CN108829845A - A kind of audio file play method, device and electronic equipment - Google Patents

Abstract

The embodiment of the invention provides a kind of audio file play method, device and electronic equipments, wherein this method includes：The play instruction that user plays pretreated audio file to be played is received, shows announcer's identification information of pretreated audio file to be played；Announcer's identification information of user's selection is obtained, and according to announcer's identification information of selection, plays pretreated audio file to be played, wherein the audio fragment of pretreated audio file to be played is added with corresponding announcer's identification information.It can be seen that, when playing audio file to be played, as long as user has selected the corresponding announcer's identification information of the audio fragment for wanting to listen, audio fragment corresponding with announcer's identification information of the selection can be played, to reduce operation complexity when user plays audio file.

Description

A kind of audio file play method, device and electronic equipment

Technical field

The present invention relates to audio signal processing technique fields, more particularly to a kind of audio file play method, device and electronics Equipment.

Background technique

With the development of economy, the living standard of people has significant raising, with mentioning for living standard Height, requirement of the people to cultural life is also higher and higher, for example, by watching the video oneself liked, playing what oneself was liked Audio enriches the life of the spirit.Specifically, user can carry out F.F., rewind, pause etc. when playing the audio oneself liked Operation.

However, inventor has found in the implementation of the present invention, at least there are the following problems for the prior art：

When user is when playing audio file, it is desirable to when listening an audio fragment or being not desired to listen an audio fragment, need The audio fragment for wanting to listen is found by way of F.F. perhaps rewind or skips the audio fragment for being not desired to listen, to increase The operation complexity of user is added.

Summary of the invention

The embodiment of the present invention is designed to provide a kind of audio file play method, device and electronic equipment, so that User can choose the audio fragment to be played, and play the audio fragment of user's selection automatically, reduces and plays audio to be played When file, the operation complexity of user.Specific technical solution is as follows：

In the one aspect that the present invention is implemented, the embodiment of the invention also provides a kind of audio file play method, the party Method includes：

Receive the play instruction that user plays pretreated audio file to be played；

Show announcer's identification information of pretreated audio file to be played, wherein pretreated sound to be played The audio fragment of frequency file is added with corresponding announcer's identification information；

Announcer's identification information of user's selection is obtained, and according to announcer's identification information of selection, after playing pretreatment Audio file to be played.

Optionally, pretreated process is carried out to audio file to be played, including：

Audio file to be played is divided into multiple audio fragments according to preset duration, wherein preset duration is sampling every time Duration or every frame duration；

The first audio fragment in multiple audio fragments is selected, and is searched and the first audio in default announcer's database Identical first audio-frequency information of the audio feature information of segment, and the first announcer corresponding with the first audio-frequency information identify letter Breath, wherein the first audio fragment is any one audio fragment in multiple audio fragments, is stored in default announcer's database Multiple audio-frequency informations and announcer's identification information corresponding with audio-frequency information each in multiple audio-frequency informations, audio feature information Including at least one of acoustic feature and characteristics of image；

In multiple audio fragments of audio file to be played, search identical as the audio feature information of the first audio-frequency information Audio fragment, and establish identical with the audio feature information of the first audio-frequency information audio fragment and the first announcer mark is believed The index of breath obtains pretreated audio file to be played.

Optionally, pretreated process is carried out to audio file to be played, further includes：

Audio file to be played is divided into multiple audio fragments according to preset duration, wherein preset duration is sampling every time Duration or every frame duration；

For any two adjacent audio fragments in multiple audio fragments, in the audio of two adjacent audio fragments When characteristic information is identical, using two adjacent audio fragments as the first audio section, wherein audio feature information includes acoustics Feature and characteristics of image, the duration of the first audio section are greater than the duration of each audio fragment in multiple audio fragments；

The audio feature information for obtaining the first audio section searches the sound with the first audio section in default announcer's database Identical second audio-frequency information of frequency characteristic information, and second announcer's identification information corresponding with the second audio-frequency information are established The index of first audio section and second announcer's identification information obtains pretreated audio file to be played, wherein default to broadcast Multiple audio-frequency informations and announcer corresponding with audio-frequency information each in multiple audio-frequency informations mark are stored in sound person's database Know information.

Optionally, before audio file to be played is divided into multiple audio fragments according to preset duration, the present invention is implemented Example a kind of audio file play method, further include：

In audio file to be played there are when background sound, the disjunctive model that training obtains in advance is obtained, wherein training in advance Obtained disjunctive model is used to filter the background sound in the audio file to be played there are background sound；

The background sound in audio file to be played is filtered by the disjunctive model that training obtains in advance, is filtered Audio file to be played afterwards；

Correspondingly, audio file to be played is divided into multiple audio fragments according to preset duration, including：

Filtered audio file to be played is divided into multiple audio fragments according to preset duration.

Optionally, announcer's identification information of pretreated audio file to be played is shown, including：

Show the announcer's identification information and options of pretreated audio file to be played；

Correspondingly, obtaining announcer's identification information of user's selection, and according to announcer's identification information of selection, play pre- Treated audio file to be played, including：

The options of user's selection and announcer's identification information of selection are obtained, and according to the options and choosing of selection The announcer's identification information selected plays pretreated audio file to be played.

Optionally, it according to the options of selection and announcer's identification information of selection, plays pretreated to be played Audio file, including：

When the options selected is including the options of positivity word, play in pretreated audio file to be played, Audio fragment corresponding with announcer's identification information of selection；

When the options selected is including the options of negativity word, play in pretreated audio file to be played, Audio fragment in addition to audio fragment corresponding with announcer's identification information of selection.

At the another aspect that the present invention is implemented, the embodiment of the invention also provides a kind of audio file playing device, the dresses Set including：

Receiving module plays the play instruction of pretreated audio file to be played for receiving user；

Display module, for showing announcer's identification information of pretreated audio file to be played, wherein pretreatment The audio fragment of audio file to be played afterwards is added with corresponding announcer's identification information；

Playing module, for obtaining announcer's identification information of user's selection, and according to announcer's identification information of selection, Play pretreated audio file to be played.

Optionally, a kind of audio file playing device of the embodiment of the present invention further includes：

Segmentation module, for audio file to be played to be divided into multiple audio fragments according to preset duration, wherein when default A length of each sampling duration or every frame duration；

First audio frequency characteristics contrast module is broadcast for selecting the first audio fragment in multiple audio fragments, and default Search identical with the audio feature information of the first audio fragment the first audio-frequency information in sound person's database, and with the first audio The corresponding first announcer identification information of information, wherein the first audio fragment is any one audio piece in multiple audio fragments Section is stored with multiple audio-frequency informations and corresponding with each audio-frequency information in multiple audio-frequency informations in default announcer's database Announcer's identification information, audio feature information include at least one of acoustic feature and characteristics of image；

First index establishes module, for searching and the first audio in multiple audio fragments of audio file to be played The identical audio fragment of the audio feature information of information, and establish audio identical with the audio feature information of the first audio-frequency information The index of segment and first announcer's identification information obtains pretreated audio file to be played.

Optionally, a kind of audio file playing device of the embodiment of the present invention further includes：

Segmentation module, for audio file to be played to be divided into multiple audio fragments according to preset duration, wherein when default A length of each sampling duration or every frame duration；

Second audio frequency characteristics contrast module, any two adjacent audio fragments for being directed in multiple audio fragments, When the audio feature information of two adjacent audio fragments is identical, using two adjacent audio fragments as the first audio Section, wherein audio feature information includes acoustic feature and characteristics of image, and the duration of the first audio section is greater than in multiple audio fragments Each audio fragment duration；

Second index establishes module, for obtaining the audio feature information of the first audio section, in default announcer's database It is middle to search identical with the audio feature information of the first audio section the second audio-frequency information, and corresponding with the second audio-frequency information the Two announcer's identification informations establish the index of the first audio section and second announcer's identification information, obtain pretreated wait broadcast Playback frequency file, wherein be stored in default announcer's database multiple audio-frequency informations and with it is each in multiple audio-frequency informations The corresponding announcer's identification information of audio-frequency information.

Optionally, a kind of audio file playing device of the embodiment of the present invention further includes：

Background sound separation module, for there are when background sound, obtain point trained obtain in advance in audio file to be played From model, the background sound in audio file to be played is filtered by the disjunctive model that training obtains in advance, is filtered Audio file to be played afterwards, wherein the disjunctive model that training obtains in advance is used to filter the audio to be played there are background sound Background sound in file；

Correspondingly, segmentation module, is specifically used for：

Filtered audio file to be played is divided into multiple audio fragments according to preset duration.

Optionally, display module is specifically used for

Show the announcer's identification information and options of pretreated audio file to be played；

Correspondingly, playing module, is specifically used for：

The options of user's selection and announcer's identification information of selection are obtained, and according to the options and choosing of selection The announcer's identification information selected plays pretreated audio file to be played.

Optionally, playing module, also particularly useful for：

When the options selected is including the options of positivity word, play in pretreated audio file to be played, Audio fragment corresponding with announcer's identification information of selection；

When the options selected is including the options of negativity word, play in pretreated audio file to be played, Audio fragment in addition to audio fragment corresponding with announcer's identification information of selection.

At the another aspect implemented of the present invention, the embodiment of the invention also provides a kind of electronic equipment, including it is processor, logical Believe interface, memory and communication bus, wherein processor, communication interface, memory complete mutual lead to by communication bus Letter；

Memory, for storing computer program；

Processor when for executing the program stored on memory, realizes that any of the above-described audio file plays Method.

At the another aspect that the present invention is implemented, the embodiment of the invention also provides a kind of computer readable storage medium, institutes It states and is stored with instruction in computer readable storage medium, when run on a computer, so that computer execution is any of the above-described The audio file play method.

At the another aspect that the present invention is implemented, the embodiment of the invention also provides a kind of, and the computer program comprising instruction is produced Product, when run on a computer, so that computer executes any of the above-described audio file play method.

A kind of audio file play method, device and electronic equipment provided in an embodiment of the present invention, broadcast receiving user After the play instruction for putting pretreated audio file to be played, announcer's mark of pretreated audio file to be played is shown Know information, wherein the audio fragment of pretreated audio file to be played is added with corresponding announcer's identification information；It obtains and uses Announcer's identification information of family selection, and according to announcer's identification information of selection, play pretreated audio text to be played Part.As it can be seen that as long as user has selected the audio fragment for wanting to listen, corresponding announcer identifies letter when playing audio file to be played Breath, can play audio fragment corresponding with announcer's identification information of the selection, so that reducing user plays audio text Operation complexity when part.Certainly, it implements any of the products of the present invention or method must be not necessarily required to reach described above simultaneously All advantages.

Detailed description of the invention

In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below There is attached drawing needed in technical description to be briefly described.

Fig. 1 is a kind of flow chart of the first embodiment of audio file play method of the embodiment of the present invention；

Fig. 2 is that a kind of audio file play method of the embodiment of the present invention carries out pretreated audio file to be played The first display diagram shown；

Fig. 3 is a kind of flow chart of second of embodiment of audio file play method of the embodiment of the present invention；

Fig. 4 is a kind of flow chart of the third embodiment of audio file play method of the embodiment of the present invention；

Fig. 5 is a kind of flow chart of the 4th kind of embodiment of audio file play method of the embodiment of the present invention；

Fig. 6 is a kind of flow chart of the 5th kind of embodiment of audio file play method of the embodiment of the present invention；

Fig. 7 is a kind of flow chart of the 6th kind of embodiment of audio file play method of the embodiment of the present invention；

Fig. 8 is that a kind of audio file play method of the embodiment of the present invention carries out pretreated audio file to be played The second display diagram shown；

Fig. 9 is a kind of structural schematic diagram of audio file playing device of the embodiment of the present invention；

Figure 10 is the structural schematic diagram of a kind of electronic equipment of the embodiment of the present invention.

Specific embodiment

Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention is described.

Of the existing technology in order to solve the problems, such as, the embodiment of the invention provides a kind of audio file play methods, dress It sets and electronic equipment, so that user can choose the audio fragment to be played, and play the audio fragment of user's selection automatically, When reducing broadcasting audio file to be played, the operation complexity of user.

In the following, a kind of audio file play method of the embodiment of the present invention is introduced first, as shown in Figure 1, for this A kind of flow chart of the first embodiment of audio file play method of inventive embodiments, in Fig. 1, this method be can wrap It includes：

S110 receives user and plays the play instruction of pretreated audio file to be played, show it is pretreated to Play announcer's identification information of audio file.

Wherein, the audio fragment in pretreated audio file to be played is added with corresponding announcer's identification information.

Specifically, when user is when playing audio file to be played, it can be in a kind of audio of the application embodiment of the present invention In the playing device of document play-back method, the audio file to be played is selected, and click play button, then the playing device can be with The play instruction that user plays the audio file to be played of selection is received, and the audio file of user's selection to be played is made For audio file to be played.

After above-mentioned playing device is receiving user and plays the play instruction of pretreated audio file to be played, It can show announcer's identification information of pretreated audio file to be played.So that user can choose and want to listen The identification information of the corresponding announcer of audio.

In some instances, multiple audio files to be played can store in above-mentioned playing device, the sound to be played Frequency file can be pretreated audio file.

In some instances, above-mentioned audio file to be played, can be by manually being pre-processed, for example, firstly, pre- place Reason personnel listen to the audio sample of an announcer, and the audio sample with the announcer is then found in audio file to be played Identical audio fragment, the mark for then adding the announcer to audio fragment identical with the audio sample of the announcer are believed Breath.

In some instances, above-mentioned audio file to be played can be music, talking book, can also be video file In audio file.Announcer can be singer, talking book author, can be with performer of video file etc..

For example, as shown in Fig. 2, being a kind of audio file play method of the embodiment of the present invention to pretreated to be played The first display diagram that audio file is shown, in fig. 2 it is possible to include announcer 1, announcer 2, announcer 3, announcer 4, Announcer 5 and announcer 6.

For more clearly bright treated audio file to be played, illustratively show this below treated to Play the audio fragment in audio file, in Fig. 2, should the audio fragment of treated audio file to be played may include： First audio fragment 210, the second audio fragment 220, third audio fragment 230, the 4th audio fragment 240, fifth audio segment 250, the 6th audio fragment 260.

Wherein, which can be added with the identification information of announcer 1, and the second audio fragment 220 can be with Identification information added with announcer 2, third audio fragment 230 can be added with the identification information of announcer 3, the 4th audio piece Section 240 can be added with the identification information of announcer 4, and fifth audio segment 250 can be added with the identification information of announcer 5, 6th audio fragment 260 can be added with the identification information of announcer 6.After showing display diagram shown in Fig. 2, it can make User selects in 6 announcer's identification informations in the display diagram.

S120 obtains announcer's identification information of user's selection, and according to announcer's identification information of selection, plays pre- place Audio file to be played after reason.

When announcer's identification information of pretreated audio file to be played is being showed use by above-mentioned playing device Behind family, user can select in announcer's identification information of displaying, when user is in announcer's identification information of displaying When being selected, the available announcer's identification information to user's selection of above-mentioned playing device.

The playing device is broadcast after the announcer's identification information for getting user's selection to audio file to be played When putting, the announcer's identification information that can be selected according to user plays audio fragment corresponding with announcer's identification information.

For example, it is assumed that user has selected announcer 2, announcer 4 and announcer 5, then above-mentioned playing device in Fig. 2 When playing the audio file to be played, can play and corresponding second audio fragment 220 of announcer 2, corresponding with announcer 4 The 4th audio fragment 240 and fifth audio segment 250 corresponding with announcer 5.Without playing the non-selected broadcast of user The corresponding audio fragment of member.

As it can be seen that when playing audio file to be played, as long as user has selected the corresponding announcer of the audio fragment for wanting to listen Identification information, above-mentioned playing device can play audio fragment corresponding with announcer's identification information of the selection, thus Reduce operation complexity when user plays audio file.

A kind of audio file play method through the embodiment of the present invention, receiving, user's broadcasting is pretreated wait broadcast After the play instruction of playback frequency file, announcer's identification information of pretreated audio file to be played is shown, wherein pre- place The audio fragment of audio file to be played after reason is added with corresponding announcer's identification information；Obtain announcer's mark of user's selection Know information, and according to announcer's identification information of selection, plays pretreated audio file to be played.As it can be seen that play to Play audio file when, as long as user has selected the corresponding announcer's identification information of the audio fragment for wanting to listen, can play with The corresponding audio fragment of announcer's identification information of the selection, thus complicated for operation when reducing user's broadcasting audio file Degree.

In a kind of optional embodiment of the embodiment of the present invention, except through artificial treatment mode to audio to be played Outside file is pre-processed, pretreated accuracy and treatment effeciency are carried out to audio file to be played in order to improve, reduce people Power cost, on the basis of a kind of audio file play method shown in Fig. 1, the embodiment of the invention also provides a kind of audio texts Part playback method, as shown in figure 3, a kind of process of second of embodiment of audio file play method for the embodiment of the present invention Figure carries out pretreated process to audio file to be played, may include in Fig. 3：

Audio file to be played is divided into multiple audio fragments according to preset duration by S130,

Wherein, preset duration is every time sampling duration or every frame duration.

In some instances, above-mentioned playing device, can be right first when pre-processing to audio file to be played Audio file to be played carries out cutting, and cutting is multiple audio fragments.

Specifically, above-mentioned playing device can carry out cutting to the audio file to be played according to preset duration.This is pre- If duration can be the time interval of pre-set cutting.For example, it is assumed that audio file to be played is the audio file of 300s, Preset duration is 3s, then can be time interval according to 3s, be 100 parts by the audio file cutting of the 300s.

In some instances, when the coded format of the audio file to be played be PCM (Pulse Code Modulation, Pulse code modulation) format when, then can will every time sampling duration as the preset duration of the audio file to be played.It should be wait broadcast It, can be using every frame duration as preset duration when the coded format of playback frequency file is not PCM format.

S140 selects the first audio fragment in multiple audio fragments, and searches and the in default announcer's database Identical first audio-frequency information of the audio feature information of one audio fragment, and the first announcer corresponding with the first audio-frequency information Identification information.

Wherein, the first audio fragment is any one audio fragment in multiple audio fragments, is preset in announcer's database It is stored with multiple audio-frequency informations and announcer's identification information corresponding with audio-frequency information each in multiple audio-frequency informations, audio is special Reference breath includes acoustic feature and characteristics of image.

Above-mentioned playing device is after carrying out cutting to audio file to be played, it is understood that there may be the audio of multiple audio fragments Characteristic information is identical as the audio feature information of the same announcer, if adding one respectively to each audio fragment after cutting A announcer's identification information, then will increase pretreated complexity, and make the number of pretreated audio file to be played Increase according to amount, increases pretreated audio file to be played to the occupancy of memory space.

In this regard, above-mentioned playing device can optionally select an audio fragment conduct in multiple audio fragments after cutting Then first audio fragment can search the audio feature information with first audio fragment in default announcer's database Identical audio-frequency information, after finding audio-frequency information identical with the audio feature information of first audio fragment, Ke Yi The corresponding announcer's identification information of the audio-frequency information is searched in default announcer's database.

In some instances, above-mentioned default announcer's database can be pre-set, be stored with multiple announcers Identification information, and audio-frequency information corresponding with the identification information of each announcer should identification information with each announcer Corresponding audio-frequency information can be sample audio file.

In some instances, above-mentioned playing device is searching identical with the audio feature information of the first audio fragment the When one audio-frequency information, the first audio-frequency information identical with the acoustic feature of the first audio fragment can be searched, can also search with Identical first audio-frequency information of the characteristics of image of first audio fragment, can also search with the acoustic feature of the first audio fragment and All identical first audio-frequency information of characteristics of image.

S150 is searched and is believed with the audio frequency characteristics of the first audio-frequency information in multiple audio fragments of audio file to be played Identical audio fragment is ceased, and establishes audio fragment identical with the audio feature information of the first audio-frequency information and the first announcer The index of identification information obtains pretreated audio file to be played.

In some instances, above-mentioned playing device find it is identical with the audio feature information of the first audio fragment It, can be in audio text to be played after first audio-frequency information, and first announcer's identification information corresponding with the first audio-frequency information In multiple audio fragments of part, audio fragment identical with the audio feature information of first audio-frequency information is searched.

Specifically, above-mentioned playing device can be by comparing the audio feature information of first audio-frequency information and above-mentioned The audio feature information of each audio fragment in multiple audio fragments, determination are identical as the audio feature information of the first audio-frequency information Audio fragment.

In some instances, being somebody's turn to do audio fragment identical with the audio feature information of the first audio-frequency information can be one, It is also possible to multiple.

Above-mentioned playing device, can after finding audio fragment identical with the audio feature information of the first audio-frequency information To establish the index of identical with the audio feature information of the first audio-frequency information audio fragment and first announcer's identification information, from And available pretreated audio file to be played.

Letter is identified by establishing audio fragment identical with the audio feature information of the first audio-frequency information and the first announcer The index of breath can make after user selects the first announcer identification information, above-mentioned playing device can by this One announcer's identification information, gets audio fragment corresponding with the first announcer identification information, so to this with this first The corresponding audio fragment of announcer's identification information plays out.

A kind of audio file play method through the embodiment of the present invention can be improved and carry out in advance to audio file to be played The accuracy and treatment effeciency of processing reduce human cost.

In a kind of optional embodiment of the embodiment of the present invention, a kind of audio file play method shown in Fig. 1 On the basis of, the embodiment of the invention also provides a kind of audio file play methods, as shown in figure 4, being the one of the embodiment of the present invention The flow chart of kind the third embodiment of audio file play method carries out audio file to be played pretreated in Fig. 4 Process may include：

Audio file to be played is divided into multiple audio fragments according to preset duration by S160.

Wherein, preset duration is every time sampling duration or every frame duration.

In some instances, above-mentioned playing device, can be right first when pre-processing to audio file to be played Audio file to be played carries out cutting, and cutting is multiple audio fragments.

Specifically, above-mentioned playing device can carry out cutting to the audio file to be played according to preset duration.This is pre- If duration can be the time interval of pre-set cutting.For example, it is assumed that audio file to be played is the audio file of 300s, Preset duration is 3s, then can be time interval according to 3s, be 100 parts by the audio file cutting of the 300s.

In some instances, when the coded format of the audio file to be played be PCM (Pulse Code Modulation, Pulse code modulation) format when, then can will every time sampling duration as the preset duration of the audio file to be played.It should be wait broadcast It, can be using every frame duration as preset duration when the coded format of playback frequency file is not PCM format.

S170, for any two adjacent audio fragments in multiple audio fragments, in two adjacent audio fragments Audio feature information it is identical when, using two adjacent audio fragments as the first audio section.

Wherein, audio feature information includes acoustic feature and characteristics of image.

Above-mentioned playing device is after carrying out cutting to audio file to be played, it is understood that there may be audio feature information is identical Multiple audio fragments will increase pre- if adding announcer's identification information respectively to each audio fragment after cutting The complexity of processing, and the data volume of pretreated audio file to be played is increased, increase it is pretreated to Audio file is played to the occupancy of memory space.

In this regard, above-mentioned playing device, it can be in multiple audio fragment, lookup audio feature information is identical, and phase Two adjacent audio fragments, then, two audio feature information is identical and adjacent audio fragments are as the same audio Segment namely the first audio section.So as to realize the classification first to multiple audio fragments of audio file to be played.

In some instances, the duration of above-mentioned audio section is greater than the duration of above-mentioned each audio fragment.

For example, it is assumed that obtaining 10 audio fragments, respectively audio fragment 1 after carrying out cutting to audio file to be played ~audio fragment 10, wherein the audio feature information of 1~audio fragment of audio fragment 5 is identical, also, audio fragment 1 and audio Segment 2 is adjacent, and audio fragment 2 and audio fragment 3 are adjacent, and audio fragment 3 and audio fragment 4 are adjacent, audio fragment 4 and audio piece Section 5 is adjacent, then above-mentioned playing device can regard 1~audio fragment of audio fragment 5 as the first audio section.

S180 obtains the audio feature information of the first audio section, searches and the first audio in default announcer's database Identical second audio-frequency information of audio feature information of section, and the second announcer corresponding with the second audio-frequency information identify letter Breath, establishes the index of the first audio section and second announcer's identification information, obtains pretreated audio file to be played.

Wherein, preset announcer's database in be stored with multiple audio-frequency informations and with each audio in multiple audio-frequency informations The corresponding announcer's identification information of information.

Above-mentioned playing device using two adjacent audio fragments as the first audio section after, available first sound The audio feature information of frequency range, it is then possible to search the audio frequency characteristics with first audio section in default announcer's database The identical audio-frequency information of information, after finding the second audio-frequency information identical with the audio feature information of first audio section, It can preset at this and search the corresponding second announcer identification information of second audio-frequency information in announcer's database.

Finally, can establish the index of the first audio section and second announcer's identification information, so as to be pre-processed Audio file to be played afterwards.

In some instances, above-mentioned default announcer's database can be pre-set, be stored with multiple announcers Identification information, and audio-frequency information corresponding with the identification information of each announcer should identification information with each announcer Corresponding audio-frequency information can be sample audio file.

In some instances, above-mentioned playing device is searching identical with the audio feature information of the first audio section first When audio-frequency information, the second audio-frequency information identical with the acoustic feature of the first audio section can be searched, can also be searched and first Identical second audio-frequency information of the characteristics of image of audio section can also be searched special with the acoustic feature of the first audio fragment and image Levy all identical second audio-frequency information.

By establish with the index of the first audio section and second announcer's identification information, can make user select this After two announcer's identification informations, above-mentioned playing device can by the second announcer identification information, get with this second Corresponding first audio section of announcer's identification information, so to the first audio section corresponding with the second announcer identification information into Row plays.

A kind of audio file play method through the embodiment of the present invention, first in multiple audios of audio file to be played In segment, the identical audio fragment of audio feature information is searched, and using the identical audio fragment of audio feature information as one Audio section when so that searching in default announcer's database, is only searched primary, so that it may find in the audio section The corresponding announcer's identification information of audio fragment, can be improved and pretreated accuracy and place are carried out to audio file to be played Efficiency is managed, human cost is reduced.By establishing the index with the first audio section and second announcer's identification information, can make After user selects the second announcer identification information, it can get and second be broadcast with this by the second announcer identification information Corresponding first audio section of sound person's identification information, and play out.Operation complexity when audio file is played to reduce.

When being pre-processed to audio file to be played, when in the audio file to be played there are when background sound, may It will affect pretreated accuracy, in this regard, in a kind of optional embodiment of the embodiment of the present invention, one kind shown in Fig. 3 On the basis of audio file play method, the embodiment of the invention also provides a kind of audio file play methods, as shown in figure 5, Flow chart for a kind of the 4th kind of embodiment of audio file play method of the embodiment of the present invention, in S130, is pressed in Fig. 5 Before audio file to be played is divided into multiple audio fragments according to preset duration, a kind of audio file of the embodiment of the present invention is played Method can also include：

S190 obtains the disjunctive model that training obtains in advance in audio file to be played there are when background sound.

Wherein, the disjunctive model that training obtains in advance is used to filter the background in the audio file to be played there are background sound Sound.

Specifically, when audio file to be played is there are when background sound, above-mentioned playing device is available preparatory trained The disjunctive model arrived.

In some instances, the disjunctive model which obtains can be disjunctive model neural network based.

Specifically, above-mentioned playing device can obtain audio sample collection and background sound first, then to the audio sample Collection and background sound carry out fusion treatment, obtain training sample data, are then trained by neural network model, are based on The disjunctive model of neural network.

S200 is filtered the background sound in audio file to be played by the disjunctive model that training obtains in advance, obtains To filtered audio file to be played.

Above-mentioned playing device can be obtained after getting the disjunctive model that training obtains in advance by training in advance Disjunctive model is filtered the background sound in audio file to be played, so as to obtain filtered audio text to be played Part.

By being filtered the background sound in the audio file to be played there are background sound, can that this is being waited broadcasting When playback frequency file is pre-processed, pretreated accuracy is improved.

Correspondingly, S130, is divided into multiple audio fragments for audio file to be played according to preset duration, including：

Filtered audio file to be played is divided into multiple audio fragments according to preset duration by S131.

Above-mentioned playing device, can be with after being filtered to the background sound in the audio file to be played there are background sound Filtered audio file to be played is obtained, then when carrying out cutting, can be will be filtered to be played according to preset duration Audio file is divided into multiple audio fragments.

In some instances, step S190~S200 in above-described embodiment can be used for audio file shown in Fig. 4 In playback method, as shown in fig. 6, a kind of process of the 5th kind of embodiment of audio file play method for the embodiment of the present invention Figure, in Fig. 6, when in audio file to be played there are when background sound, can be using the method for step S190~S200 to the back Scape sound is filtered.

Correspondingly, S160, is divided into multiple audio fragments for audio file to be played according to preset duration, including：

Filtered audio file to be played is divided into multiple audio fragments according to preset duration by S161.

Above-mentioned playing device, can be with after being filtered to the background sound in the audio file to be played there are background sound Filtered audio file to be played is obtained, then when carrying out cutting, can be will be filtered to be played according to preset duration Audio file is divided into multiple audio fragments.

In a kind of optional embodiment of the embodiment of the present invention, a kind of audio file play method shown in Fig. 1 On the basis of, the embodiment of the invention also provides a kind of audio file play methods, as shown in fig. 7, being the one of the embodiment of the present invention The flow chart of kind the 6th kind of embodiment of audio file play method, in Fig. 7, S110 shows pretreated sound to be played Announcer's identification information of frequency file may include：

S111 shows the announcer's identification information and options of pretreated audio file to be played.

In some instances, when above-mentioned playing device is after receiving play instruction, in addition to show it is pretreated to Outside the announcer's identification information for playing audio file, in order to provide multiple choices mode for user, the alternative of user is improved, Above-mentioned playing device can also show options.

For example, as shown in figure 8, being a kind of audio file play method of the embodiment of the present invention to pretreated to be played The second display diagram that audio file is shown can also show choosing other than showing six above-mentioned announcer's identification informations Select item 1 and options 2.In some instances, above-mentioned options 1 and options 2 can be positivity word and negativity word, for example, Options 1 can be the positivities words such as " liking ", " wanting to listen ", and it is negative that options 2 can be " not liking ", " disagreeable ", " being not desired to listen " etc. Property word.

After showing options, user can select the options above-mentioned playing device.When user is to selection When item is selected, the available options to user's selection of above-mentioned playing device.For the selection selected according to user Item plays out audio file to be played, and the step S120 in a kind of audio file play method of the embodiment of the present invention is obtained Announcer's identification information of family selection is taken, and according to announcer's identification information of selection, plays pretreated sound to be played Frequency file may include：

S121 obtains the options of user's selection and announcer's identification information of selection, and according to the options of selection And announcer's identification information of selection, play pretreated audio file to be played.

Specifically, when above-mentioned playing device identifies letter in the announcer of the options and selection that get user's selection After breath, which can be played according to the options of selection and announcer's identification information of selection File.

In some instances, it according to the options of selection and announcer's identification information of selection, plays pretreated Audio file to be played, including：

When the options selected is including the options of positivity word, play in pretreated audio file to be played, Audio fragment corresponding with announcer's identification information of selection；

When the options selected is including the options of negativity word, play in pretreated audio file to be played, Audio fragment in addition to audio fragment corresponding with announcer's identification information of selection.

For example, it is assumed that announcer's identification information that user selects is announcer 1, announcer 3, announcer 4 and announcer 6, the options selected is " liking ", then above-mentioned playing device can play in above-mentioned audio file to be played with announcer 1 corresponding audio fragment, audio fragment corresponding with announcer 3, audio fragment corresponding with announcer 4 and with announcer 6 Corresponding audio fragment.

When announcer's identification information that user selects is announcer 2, announcer 5, when the options selected is " being not desired to listen ", Then above-mentioned playing device can play audio fragment corresponding with announcer 1 in above-mentioned audio file to be played, with broadcast 3 corresponding audio fragments of member, and the corresponding audio fragment of announcer 4 and audio fragment corresponding with announcer 6, will not play And the corresponding audio fragment of announcer 2 and audio fragment corresponding with announcer 5.

A kind of audio file play method through the embodiment of the present invention may provide the user with a variety of broadcasting selections, increase User is added to play the selectivity of pretreated audio file to be played, so as to improve user experience.

Corresponding to above-mentioned embodiment of the method, the embodiment of the invention also provides a kind of audio file playing device, such as Fig. 9 It is shown, it is a kind of structural schematic diagram of audio file playing device of the embodiment of the present invention, in Fig. 9, the apparatus may include：

Receiving module 910 plays the play instruction of pretreated audio file to be played for receiving user；

Display module 920, for showing announcer's identification information of pretreated audio file to be played, wherein pre- The audio fragment of treated audio file to be played is added with corresponding announcer's identification information；

Playing module 930 for obtaining announcer's identification information of user's selection, and identifies according to the announcer of selection and believes Breath plays pretreated audio file to be played.

A kind of audio file playing device provided in an embodiment of the present invention, receiving, user's broadcasting is pretreated wait broadcast After the play instruction of playback frequency file, announcer's identification information of pretreated audio file to be played is shown, wherein pre- place The audio fragment of audio file to be played after reason is added with corresponding announcer's identification information；Obtain announcer's mark of user's selection Know information, and according to announcer's identification information of selection, plays pretreated audio file to be played.As it can be seen that play to Play audio file when, as long as user has selected the corresponding announcer's identification information of the audio fragment for wanting to listen, can play with The corresponding audio fragment of announcer's identification information of the selection, thus complicated for operation when reducing user's broadcasting audio file Degree.

Specifically, a kind of audio file playing device of the embodiment of the present invention, further includes：

Segmentation module, for audio file to be played to be divided into multiple audio fragments according to preset duration, wherein when default A length of each sampling duration or every frame duration；

First audio frequency characteristics contrast module is broadcast for selecting the first audio fragment in multiple audio fragments, and default Search identical with the audio feature information of the first audio fragment the first audio-frequency information in sound person's database, and with the first audio The corresponding first announcer identification information of information, wherein the first audio fragment is any one audio piece in multiple audio fragments Section is stored with multiple audio-frequency informations and corresponding with each audio-frequency information in multiple audio-frequency informations in default announcer's database Announcer's identification information, audio feature information include at least one of acoustic feature and characteristics of image；

First index establishes module, for searching and the first audio in multiple audio fragments of audio file to be played The identical audio fragment of the audio feature information of information, and establish audio identical with the audio feature information of the first audio-frequency information The index of segment and first announcer's identification information obtains pretreated audio file to be played.

Specifically, a kind of audio file playing device of the embodiment of the present invention, further includes：

Segmentation module, for audio file to be played to be divided into multiple audio fragments according to preset duration, wherein when default A length of each sampling duration or every frame duration；

Second audio frequency characteristics contrast module, any two adjacent audio fragments for being directed in multiple audio fragments, When the audio feature information of two adjacent audio fragments is identical, using two adjacent audio fragments as the first audio Section, wherein audio feature information includes acoustic feature and characteristics of image, and the duration of the first audio section is greater than in multiple audio fragments Each audio fragment duration；

Second index establishes module, for obtaining the audio feature information of the first audio section, in default announcer's database It is middle to search identical with the audio feature information of the first audio section the second audio-frequency information, and corresponding with the second audio-frequency information the Two announcer's identification informations establish the index of the first audio section and second announcer's identification information, obtain pretreated wait broadcast Playback frequency file, wherein be stored in default announcer's database multiple audio-frequency informations and with it is each in multiple audio-frequency informations The corresponding announcer's identification information of audio-frequency information.

Specifically, a kind of audio file playing device of the embodiment of the present invention, further includes：

Background sound separation module, for there are when background sound, obtain point trained obtain in advance in audio file to be played From model, the background sound in audio file to be played is filtered by the disjunctive model that training obtains in advance, is filtered Audio file to be played afterwards, wherein the disjunctive model that training obtains in advance is used to filter the audio to be played there are background sound Background sound in file；

Correspondingly, segmentation module, is specifically used for：

Filtered audio file to be played is divided into multiple audio fragments according to preset duration.

Specifically, display module 920, is specifically used for

Show the announcer's identification information and options of pretreated audio file to be played；

Correspondingly, playing module 930, is specifically used for：

The options of user's selection and announcer's identification information of selection are obtained, and according to the options and choosing of selection The announcer's identification information selected plays pretreated audio file to be played.

Specifically, playing module 930, also particularly useful for：

When the options selected is including the options of positivity word, play in pretreated audio file to be played, Audio fragment corresponding with announcer's identification information of selection；

When the options selected is including the options of negativity word, play in pretreated audio file to be played, Audio fragment in addition to audio fragment corresponding with announcer's identification information of selection.

The embodiment of the invention also provides a kind of electronic equipment, as shown in Figure 10, including processor 1010, communication interface 1020, memory 1030 and communication bus 1040, wherein processor 1010, communication interface 1020, memory 1030 pass through communication Bus 1040 completes mutual communication,

Memory 1030, for storing computer program；

Processor 1010 when for executing the program stored on memory 1030, realizes following steps：

The play instruction that user plays pretreated audio file to be played is received, shows pretreated sound to be played Announcer's identification information of frequency file, wherein the audio fragment of pretreated audio file to be played is added with corresponding broadcast Member's identification information；

Announcer's identification information of user's selection is obtained, and according to announcer's identification information of selection, after playing pretreatment Audio file to be played.

A kind of electronic equipment provided in an embodiment of the present invention plays pretreated audio text to be played receiving user After the play instruction of part, show announcer's identification information of pretreated audio file to be played, wherein it is pretreated to The audio fragment for playing audio file is added with corresponding announcer's identification information；Announcer's identification information of user's selection is obtained, And according to announcer's identification information of selection, pretreated audio file to be played is played.As it can be seen that playing audio to be played When file, as long as user has selected the corresponding announcer's identification information of the audio fragment for wanting to listen, it can play and the selection The corresponding audio fragment of announcer's identification information, to reduce operation complexity when user plays audio file.

The communication bus that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component Interconnect, abbreviation PCI) bus or expanding the industrial standard structure (Extended Industry Standard Architecture, abbreviation EISA) bus etc..The communication bus can be divided into address bus, data/address bus, control bus etc.. Only to be indicated with a thick line in figure, it is not intended that an only bus or a type of bus convenient for indicating.

Communication interface is for the communication between above-mentioned electronic equipment and other equipment.

Memory may include random access memory (Random Access Memory, abbreviation RAM), also may include Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.Optionally, memory may be used also To be storage device that at least one is located remotely from aforementioned processor.

Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit, Abbreviation CPU), network processing unit (Network Processor, abbreviation NP) etc.；It can also be digital signal processor (Digital Signal Processing, abbreviation DSP), specific integrated circuit (Application Specific Integrated Circuit, abbreviation ASIC), field programmable gate array (Field-Programmable Gate Array, Abbreviation FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.

In another embodiment provided by the invention, a kind of computer readable storage medium is additionally provided, which can It reads to be stored with instruction in storage medium, when run on a computer, so that computer executes any institute in above-described embodiment A kind of audio file play method stated.

A kind of computer readable storage medium provided in an embodiment of the present invention, receive user play it is pretreated to After the play instruction for playing audio file, announcer's identification information of pretreated audio file to be played is shown, wherein pre- The audio fragment of treated audio file to be played is added with corresponding announcer's identification information；Obtain the announcer of user's selection Identification information, and according to announcer's identification information of selection, play pretreated audio file to be played.As it can be seen that playing When audio file to be played, as long as user has selected the corresponding announcer's identification information of the audio fragment for wanting to listen, it can play Audio fragment corresponding with announcer's identification information of the selection, thus complicated for operation when reducing user's broadcasting audio file Degree.

In another embodiment provided by the invention, a kind of computer program product comprising instruction is additionally provided, when it When running on computers, so that computer executes any a kind of audio file play method in above-described embodiment.

A kind of computer program product comprising instruction provided in an embodiment of the present invention plays pretreatment receiving user After the play instruction of audio file to be played afterwards, announcer's identification information of pretreated audio file to be played is shown, Wherein, the audio fragment of pretreated audio file to be played is added with corresponding announcer's identification information；Obtain user's selection Announcer's identification information play pretreated audio file to be played and according to announcer's identification information of selection.It can See, when playing audio file to be played, as long as user has selected the corresponding announcer's identification information of the audio fragment for wanting to listen, just Audio fragment corresponding with announcer's identification information of the selection can be played, thus when reducing user's broadcasting audio file Operation complexity.

In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer program Product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all or It partly generates according to process or function described in the embodiment of the present invention.The computer can be general purpose computer, dedicated meter Calculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage medium In, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, the computer Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center User's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or Data center is transmitted.The computer readable storage medium can be any usable medium that computer can access or It is comprising data storage devices such as one or more usable mediums integrated server, data centers.The usable medium can be with It is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid State Disk (SSD)) etc..

It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that There is also other identical elements in process, method, article or equipment including the element.

Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method Part explanation.

The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention It is interior.

Claims (13)

1. a kind of audio file play method, which is characterized in that the method includes：

Receive the play instruction that user plays pretreated audio file to be played；

Show announcer's identification information of the pretreated audio file to be played, wherein described pretreated wait broadcast The audio fragment of playback frequency file is added with corresponding announcer's identification information；

Announcer's identification information of user's selection is obtained, and according to selected announcer's identification information, plays the pre- place Audio file to be played after reason.

2. the method according to claim 1, wherein carrying out pretreated mistake to the audio file to be played Journey, including：

The audio file to be played is divided into multiple audio fragments according to preset duration, wherein the preset duration is each Sample duration or every frame duration；

The first audio fragment in the multiple audio fragment is selected, and is searched and described first in default announcer's database Identical first audio-frequency information of the audio feature information of audio fragment, and the first broadcast corresponding with first audio-frequency information Member's identification information, wherein first audio fragment is any one audio fragment in the multiple audio fragment, described default Be stored in announcer's database multiple audio-frequency informations and with each audio-frequency information is corresponding in the multiple audio-frequency information broadcasts Sound person's identification information, the audio feature information include at least one of acoustic feature and characteristics of image；

In multiple audio fragments of the audio file to be played, the audio feature information with first audio-frequency information is searched Identical audio fragment, and establish the audio fragment identical with the audio feature information of first audio-frequency information and described The index of first announcer's identification information obtains pretreated audio file to be played.

3. the method according to claim 1, wherein carrying out pretreated mistake to the audio file to be played Journey further includes：

The audio file to be played is divided into multiple audio fragments according to preset duration, wherein the preset duration is each Sample duration or every frame duration；

For any two adjacent audio fragments in the multiple audio fragment, in the audio of two adjacent audio fragments When characteristic information is identical, using two adjacent audio fragments as the first audio section, wherein the audio feature information includes Acoustic feature and characteristics of image, the duration of first audio section are greater than each audio fragment in the multiple audio fragment Duration；

The audio feature information for obtaining first audio section is searched and first audio section in default announcer's database Identical second audio-frequency information of audio feature information, and the second announcer corresponding with second audio-frequency information identify letter Breath, establishes the index of first audio section and the second announcer identification information, obtains pretreated audio to be played File, wherein be stored in default announcer's database multiple audio-frequency informations and with it is every in the multiple audio-frequency information The corresponding announcer's identification information of a audio-frequency information.

4. according to the method in claim 2 or 3, which is characterized in that it is described according to preset duration by the sound to be played Frequency file is divided into before multiple audio fragments, the method also includes：

In the audio file to be played there are when background sound, the disjunctive model that training obtains in advance is obtained, wherein described preparatory The disjunctive model that training obtains is used to filter the background sound in the audio file to be played there are background sound；

The disjunctive model obtained by the preparatory training is filtered the background sound in the audio file to be played, obtains Filtered audio file to be played；

Correspondingly, described be divided into multiple audio fragments for the audio file to be played according to preset duration, including：

The filtered audio file to be played is divided into multiple audio fragments according to preset duration.

5. the method according to claim 1, wherein described show the pretreated audio file to be played Announcer's identification information, including：

Show the announcer's identification information and options of the pretreated audio file to be played；

Correspondingly, the announcer's identification information for obtaining user's selection, and according to selected announcer's identification information, it broadcasts The pretreated audio file to be played is put, including：

The options of user's selection and announcer's identification information of selection are obtained, and according to the selected options and institute Announcer's identification information of selection is stated, the pretreated audio file to be played is played.

6. according to the method described in claim 5, it is characterized in that, described according to the selected options and the selection Announcer's identification information, play the pretreated audio file to be played, including：

The selected options be include the options of positivity word when, play the pretreated audio file to be played In, audio fragment corresponding with selected announcer's identification information；

The selected options be include the options of negativity word when, play the pretreated audio file to be played In, the audio fragment in addition to audio fragment corresponding with selected announcer's identification information.

7. a kind of audio file playing device, which is characterized in that described device includes：

Receiving module plays the play instruction of pretreated audio file to be played for receiving user；

Display module, for showing announcer's identification information of the pretreated audio file to be played, wherein described pre- The audio fragment of treated audio file to be played is added with corresponding announcer's identification information；

Playing module, for obtaining announcer's identification information of user's selection, and according to selected announcer's identification information, Play the pretreated audio file to be played.

8. device according to claim 7, which is characterized in that described device further includes：

Segmentation module, for the audio file to be played to be divided into multiple audio fragments according to preset duration, wherein described pre- If when a length of each sampling duration or every frame duration；

First audio frequency characteristics contrast module is broadcast for selecting the first audio fragment in the multiple audio fragment, and default Search identical with the audio feature information of first audio fragment the first audio-frequency information in sound person's database, and with it is described The corresponding first announcer identification information of first audio-frequency information, wherein first audio fragment is the multiple audio fragment In any one audio fragment, be stored in default announcer's database multiple audio-frequency informations and with the multiple audio The corresponding announcer's identification information of each audio-frequency information in information, the audio feature information includes acoustic feature and characteristics of image At least one of；

First index establishes module, for searching and described first in multiple audio fragments of the audio file to be played The identical audio fragment of the audio feature information of audio-frequency information, and establish the audio frequency characteristics with first audio-frequency information and believe The index for ceasing identical audio fragment and the first announcer identification information obtains pretreated audio file to be played.

9. device according to claim 7, which is characterized in that described device further includes：

Segmentation module, for the audio file to be played to be divided into multiple audio fragments according to preset duration, wherein described pre- If when a length of each sampling duration or every frame duration；

Second audio frequency characteristics contrast module, any two adjacent audio fragments for being directed in the multiple audio fragment, When the audio feature information of two adjacent audio fragments is identical, using two adjacent audio fragments as the first audio Section, wherein the audio feature information includes acoustic feature and characteristics of image, and the duration of first audio section is greater than described more The duration of each audio fragment in a audio fragment；

Second index establishes module, for obtaining the audio feature information of first audio section, in default announcer's database It is middle to search identical with the audio feature information of first audio section the second audio-frequency information, and with second audio-frequency information Corresponding second announcer identification information is established the index of first audio section and the second announcer identification information, is obtained To pretreated audio file to be played, wherein be stored in default announcer's database multiple audio-frequency informations and Announcer's identification information corresponding with audio-frequency information each in the multiple audio-frequency information.

10. device according to claim 8 or claim 9, which is characterized in that described device further includes：

Background sound separation module, for there are when background sound, obtain point trained obtain in advance in the audio file to be played From model, the disjunctive model obtained by the preparatory training is filtered the background sound in the audio file to be played, Obtain filtered audio file to be played, wherein there are background sounds for filtering for the disjunctive model that the preparatory training obtains Audio file to be played in background sound；

Correspondingly, the segmentation module, is specifically used for：

The filtered audio file to be played is divided into multiple audio fragments according to preset duration.

11. device according to claim 7, which is characterized in that the display module is specifically used for

Show the announcer's identification information and options of the pretreated audio file to be played；

Correspondingly, the playing module, is specifically used for：

The options of user's selection and announcer's identification information of selection are obtained, and according to the selected options and institute Announcer's identification information of selection is stated, the pretreated audio file to be played is played.

12. device according to claim 11, which is characterized in that the playing module, also particularly useful for：

The selected options be include the options of positivity word when, play the pretreated audio file to be played In, audio fragment corresponding with selected announcer's identification information；

The selected options be include the options of negativity word when, play the pretreated audio file to be played In, the audio fragment in addition to audio fragment corresponding with selected announcer's identification information.

13. a kind of electronic equipment, which is characterized in that including processor, communication interface, memory and communication bus, wherein processing Device, communication interface, memory complete mutual communication by communication bus；

Memory, for storing computer program；

Processor when for executing the program stored on memory, realizes any method and step of claim 1-6.