KR20160043732A - Method and apparatus for providing a filtered voice - Google Patents

Method and apparatus for providing a filtered voice Download PDF

Info

Publication number
KR20160043732A
KR20160043732A KR1020140138305A KR20140138305A KR20160043732A KR 20160043732 A KR20160043732 A KR 20160043732A KR 1020140138305 A KR1020140138305 A KR 1020140138305A KR 20140138305 A KR20140138305 A KR 20140138305A KR 20160043732 A KR20160043732 A KR 20160043732A
Authority
KR
South Korea
Prior art keywords
media file
prohibited word
reproduced
providing
word
Prior art date
Application number
KR1020140138305A
Other languages
Korean (ko)
Inventor
김동건
Original Assignee
주식회사 인프라웨어
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 주식회사 인프라웨어 filed Critical 주식회사 인프라웨어
Priority to KR1020140138305A priority Critical patent/KR20160043732A/en
Publication of KR20160043732A publication Critical patent/KR20160043732A/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/439—Processing of audio elementary streams
    • H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/454—Content or additional data filtering, e.g. blocking advertisements
    • H04N21/4545—Input to filtering algorithms, e.g. filtering a region of the image
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/458—Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Storage Device Security (AREA)

Abstract

The present invention relates to a method and apparatus for providing filtered speech in a streaming manner, and a method and apparatus for providing filtered speech according to an embodiment of the present invention includes playing a media file, A step of recording a section in which a prohibited word is reproduced, and a step of giving a filtering effect so that a prohibited word is not audible to a user during a period in which the prohibited word is reproduced when the media file is reproduced. And an apparatus can be provided.

Description

METHOD AND APPARATUS FOR PROVIDING A FILTERED VOICE [0002]

The present invention relates to a method and apparatus for providing a voice in a streaming manner, and more particularly, to a method and apparatus for providing a voice by filtering a banned word when an unauthorized user includes the prohibited word.

Recently, with the development of wireless communication technology, a variety of media such as music, movies, and video lectures are being streamed. Various media including voice data are provided in a streaming manner. However, there is a need for a way to block the voice in the process of providing harmful music or harmful movie dialogue to the youth.

When broadcasting a harmful music to a youth or a movie containing a violent dialogue, a method of filtering the music or the voice of the movie through an individual work is provided. Recently, however, there is a need for a method of filtering voice more fundamentally in a situation where video files including various voices such as youtube are mass-produced and freely distributed by the general public.

Therefore, there is a need for a method and apparatus for filtering speech without any artificial processing other than a method of manually filtering harmful parts of speech.

Korean Patent No. 10-0639650 "VOD streaming service system and method" (registered on October 22, 2006)

SUMMARY OF THE INVENTION It is an object of the present invention to provide an apparatus and a method for filtering a voice including a banned speech and providing the voice including the voice without any artificial processing.

Another object of the present invention is to provide an apparatus and method for distinguishing original voice and filtered voice according to whether a user is authenticated.

The problems of the present invention are not limited to the above-mentioned problems, and other problems not mentioned can be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided a method of providing a filtered speech, the method comprising: reproducing a media file and scanning a prohibited word using a speech recognition algorithm; And providing a filtering effect so that a prohibited word can not be heard by the user in a period in which the prohibited word is reproduced when the media file is reproduced.

According to another aspect of the present invention, there is provided a method of providing a filtered speech comprising the steps of: playing a media file and scanning a prohibited word using a speech recognition algorithm; recording a section in which a prohibited word is reproduced; The step of giving a filtering effect so that the user can not hear a prohibited word during a period in which the media file is reproduced is executed when the media file is uploaded.

According to another aspect of the present invention, there is provided a method of providing filtered speech, the method comprising: playing a media file to search for a prohibited word using a speech recognition algorithm, And a step of searching for the lyrics determined to be prohibited by using a speech recognition algorithm.

According to another aspect of the present invention, there is provided a method of providing a filtered voice, the method comprising: storing information about a section of a period in which a prohibited word is reproduced, together with a media file.

According to another aspect of the present invention, there is provided a method of providing filtered speech, the method comprising the steps of: providing a filtering effect;

According to another aspect of the present invention, there is provided a method of providing filtered speech, wherein the step of providing a filtering effect is a method of blocking a sound by adding a beep to a section.

According to another aspect of the present invention, there is provided a method of providing a filtered speech, wherein the banned words can be added or deleted by updating the banned words.

According to another aspect of the present invention, there is provided a method of providing a filtered voice, the method comprising: providing a voice having a filtering effect only when a user fails to authenticate, when a media file is reproduced.

According to another aspect of the present invention, there is provided a method of providing filtered speech, wherein the media file is one of a music file and a moving picture file including a voice.

According to an aspect of the present invention, there is provided a media providing server for providing a filtered voice according to an exemplary embodiment of the present invention includes a communication unit for transmitting and receiving a media file, a media file, A storage unit, and a control unit for reproducing the media file and performing speech recognition, scanning, and filtering.

The present invention provides an apparatus and method for filtering and providing a voice including a banned speech to media including voice without any artificial processing.

The present invention provides an apparatus and method for distinguishing and providing a source voice and a filtered voice according to whether a user is authenticated.

The effects according to the present invention are not limited by the contents exemplified above, and more various effects are included in the specification.

1 shows a schematic configuration of an apparatus for providing filtered speech according to an embodiment of the present invention.
2A and 2B illustrate a procedure for providing filtered speech according to a method for providing filtered speech according to an embodiment of the present invention.
2C illustrates a procedure for providing filtered speech according to a method for providing filtered speech to an unauthorized user according to an embodiment of the present invention.
3A and 3B illustrate another procedure for providing filtered speech according to a method for providing filtered speech according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention, and the manner of achieving them, will be apparent from and elucidated with reference to the embodiments described hereinafter in conjunction with the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims.

Like reference numerals refer to like elements throughout the specification unless otherwise specified.

It is to be understood that each of the features of the various embodiments of the present invention may be combined or combined with each other partially or entirely and technically various interlocking and driving is possible as will be appreciated by those skilled in the art, It may be possible to cooperate with each other in association.

The suffix "module" and " part "for components used in the following description are given merely for convenience of description, and do not give special significance or role in themselves. Accordingly, the terms "module" and "part" may be used interchangeably.

In the present specification, the term " media file " is used to digitize a text, a photo image, a chart, a voice, sound and music, an animation, Quot; refers to a file storing a composite constituent medium.

As used herein, the term " forbidden word " means a word that is not suitable for streaming to a user. For example, in the case of a movie provided to young people, it is an ambassador that includes profanity.

1 shows a schematic configuration of an apparatus for providing filtered speech according to an embodiment of the present invention.

Referring to FIG. 1, a media providing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

The communication unit 110 transmits and receives information in the media providing apparatus 100 using various communication networks. Specifically, the communication unit can receive a media file from another media providing apparatus using various communication networks. And may also receive a media file from the personal user terminal device. It is possible to transmit various types of media in a streaming form to the personal user terminal device through the communication unit 110. And may transmit the media file received by the communication unit 110 to the storage unit 120 and the control unit 130. [

The storage unit 120 stores media files, time information on a period in which prohibited words are reproduced, and media files including filtered audio information. Also, a basic OS system for operation of the media providing apparatus 100 may be stored. Specifically, the media file refers to all media files such as music and video, and the time information about the period in which the prohibited word is reproduced may be stored in a tag form together with the media file, or may be stored as a separate file. The media file including the filtered voice information may be filtered to include the prohibited word so as to store the processed media file so that the user can not listen to the portion including the prohibited word.

The control unit 130 performs a function of reproducing the media file received by the communication unit 110, internal data processing, internal module control, and the like. In addition, during the reproduction of the media, the voice of the prohibited word stored in the storage unit 120 and the voice of the media file being reproduced are compared with each other to scan whether the lyrics are the same or not. In addition, the media file is scanned and the time information of the section determined to be the same as the prohibited word is stored in the storage unit 120. And performs a function of giving a filtering effect to the section determined to be the same as the prohibited word. The same does not only mean the same thing but also includes substantially the same thing with similar pronunciation.

Each configuration of the media providing apparatus 100 is shown as an individual configuration for convenience of description, and may be implemented in one module or one configuration may be separated into two or more configurations according to an implementation method.

2A and 2B illustrate a procedure for providing filtered speech according to a method for providing filtered speech according to an embodiment of the present invention. Will be described with reference to Fig. 1 for convenience of explanation.

The method for providing the filtered speech according to the present invention can largely be divided into a preparation step for providing a voice and a reproduction step for providing a filtered voice to the user. The preparation step is shown in Fig. 2A, and the regeneration step is shown in Fig. 2B.

The method for providing the filtered speech according to the present invention is started by reproducing the media added to the database in the control unit 130 (S110). And reproduces the media to obtain the audio output included in the media file. Here, playback may be to obtain a physical audio output such as a speaker, or to obtain a digitized audio output of a media file within the control unit, not physically reproducing the audio output.

When the media file is reproduced, the control unit 130 performs a prohibition word scan for comparing the prohibited word stored in the storage unit 120 and the voice output (S120). Speech recognition is required for scanning these prohibited words. Speech recognition is a technology that extracts and analyzes features from the voice of a person who is delivered to a computer or voice recognition system through a telephone or a microphone, and finds the closest result from a previously entered recognition list. The speech recognition process is roughly divided into a preprocessing unit and a recognition unit. In the preprocessing unit, a noise component is extracted by searching a section to be recognized from a voice uttered by the user, and a feature for the recognition process is extracted. For example, a filter that can extract a specific frequency sound, such as a band pass filter, can emphasize the sound of the human range to make it easier to recognize the sound. The recognition unit outputs the most probable words as a recognition result by comparing the inputted speech with the speech database. When recognizing a sentence other than a simple command, the recognition performance is improved by using a language model to restrict the comparison word. The speech recognition method of the present invention can be implemented by various methods other than the above method and is not limited by a specific method. The prohibited word scanning step may be generally performed simultaneously with the media reproduction, but the prohibited word scanning step may be performed after the media reproduction is completed.

Then, the control unit 130 records the prohibited word playback period in the storage unit 120 (S130). Time information about a section in which a prohibited word is reproduced is recorded to indicate that a prohibited word is included in a specific portion of the music file.

Then, the control unit 130 stores the prohibited word playback period record in the storage unit 120 (S140). The prohibited word playback section can be recorded together with the media file in tag form. It is also possible to store the media files separately in separate files.

In this case, if the user requests a playback of the media file, the playback step is started (S210).

The control unit 130 may give the user the effect of not hearing the prohibited word in various ways during the prohibited word reproducing period (S220). For example, the size of the audio output during the time period during which the prohibited word is reproduced can be reduced so that the user can implement the method in such a manner that the audio output is not audible. In this case, it is also possible to separate the human voice and the background music so that only the size of the human voice is reduced so that the user can listen to the background music normally. It is also possible to add a beep sound to the audio output during the time when the prohibited word is reproduced so that the user can select a method for preventing the user from listening to the music. It is possible to implement a method of preventing the user from hearing the prohibited word in various ways including this method. In yet another embodiment, it is also possible to have the user select a method to prevent the forbidden word from being heard.

2C illustrates a procedure for providing filtered speech according to a method for providing filtered speech to an unauthorized user according to an embodiment of the present invention.

If the user has a playback request for the media file, the playback step is started (S310).

Subsequently, the user determines whether the right to reproduce the unfiltered original is authenticated (S320). According to one embodiment, it may be determined whether or not the adult is authenticated. According to another embodiment, it may be determined whether or not security authentication is performed.

In the case of the authenticated user, the media file is directly reproduced (S330).

In the case of a user who has not been authenticated, a filtering effect is given to the same prohibited word reproducing section as in the above-described step S220 and reproduced (S340).

3A and 3B illustrate another procedure for providing filtered speech according to a method for providing filtered speech according to an embodiment of the present invention. 3A and 3B are omitted from the description of the duplicated contents in comparison with the procedures shown in FIGS. 2A and 2B.

Referring to FIG. 3A, a filtering effect can be given to the prohibited word playback section and stored (S440). 2A and 2B, the filtering effect is given in advance and stored. When the filtering effect is given in advance, the control unit simply plays the voice file to which the stored filtering effect is given. Accordingly, it is possible to reduce the load on the controller 130 due to filtering in real time during reproduction. However, in such a case, the filtering effect should be given to the prohibited word playback section and stored as a separate file.

Referring to FIG. 3B, if there is a media playback request of the user, the media file having the filtering effect of the prohibited word playback interval is reproduced (S520).

3C illustrates a procedure for providing filtered speech according to a method for providing filtered speech to an unauthorized user according to an embodiment of the present invention. The procedure shown in FIG. 3C is different from the procedure shown in FIG. 2C in that the step S340 is changed to the step S640, but the other steps are the same and the explanation is omitted.

In the case of a user who has not been authenticated, the media file having the filtering effect is reproduced in the same prohibited word reproducing section as in step S520 described above (S340).

According to another embodiment of the present invention, a method for providing filtered speech according to the present invention is a method for providing a filtered voice in which a new media file is received in the communication unit 110 of the media providing apparatus 100, And the media playback step (S110) is executed. Therefore, even if there is no separate media playback command, it is possible to automatically record the forbidden word scan and playback sections and to prepare the filtered media.

According to another embodiment of the present invention, if the lyrics file exists in the media file in the step of scanning the prohibited word (S120), it is possible to increase the accuracy of speech recognition by searching for the same pronunciation based on the lyrics file . More specifically, the prohibited word reproduction section can be recorded by capturing and recording time information of the same lyrics based on the lyrics information.

According to another embodiment of the present invention, the prohibited word stored in the storage unit 120 can be updated and added or deleted. A method and an apparatus for providing a filtered voice reflecting the age can be provided since it is possible to reflect a newly added banned word through such an update.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, which is capable of reading information from, and writing information to, the storage medium. Alternatively, the storage medium may be integral with the processor. The processor and the storage medium may reside within an application specific integrated circuit (ASIC). The ASIC may reside within the user terminal. Alternatively, the processor and the storage medium may reside as discrete components in a user terminal.

Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, it is to be understood that the present invention is not limited to those embodiments and various changes and modifications may be made without departing from the scope of the present invention. . Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. Therefore, it should be understood that the above-described embodiments are illustrative in all aspects and not restrictive. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

100: media providing server 110:
120: storage unit 130:

Claims (10)

Reproducing a media file and scanning a prohibited word using a speech recognition algorithm;
Recording a section in which the prohibited word is reproduced;
And providing a filtering effect so that the prohibited word is not audible to a user during a period in which the prohibited word is reproduced when the media file is reproduced. The method according to claim 1,
Reproducing a media file and scanning a prohibited word using a speech recognition algorithm;
Recording a section in which the prohibited word is reproduced;
The step of giving a filtering effect to prevent the user from hearing the prohibited word in a period in which the prohibited word is reproduced when the music file is reproduced
And when the media file is uploaded, the media file is uploaded. The method according to claim 1,
Wherein the step of reproducing the media file and searching for a prohibited word using a speech recognition algorithm comprises:
If the music file includes the lyrics information, determining the prohibited word based on the lyrics information; And
And searching the lyrics determined to be prohibited by using a speech recognition algorithm. The method according to claim 1,
Wherein the recording of the section in which the prohibited word is reproduced includes:
And storing the information about the interval together with the media file. The method according to claim 1,
The step of imparting the filtering effect comprises:
And a method of reducing the size of the sound of the section so as to provide a smaller sound. The method according to claim 1,
The step of imparting the filtering effect comprises:
And a sound is blocked by adding a beep sound to the section. The method according to claim 1,
Characterized in that the prohibited word can be added or deleted by updating the banishment word. The method according to claim 1,
When the media file is reproduced, providing a voice having a filtering effect only when the authentication of the user is unsuccessful. The method according to claim 1,
The media file may include:
Wherein the audio file is one of a music file and a moving picture file including a voice. A media providing server comprising:
A communication unit for transmitting and receiving a media file;
A storage unit for storing a media file, lyric information, and a prohibited word; And
And a control unit for reproducing the media file and performing speech recognition, scanning, and filtering.
KR1020140138305A 2014-10-14 2014-10-14 Method and apparatus for providing a filtered voice KR20160043732A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020140138305A KR20160043732A (en) 2014-10-14 2014-10-14 Method and apparatus for providing a filtered voice

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020140138305A KR20160043732A (en) 2014-10-14 2014-10-14 Method and apparatus for providing a filtered voice

Publications (1)

Publication Number Publication Date
KR20160043732A true KR20160043732A (en) 2016-04-22

Family

ID=55918276

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020140138305A KR20160043732A (en) 2014-10-14 2014-10-14 Method and apparatus for providing a filtered voice

Country Status (1)

Country Link
KR (1) KR20160043732A (en)

Similar Documents

Publication Publication Date Title
US20230402029A1 (en) Systems and methods for providing notifications within a media asset without breaking immersion
US8869222B2 (en) Second screen content
KR20170069258A (en) Voiceprint information management method and device as well as identity authentication method and system
WO2016184096A1 (en) Audio unlocking method and apparatus
KR20150057591A (en) Method and apparatus for controlling playing video
KR20160027005A (en) Collaborative audio conversation attestation
US11849181B2 (en) Systems and methods for applying behavioral-based parental controls for media assets
US20200013422A1 (en) System, Method, and Apparatus for Morphing of an Audio Track
WO2019114015A1 (en) Robot performance control method and robot
KR101727587B1 (en) A Method Generating Transcripts Of Digital Recording File
JP2008309959A (en) Audio signal recording device and electronic file
KR101592518B1 (en) The method for online conference based on synchronization of voice signal and the voice signal synchronization process device for online conference and the recoding medium for performing the method
KR102232642B1 (en) Media play device and voice recognition server for providing sound effect of story contents
KR20160043732A (en) Method and apparatus for providing a filtered voice
WO2022179253A1 (en) Speech operation method for device, apparatus, and electronic device
KR101781353B1 (en) A Method Generating Digital Recording File Having Integrity
JP2007183410A (en) Information reproduction apparatus and method
KR102076565B1 (en) Speech processing apparatus which enables identification of a speaking person through insertion of speaker identification noise and operating method thereof
CN111833882A (en) Voiceprint information management method, device and system, computing equipment and storage medium
JP2005352330A (en) Speech division recording device
JP2006157692A (en) Video reproducing method and device thereof, and program
KR102443582B1 (en) Interactive video output system and method
KR102025903B1 (en) Apparatus and method for language learning
US11665392B2 (en) Methods and systems for selective playback and attenuation of audio based on user preference
KR101562901B1 (en) System and method for supporing conversation

Legal Events

Date Code Title Description
WITN Withdrawal due to no request for examination