Date
CN103561303A true CN103561303A (en) 2014-02-05

Family

ID=50015435

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310512978.1A Pending CN103561303A (en) 2013-10-28 2013-10-28 Television interaction device and method based on audio fingerprints

Country Status (1)

Country Link
CN (1) CN103561303A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104361889A (en) * 2014-10-28 2015-02-18 百度在线网络技术(北京)有限公司 Audio file processing method and device
CN105872089A (en) * 2016-05-26 2016-08-17 无锡天脉聚源传媒科技有限公司 Method and device for transmitting audio characteristics

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104361889A (en) * 2014-10-28 2015-02-18 百度在线网络技术(北京)有限公司 Audio file processing method and device
CN104361889B (en) * 2014-10-28 2018-03-16 北京音之邦文化科技有限公司 Method and device for processing audio file
CN105872089A (en) * 2016-05-26 2016-08-17 无锡天脉聚源传媒科技有限公司 Method and device for transmitting audio characteristics

Similar Documents

Publication Publication Date Title
CN103123787B (en) A kind of mobile terminal and media sync and mutual method
CN104023247B (en) The method and apparatus of acquisition, pushed information and information interaction system
US9219559B2 (en) Methods and systems for audience measurement
US20140196070A1 (en) System and method for automated broadcast media identification
US20140278845A1 (en) Methods and Systems for Identifying Target Media Content and Determining Supplemental Information about the Target Media Content
US20120317241A1 (en) Methods and Systems for Performing Comparisons of Received Data and Providing a Follow-On Service Based on the Comparisons
US11848030B2 (en) Audio encoding for functional interactivity
CN106340291A (en) Bilingual subtitle production method and system
CN103402118A (en) Media program interaction method and system
CN103347070B (en) Push method, terminal, server and the system of speech data
WO2014199357A1 (en) Hybrid video recognition system based on audio and subtitle data
CN106162321A (en) The audio signal identification method that a kind of vocal print feature and audio frequency watermark combine
CN103200429B (en) The method and system interacted with the advertisement in TV, radio station
US20190124380A1 (en) Methods and Systems for Determining a Latency Between a Source and an Alternative Feed of the Source
CN103108229A (en) Method for identifying video contents in cross-screen mode through audio frequency
CN103594083A (en) Technology of television program automatic identification through television accompanying sound
WO2014043969A1 (en) Information transmission method and device
CN103561303A (en) Television interaction device and method based on audio fingerprints
CN103716647A (en) Method for achieving dual-channel stereophonic effect when multichannel surround sound video and audio are played
CA2827514A1 (en) Methods and systems for identifying content in a data stream by a client device
CN103489119A (en) Advertisement monitoring method, device and system
WO2012126406A2 (en) Method and system for researching viewership
Bisio et al. Opportunistic estimation of television audience through smartphones
CN104202628B (en) The identifying system and method for client terminal playing program
CN104349183B (en) The method of the collection medium audience staining effect realized by sound channel

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
DD01 Delivery of document by public notice
DD01 Delivery of document by public notice

Addressee: Li Xuesheng

Document name: Notification of Passing Preliminary Examination of the Application for Invention

C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20140205