CN107609034A - A kind of audio frequency playing method of intelligent sound box, audio playing apparatus and storage medium - Google Patents
A kind of audio frequency playing method of intelligent sound box, audio playing apparatus and storage medium Download PDFInfo
- Publication number
- CN107609034A CN107609034A CN201710678203.XA CN201710678203A CN107609034A CN 107609034 A CN107609034 A CN 107609034A CN 201710678203 A CN201710678203 A CN 201710678203A CN 107609034 A CN107609034 A CN 107609034A
- Authority
- CN
- China
- Prior art keywords
- audio
- played
- sound box
- intelligent sound
- current speech
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention discloses a kind of audio frequency playing method of intelligent sound box, audio playing apparatus and storage medium, methods described includes：Intelligent sound box carries out speech detection and obtains current speech signal；Feature extraction is carried out to the current speech signal, obtains the current speech feature in the current speech signal；Search target audio corresponding with the current speech feature, and play the target audio, can be when user carries out audio broadcasting using intelligent sound box, intelligent sound box only needs to obtain for user automatically by the current speech feature for obtaining user and plays target audio, the target audio oneself liked is pushed manually every time without user, user's setting is simplified, improves Consumer's Experience.
Description
Technical field
The invention belongs to sound-box device field, more particularly to a kind of audio frequency playing method of intelligent sound box, audio to play dress
Put and storage medium.
Background technology
Audio amplifier is often used for playing music or audio file, some existing sound-box devices for user play music or
The audio to be played that user is pushed by mobile terminal (mobile phone, Pad, PC etc.) can be received during audio file, but to every
The individual user that audio broadcasting is carried out using the audio amplifier, existing intelligent sound box can't be by the audio files played with pushing this
The user-association of a little audio files gets up, so even being that same user is broadcast using same sound-box device progress audio every time
When putting, the music that is required for liking oneself is repeatedly pushed to sound-box device, frequent operation, and user experience is relatively low.
The above is only used for auxiliary and understands technical scheme, does not represent and recognizes that the above is existing skill
Art.
The content of the invention
It is a primary object of the present invention to provide a kind of audio frequency playing method of intelligent sound box, audio playing apparatus and deposit
Storage media, it is intended to solve in the prior art user every time using audio amplifier carry out audio broadcasting when, be required for carry out audio push,
The relatively low technical problem of user experience.
To achieve the above object, the invention provides a kind of audio frequency playing method of intelligent sound box, methods described include with
Lower step:
Intelligent sound box carries out speech detection, obtains current speech signal；
Feature extraction is carried out to the current speech signal, obtains the current speech feature in the current speech signal；
Target audio corresponding with the current speech feature is searched, and plays the target audio.
Preferably, the target audio according to corresponding to obtaining the target audio list, and play the target audio
Afterwards, methods described also includes：
The accumulative broadcasting time of each audio is counted, accumulative broadcasting time is more than the audio of preset times as referring to sound
Frequently；
Search the to be pushed audio associated with the reference audio；
When the target audio finishes, audio to be pushed described in broadcasting.
Preferably, after lookup target audio corresponding with the current speech feature, methods described also includes：
When not finding target audio corresponding with the current speech feature, prompt message is issued the user with；
The audio push instruction of user's input is received, audio-frequency information to be played, root are extracted from audio push instruction
According to audio to be played corresponding to the audio-frequency information acquisition to be played, and play the audio to be played.
Preferably, the audio to be played according to corresponding to obtaining the audio-frequency information to be played, and wait to broadcast described in broadcasting
After playback frequency, methods described also includes：
Mapping table is established, and the audio to be played and the current speech feature are associated；
By the audio to be played after association and the current speech characteristic storage into the mapping table.
Preferably, the audio to be played according to corresponding to obtaining the audio-frequency information to be played, is specifically included：
According to the audio-frequency information to be played, search whether corresponding audio to be played be present in local storage space；
If in the presence of obtaining the audio to be played found from the local storage space.
Preferably, it is described to be searched whether in local storage space after corresponding audio to be played being present, methods described
Also include：
If being not present, protected by audio to be played corresponding to Network Capture, and by the audio to be played got
Deposit to the local storage space.
Preferably, methods described also includes：
The pre- broadcasting audio instructions of user's input are received, it is pre- according to corresponding to obtaining the pre- broadcasting audio instructions to play sound
Frequently；
When currently played audio finishes, the pre- broadcasting audio is played out.
Preferably, the pre- broadcasting audio instructions for receiving user's input, according to the pre- broadcasting audio instructions acquisition pair
After the pre- broadcasting audio answered, methods described also includes：
The pre- broadcasting audio is added to the audio to be played.
In addition, to achieve the above object, the present invention also proposes a kind of audio playing apparatus, the audio playing apparatus bag
Include：Memory, processor and it is stored in the audio of the intelligent sound box that can be run on the memory and on the processor and broadcasts
Program is put, the audio playing program of the intelligent sound box is arranged for carrying out the audio frequency playing method of intelligent sound box as described above
The step of.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, and intelligence is stored with the storage medium
The audio playing program of audio amplifier, intelligence as described above is realized when the audio playing program of the intelligent sound box is executed by processor
The step of audio frequency playing method of energy audio amplifier.
The present invention carries out speech detection by intelligent sound box and obtains current speech signal；The current speech signal is carried out
Feature extraction, obtain the current speech feature in the current speech signal；Search mesh corresponding with the current speech feature
Mark with phonetic symbols frequency, and the target audio is played, can be when user carries out audio broadcasting using intelligent sound box, intelligent sound box only needs
Current speech feature by obtaining user can obtain for user and play target audio automatically, so that user need not be every
The target audio that secondary all manual push is wanted to play simplifies user's setting, improves Consumer's Experience to intelligent sound box.
Brief description of the drawings
Fig. 1 is the structural representation of the audio playing apparatus for the hardware running environment that scheme of the embodiment of the present invention is related to；
Fig. 2 is the schematic flow sheet of the audio frequency playing method first embodiment of intelligent sound box of the present invention；
Fig. 3 is the schematic flow sheet of the audio frequency playing method second embodiment of intelligent sound box of the present invention；
Fig. 4 is the schematic flow sheet of the audio frequency playing method 3rd embodiment of intelligent sound box of the present invention.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
It should be appreciated that specific embodiment described herein is not intended to limit the present invention only to explain the present invention.
Reference picture 1, Fig. 1 are the audio playing apparatus structural representation for the hardware running environment that scheme of the embodiment of the present invention is related to
Figure.
As shown in figure 1, the audio playing apparatus can include：Processor 1001, such as CPU, communication bus 1002, user
Interface 1003, network interface 1004, memory 1005, microphone array 1006.Wherein, communication bus 1002 is used to realize these
Connection communication between component.User interface 1003 can include display screen (Display), input block such as keyboard
(Keyboard), optional user interface 1003 can also include wireline interface, the wave point of standard.Network interface 1004 is optional
Wireline interface, the wave point (such as WI-FI interfaces) that can include standard.Memory 1005 can be high-speed RAM memory,
Can also be stable memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally may be used also
To be independently of the storage device of aforementioned processor 1001.
It will be understood by those skilled in the art that the structure shown in Fig. 1 does not form the restriction to audio playing apparatus, can
With including than illustrating more or less parts, either combining some parts or different parts arrangement.
As shown in figure 1, as in a kind of memory 1005 of storage medium can include operating system, data storage mould
Block, network communication module, the audio playing program of Subscriber Interface Module SIM and intelligent sound box.
The audio amplifier that the audio playing apparatus can be that by voice collecting or detection, program operation and audio plays
Equipment, the present embodiment are not any limitation as to this.
In the audio playing apparatus shown in Fig. 1, network interface 1004 is mainly used in leading to background server progress data
Letter；Microphone array 1006, is configured to gather or detects user and send current speech；User interface 1003 is mainly used in and user
Carry out data interaction；Processor 1001, memory 1005 in audio playing apparatus of the present invention can be arranged on audio and play dress
In putting, the audio playing apparatus calls the audio of the intelligent sound box stored in memory 1005 to play journey by processor 1001
Sequence, and perform following operate：
Intelligent sound box carries out speech detection, obtains current speech signal；
Feature extraction is carried out to the current speech signal, obtains the current speech feature in the current speech signal；
Target audio corresponding with the current speech feature is searched, and plays the target audio.
Further, processor 1001 can call the audio playing program of the intelligent sound box stored in memory 1005,
Also perform following operate：
The accumulative broadcasting time of each audio is counted, accumulative broadcasting time is more than the audio of preset times as referring to sound
Frequently；
Search the to be pushed audio associated with the reference audio；
When the target audio finishes, audio to be pushed described in broadcasting.
Further, processor 1001 can call the audio playing program of the intelligent sound box stored in memory 1005,
Also perform following operate：
When not finding target audio corresponding with the current speech feature, prompt message is issued the user with；
The audio push instruction of user's input is received, audio-frequency information to be played, root are extracted from audio push instruction
According to audio to be played corresponding to the audio-frequency information acquisition to be played, and play the audio to be played.
Further, processor 1001 can call the audio playing program of the intelligent sound box stored in memory 1005,
Also perform following operate：
Mapping table is established, and the audio to be played and the current speech feature are associated；
By the audio to be played after association and the current speech characteristic storage into the mapping table.
Further, processor 1001 can call the audio playing program of the intelligent sound box stored in memory 1005,
Also perform following operate：
According to the audio-frequency information to be played, search whether corresponding audio to be played be present in local storage space；
If in the presence of obtaining the audio to be played found from the local storage space.
Further, processor 1001 can call the audio playing program of the intelligent sound box stored in memory 1005,
Also perform following operate：
Preserved by audio to be played corresponding to Network Capture, and by the audio to be played got to the local
Memory space.
Further, processor 1001 can call the audio playing program of the intelligent sound box stored in memory 1005,
Also perform following operate：
The pre- broadcasting audio instructions of user's input are received, it is pre- according to corresponding to obtaining the pre- broadcasting audio instructions to play sound
Frequently；
When currently played audio finishes, the pre- broadcasting audio is played out.
Further, processor 1001 can call the audio playing program of the intelligent sound box stored in memory 1005,
Also perform following operate：
The pre- broadcasting audio is added to the audio to be played.
The beneficial effect of the embodiment of the present invention is：Intelligent sound box carries out speech detection and obtains current speech signal；To described
Current speech signal carries out feature extraction, obtains the current speech feature in the current speech signal；Search and described current
Target audio corresponding to phonetic feature, and the target audio is played, so that user using audio amplifier when carrying out audio broadcasting
The target audio for wanting to play need not be pushed manually every time to intelligent sound box, user's setting is simplified, improve user's body
Test.
Based on above-mentioned hardware configuration, the audio frequency playing method embodiment of intelligent sound box of the present invention is proposed.
Reference picture 2, Fig. 2 are a kind of schematic flow sheet of the audio frequency playing method first embodiment of intelligent sound box of the present invention.
In the present embodiment, it the described method comprises the following steps：
Step S10：Intelligent sound box carries out speech detection, obtains current speech signal；
It should be noted that the method executive agent of the present embodiment is intelligent sound box, the intelligent sound box can be can
Realize sound-box device or device that voice collecting or detection, program operation and audio play.
Intelligent sound box in the present embodiment can incite somebody to action when receiving startup voice or the instruction in current environment preset range
Equipment state is adjusted to open from shutdown or holding state or working condition, that is to say, that user can be referred to by sending voice
Make such as " unlatching ", " opening audio amplifier " or " unlatching audio amplifier " etc. to carry out " wake-up " intelligent sound box, intelligent sound box is entered work shape
State, the preset range size and phonetic order can be depending on actual conditions, and the present embodiment is not any limitation as to this.
It should be understood that when user sends default phonetic order " wake-up " described intelligent sound box, the intelligent sound box
Speech detection is carried out to surrounding environment by preset acoustic sensor, gathers the voice signal in current environment, it is contemplated that
Microphone array has the advantages that noise suppressed compared with traditional acoustic sensor, echo suppresses and dereverberation, this implementation
It is preferred that carrying out speech detection to current environment using microphone array, the voice signal in environment is gathered.
Gathered it should be noted that intelligent sound box carries out speech detection by microphone array to current environment in environment
During voice signal, there may be multiple sound generation sources in current environment simultaneously, to avoid intelligent sound box to each language for getting
Sound signal all carries out feature extraction, so as to additionally increase the workload of intelligent sound box, can believe in the current speech to getting
Number carry out feature extraction before, judge whether the signal intensity of the current speech signal is more than preset signal strength；If being more than,
Feature extraction is carried out to the current speech signal, the preset signal strength can be adjusted according to actual conditions, for example, when detection
When multiple voice signals into current environment be present, preset signal strength described in automatic adjustment height, when detecting in current environment only
When having a voice signal, relative to turn down the preset signal strength, setting and the regulation of specific preset signal strength can bases
Actual conditions are set, and this implementation is not any limitation as to this.
Step S20：Feature extraction is carried out to the current speech signal, obtains the current language in the current speech signal
Sound feature；
It should be noted that intelligent sound box is filtering out voice signal of the current signal strength more than preset signal strength
Afterwards, to exclude the noisy speech signals after screening in voice signal, the vehicle of such as pet, other home appliances or outdoor is sent
Voice signal, it is necessary to first be recognized to the voice signal got, it is determined that the current speech signal is active user
In the case of setting out, then feature extraction is carried out to the current speech signal, the feature extraction can be that extraction is described current
Tonality feature, loudness feature, tamber characteristic or vocal print feature etc. corresponding to voice signal, the present embodiment is not any limitation as to this,
But in view of the high identification and accuracy of vocal print feature, the present embodiment preferentially carries out vocal print to currently detected voice signal
Feature extraction.
Step S30：Target audio corresponding with the current speech feature is searched, and plays the target audio.
Certainly, before the step is performed, intelligent sound box can push to intelligent sound box for the first time in user according to personal like
When music or audio, the user vocal feature obtained in advance is associated with the music or audio to be played pushed, so as to
Phonetic feature corresponding to enough current speech signals that when user uses intelligent sound box next time, can be sent by extracting user, so
Afterwards again by the phonetic feature can obtain corresponding to the target audio that pushes in advance of user.
In the specific implementation, when user opens intelligent sound box progress audio broadcasting, intelligent sound box meeting basis is extracted
Current speech feature goes to search the to be played audio (i.e. target audio) associated with the current phonetic feature, and is broadcast for user
Put, for example, when user comes home from work and felt exhausted, it is desirable to listen several first songs to loosen mood, now he is only needed to intelligent sound box
Say " unlatching ", equipment state will be adjusted to working condition by intelligent sound box automatically, and carry out speech detection, be worked as getting
During voice signal in preceding environment, the vocal print feature of the voice signal can be extracted, then goes to search and broadcasts according to the vocal print feature
Put corresponding target audio.
Intelligent sound box obtains current speech signal by carrying out speech detection in the present embodiment；To the current speech signal
Feature extraction is carried out, obtains the current speech feature in the current speech signal；Search corresponding with the current speech feature
Target audio, and the target audio is played, so that user need not be when carrying out audio broadcasting using audio amplifier every time
The target audio that push is wanted to play manually simplifies user's setting, improves Consumer's Experience to intelligent sound box.
With reference to figure 3, Fig. 3 is the schematic flow sheet of the audio frequency playing method second embodiment of intelligent sound box of the present invention.
Based on above-mentioned first embodiment, the audio frequency playing method for the intelligent sound box that the present embodiment proposes after step S30,
Also include：
S50：The accumulative broadcasting time of each audio is counted, accumulative broadcasting time is more than the audio of preset times as reference
Audio；
It is understood that audio or the style of music that different users likes all are not quite similar, but same person is liked
Joyous audio or the style of music or type are typically relatively fixed, such as user A likes listening the song of Chinese feature type, user B
Like listening comic monologue, user C likes listening children's story etc..Different user may for the audio or song each preferred
Multiple broadcasting can be circulated, provides the user broadcasting service for more hommization, intelligent sound box can push in advance playing user
Audio when, can also count the number that each audio is accumulated broadcasting, then filter out accumulative broadcasting time and be more than preset times
Audio be set as 10 times as reference audio, such as by preset times, obtain the audio that accumulative broadcasting time is more than 10 times.
Certainly, in order to avoid over time, the accumulative broadcasting time of audio is generally above default broadcasting time
Number, can by presetting a timing statisticses scope or cycle, for example, week about or two weeks progress one secondary audio program broadcasting
Number is counted, and specific timing statisticses scope or cycle can be set according to actual conditions, and the present embodiment is not any limitation as to this.
S60：Search the to be pushed audio associated with the reference audio；
It should be noted that intelligent sound box gets accumulative broadcasting time more than default broadcasting time in the present embodiment
After reference audio, information extraction can be carried out to the reference audio got, obtain audio attribute corresponding to each reference audio,
And search to be used as more than the audio of predetermined threshold value with the audio attribute matching degree in local storage space or Internet resources and treat
Push audio.To improve search efficiency, intelligent sound box is being searched when audio is pushed, preferentially can entered in local storage space
Row is searched.In the present embodiment, the audio attribute may include (by taking song as an example)：Singer's name, album name, song style etc.,
The setting of the species and predetermined threshold value of specific audio attribute can be depending on actual conditions, and the present embodiment is not limited this
System.
In the specific implementation, intelligent sound box after reference audio is got, can the reference audio for search benchmark, from
The audio for exceeding predetermined threshold value with the reference audio matching degree, and the sound that these are got are obtained in local or Internet resources
Frequency is used as audio to be pushed.
S70：When the target audio finishes, audio to be pushed described in broadcasting.
In the specific implementation, after target audio is played, to improve Consumer's Experience, intelligent sound box can be to getting
Audio to be pushed play out, the audio of its personal like may be met by playing so as to continuing as user.
The present embodiment intelligent sound box counts the accumulative broadcasting time of each audio in audio playing process is carried out, will be accumulative
Broadcasting time is more than the audio of preset times as reference audio；Search the to be pushed audio associated with the reference audio；
Can after the target audio that user pushes in advance has been played, automatically for user play described in audio to be pushed, allow user
It can continue to listen to the audio oneself liked without push audio manually, improve user experience.
With reference to figure 4, Fig. 4 is the schematic flow sheet of the audio frequency playing method 3rd embodiment of intelligent sound box of the present invention.
The audio frequency playing method of the intelligent sound box proposed based on the various embodiments described above, the present embodiment is after step S20, also
Including：
Step S301：When not finding target audio corresponding with the current speech feature, prompting is issued the user with
Information；
It is understood that phonetic feature corresponding to the user of voice signal is not each sent in intelligent sound box
In the presence of being associated or corresponding audio to be played (target audio), such as the first user for using intelligent sound box, user are prior
The audio to be played that oneself is liked intelligent sound box is not pushed to, intelligent sound box can not naturally also be completed to treat user's push
The current speech feature for playing audio and getting is associated this operation.
Now, to improve user experience, intelligent sound box can send prompting to the user for not pushing audio to be played previously
For information to prompt user to carry out audio push, its specific prompting mode can also pass through intelligent sound box by voice broadcast
Man-machine interaction panel show corresponding word to remind user to carry out audio push, the present embodiment is not any limitation as to this.
, can in the specific implementation, when intelligent sound box does not find target audio corresponding with the current speech feature
Prompt message, such as voice broadcast are sent by predetermined manner to prompt user to carry out the push of audio to be played.
Step S401：The audio push instruction of user's input is received, sound to be played is extracted from audio push instruction
Frequency information, the audio to be played according to corresponding to obtaining the audio-frequency information to be played, and play the audio to be played.
, can be according to personal like to intelligence it is understood that user is after the prompt message that intelligent sound box is sent is received
The audio to be played that energy audio push wants to listen to, such as " song ", " cross-talk ", " Lecture Room " etc., when intelligent sound box receives
When the audio inputted to user by the man-machine interaction panel of mobile terminal or intelligent sound box pushes instruction, the audio can be pushed away
Send instruction to be parsed, obtain the information of the audio to be played included in the audio push instruction, the audio to be played
Information can be under Internet resources corresponding to audio file corresponding to the audio to be played or the audio to be played
Set address, audio title corresponding to the audio to be played is can also be, when intelligent sound box extracts above-mentioned audio letter to be played
During breath, correspondingly operated according to different perform of described information content, with audio to be played corresponding to acquisition, the sound to be played
The setting of the frequency information and specific implementation of audio to be played can be according to reality according to corresponding to obtaining the audio-frequency information to be played
Depending on the situation of border, the present embodiment is not any limitation as to this.
It should be understood that the sound to be played that different users when carrying out audio broadcasting using same audio amplifier, is pushed
Frequency, in order to avoid repetition of the intelligent sound box to audio resource obtains, may save local storage space, and improve by partly overlapping
The speed of the audio to be played is obtained, methods described also includes：According to the audio-frequency information to be played, in local storage space
In search whether corresponding audio to be played be present；If in the presence of, from the local storage space obtain find described in
Audio to be played；If being not present, by audio to be played corresponding to Network Capture, and the audio to be played that will be got
Preserve to the local storage space.
Do not have to continue to push manually during to make the user for pushing audio to be played for the first time reuse the intelligent sound box to wait to broadcast
Playback frequency, methods described also include：Mapping table is established, and the audio to be played and the current speech feature are carried out
Association；By the audio to be played after association and the current speech characteristic storage into the mapping table.
In the specific implementation, intelligent sound box will can extract for the first user that audio push is carried out using audio amplifier
Phonetic feature (such as vocal print feature) is used as log-on message, creates user account for active user automatically, then pushes user
Audio to be played be associated with the phonetic feature extracted, and by the audio to be played after association and the current language
Sound feature and the user account newly created or its account ID are bound and preserved into the mapping table pre-established.
It should be noted that the mapping relations, it is mutually " right either between classification and classification between two elements to refer to
Should " relation, you can with by pre-establishing this mapping relations, by the one of which element in the mapping relations or
Classification, precisely rapidly find corresponding element or classification.The present embodiment is by establishing mapping table, after association
The audio to be played and the current speech characteristic storage into the mapping table, so as to make intelligent sound box exist
When extracting phonetic feature, the audio (i.e. target audio) to be played according to corresponding to rapidly searching the mapping table.
Intelligent sound box in the present embodiment is not when finding target audio corresponding with the current speech feature, Xiang Yong
Family sends prompt message to prompt user to carry out audio push, when the audio for receiving user's input pushes instruction, from the sound
Audio-frequency information to be played is extracted in frequency push instruction, the audio to be played according to corresponding to obtaining the audio-frequency information to be played, and
The audio to be played is played, so as to be sound to be played corresponding to first user's quick obtaining using intelligent sound box and broadcasting
Frequently, Consumer's Experience is improved.
Based on the various embodiments described above, the audio frequency playing method for the intelligent sound box that the present embodiment proposes also includes：
The pre- broadcasting audio instructions of user's input are received, it is pre- according to corresponding to obtaining the pre- broadcasting audio instructions to play sound
Frequently；When currently played audio finishes, the pre- broadcasting audio is played out.
It is understood that user is during carrying out music or audio using intelligent sound box and playing, may be unexpected
Want to listen other audios, for example, user has listened the music of a period of time, suddenly want to listen just listening opera or cross-talk, now only need
Pre- broadcasting audio instructions are inputted by the man-machine interaction panel of mobile terminal or intelligent sound box, when intelligent sound box receives user
During the pre- broadcasting audio instructions of input, the pre- broadcasting audio instructions are parsed, pre- broadcasting audio corresponding to acquisition, and
When currently played audio finishes, the pre- broadcasting audio got is played out.Meanwhile in order that under user
Secondary when listening to audio, without carrying out secondary push to the pre- broadcasting audio of this broadcasting again, intelligent sound box pre- can also be broadcast described
Playback frequency is added to the audio to be played, to simplify user's setting, improves Consumer's Experience.
The pre- broadcasting audio instructions that the present embodiment intelligent sound box is currently inputted by receiving user, and according to the pre- broadcasting
Audio instructions play audio in advance corresponding to obtaining；When currently played audio finishes, immediately to the pre- broadcasting sound
Frequency plays out, and so as to the audio wanted to listen at broadcasting current time for user of more hommization, improves the experience of user
Sense.
In addition, the embodiment of the present invention also proposes a kind of storage medium, the sound of intelligent sound box is stored with the storage medium
Frequency playing program, following operation is realized when the audio playing program of the intelligent sound box is executed by processor：
Intelligent sound box carries out speech detection, obtains current speech signal；
Feature extraction is carried out to the current speech signal, obtains the current speech feature in the current speech signal；
Target audio corresponding with the current speech feature is searched, and plays the target audio.
Further, following operation is also realized when the audio playing program of intelligent sound box is executed by processor：
The accumulative broadcasting time of each audio is counted, accumulative broadcasting time is more than the audio of preset times as referring to sound
Frequently；
Search the to be pushed audio associated with the reference audio；
When the target audio finishes, audio to be pushed described in broadcasting.
Further, following operation is also realized when the audio playing program of intelligent sound box is executed by processor：
When not finding target audio corresponding with the current speech feature, prompt message is issued the user with；
The audio push instruction of user's input is received, audio-frequency information to be played, root are extracted from audio push instruction
According to audio to be played corresponding to the audio-frequency information acquisition to be played, and play the audio to be played.
Further, following operation is also realized when the audio playing program of intelligent sound box is executed by processor：
Mapping table is established, and the audio to be played and the current speech feature are associated；
By the audio to be played after association and the current speech characteristic storage into the mapping table.
Further, following operation is also realized when the audio playing program of intelligent sound box is executed by processor：
According to the audio-frequency information to be played, search whether corresponding audio to be played be present in local storage space；
If in the presence of obtaining the audio to be played found from the local storage space.
Further, following operation is also realized when the audio playing program of intelligent sound box is executed by processor：
Preserved by audio to be played corresponding to Network Capture, and by the audio to be played got to the local
Memory space.
Further, following operation is also realized when the audio playing program of intelligent sound box is executed by processor：
The pre- broadcasting audio instructions of user's input are received, it is pre- according to corresponding to obtaining the pre- broadcasting audio instructions to play sound
Frequently；
When currently played audio finishes, the pre- broadcasting audio is played out.
Further, following operation is also realized when the audio playing program of intelligent sound box is executed by processor：
The pre- broadcasting audio is added to the audio to be played.
The beneficial effect of the embodiment of the present invention is：Intelligent sound box carries out speech detection and obtains current speech signal；To described
Current speech signal carries out feature extraction, obtains the current speech feature in the current speech signal；Search and described current
Target audio corresponding to phonetic feature, and the target audio is played, so that user using audio amplifier when carrying out audio broadcasting
The target audio for wanting to play need not be pushed manually every time to intelligent sound box, user's setting is simplified, improve user's body
Test.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, method, article or system institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Other identical element also be present in the process of key element, method, article or system.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions to cause a station terminal equipment (can be mobile phone, computer, clothes
Be engaged in device, air conditioner, or network equipment etc.) perform method described in each embodiment of the present invention.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of audio frequency playing method of intelligent sound box, it is characterised in that methods described includes：
Intelligent sound box carries out speech detection, obtains current speech signal；
Feature extraction is carried out to the current speech signal, obtains the current speech feature in the current speech signal；
Target audio corresponding with the current speech feature is searched, and plays the target audio.
2. the method as described in claim 1, it is characterised in that the target according to corresponding to obtaining the target audio list
Audio, and after playing the target audio, methods described also includes：
The accumulative broadcasting time of each audio is counted, accumulative broadcasting time is more than the audio of preset times as reference audio；
Search the to be pushed audio associated with the reference audio；
When the target audio finishes, audio to be pushed described in broadcasting.
3. method as claimed in claim 2, it is characterised in that described to search target sound corresponding with the current speech feature
After frequency, methods described also includes：
When not finding target audio corresponding with the current speech feature, prompt message is issued the user with；
The audio push instruction of user's input is received, audio-frequency information to be played is extracted from audio push instruction, according to institute
Audio to be played corresponding to audio-frequency information acquisition to be played is stated, and plays the audio to be played.
4. method as claimed in claim 3, it is characterised in that described to be treated according to corresponding to obtaining the audio-frequency information to be played
Audio is played, and after playing the audio to be played, methods described also includes：
Mapping table is established, and the audio to be played and the current speech feature are associated；
By the audio to be played after association and the current speech characteristic storage into the mapping table.
5. method as claimed in claim 4, it is characterised in that described to be treated according to corresponding to obtaining the audio-frequency information to be played
Audio is played, is specifically included：
According to the audio-frequency information to be played, search whether corresponding audio to be played be present in local storage space；If deposit
The audio to be played found is then being obtained from the local storage space.
6. method as claimed in claim 5, it is characterised in that described to be searched whether in local storage space in the presence of corresponding
After audio to be played, methods described also includes：
If being not present, by audio to be played corresponding to Network Capture, and by the audio to be played got preserve to
The local storage space.
7. method as claimed in claim 6, it is characterised in that methods described also includes：
The pre- broadcasting audio instructions of user's input are received, it is pre- according to corresponding to obtaining the pre- broadcasting audio instructions to play audio；
When currently played audio finishes, the pre- broadcasting audio is played out.
8. method as claimed in claim 7, it is characterised in that the pre- broadcasting audio instructions for receiving user's input, according to
After pre- broadcasting audio corresponding to the pre- broadcasting audio instructions acquisition, methods described also includes：
The pre- broadcasting audio is added to the audio to be played.
9. a kind of audio playing apparatus, it is characterised in that the audio playing apparatus includes：Memory, processor and it is stored in
On the memory and the audio playing program of intelligent sound box that can run on the processor, the audio of the intelligent sound box
Playing program is arranged for carrying out the step of audio frequency playing method of the intelligent sound box as any one of claim 1 to 8.
10. a kind of storage medium, it is characterised in that the audio playing program of intelligent sound box, institute are stored with the storage medium
State the intelligent sound box realized when the audio playing program of intelligent sound box is executed by processor as described in any one of claim 1 to 8
Audio frequency playing method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710678203.XA CN107609034A (en) | 2017-08-09 | 2017-08-09 | A kind of audio frequency playing method of intelligent sound box, audio playing apparatus and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710678203.XA CN107609034A (en) | 2017-08-09 | 2017-08-09 | A kind of audio frequency playing method of intelligent sound box, audio playing apparatus and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107609034A true CN107609034A (en) | 2018-01-19 |
Family
ID=61065103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710678203.XA Pending CN107609034A (en) | 2017-08-09 | 2017-08-09 | A kind of audio frequency playing method of intelligent sound box, audio playing apparatus and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107609034A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108551376A (en) * | 2018-02-09 | 2018-09-18 | 北京猎户星空科技有限公司 | A kind of individualized radio station playback method, medium, relevant device and system |
| CN108804070A (en) * | 2018-05-30 | 2018-11-13 | Oppo广东移动通信有限公司 | Method for playing music, device, storage medium and electronic equipment |
| CN108881978A (en) * | 2018-06-29 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Resource playing method and device for smart machine |
| CN109040904A (en) * | 2018-10-31 | 2018-12-18 | 北京羽扇智信息科技有限公司 | The audio frequency playing method and device of intelligent sound box |
| TWI684874B (en) * | 2018-10-18 | 2020-02-11 | 瑞軒科技股份有限公司 | Smart speaker and operation method thereof |
| CN110858841A (en) * | 2018-08-07 | 2020-03-03 | 三星电子株式会社 | Electronic device and method for registering new user by authentication of registered user |
| CN111339348A (en) * | 2018-12-19 | 2020-06-26 | 北京京东尚科信息技术有限公司 | Information service method, device and system |
| CN112287163A (en) * | 2020-10-29 | 2021-01-29 | 珠海格力电器股份有限公司 | Song playing method and device of intelligent air conditioner |
| CN113126951A (en) * | 2021-04-16 | 2021-07-16 | 深圳地平线机器人科技有限公司 | Audio playing method and device, computer readable storage medium and electronic equipment |
| CN113438564A (en) * | 2021-06-22 | 2021-09-24 | 武汉领普科技有限公司 | Control system, terminal processing method, wireless switch and processing method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572009A (en) * | 2015-01-28 | 2015-04-29 | 合肥联宝信息技术有限公司 | External environment adaptive audio control method and device |
| CN105812969A (en) * | 2014-12-31 | 2016-07-27 | 展讯通信（上海）有限公司 | Method, system and device for picking up sound signal |
| CN106131718A (en) * | 2016-08-10 | 2016-11-16 | 微云（武汉）科技有限公司 | A kind of intelligent sound box system and control method thereof |
| CN106341756A (en) * | 2016-08-29 | 2017-01-18 | 北海爱飞数码科技有限公司 | Customized intelligent sound box |
| CN106372246A (en) * | 2016-09-20 | 2017-02-01 | 深圳市同行者科技有限公司 | Audio playing method and device |
-
2017
- 2017-08-09 CN CN201710678203.XA patent/CN107609034A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105812969A (en) * | 2014-12-31 | 2016-07-27 | 展讯通信（上海）有限公司 | Method, system and device for picking up sound signal |
| CN104572009A (en) * | 2015-01-28 | 2015-04-29 | 合肥联宝信息技术有限公司 | External environment adaptive audio control method and device |
| CN106131718A (en) * | 2016-08-10 | 2016-11-16 | 微云（武汉）科技有限公司 | A kind of intelligent sound box system and control method thereof |
| CN106341756A (en) * | 2016-08-29 | 2017-01-18 | 北海爱飞数码科技有限公司 | Customized intelligent sound box |
| CN106372246A (en) * | 2016-09-20 | 2017-02-01 | 深圳市同行者科技有限公司 | Audio playing method and device |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108551376A (en) * | 2018-02-09 | 2018-09-18 | 北京猎户星空科技有限公司 | A kind of individualized radio station playback method, medium, relevant device and system |
| CN108804070A (en) * | 2018-05-30 | 2018-11-13 | Oppo广东移动通信有限公司 | Method for playing music, device, storage medium and electronic equipment |
| CN108881978A (en) * | 2018-06-29 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Resource playing method and device for smart machine |
| CN108881978B (en) * | 2018-06-29 | 2020-03-20 | 百度在线网络技术（北京）有限公司 | Resource playing method and device for intelligent equipment |
| CN110858841B (en) * | 2018-08-07 | 2023-04-07 | 三星电子株式会社 | Electronic device and method for registering new user through authentication of registered user |
| CN110858841A (en) * | 2018-08-07 | 2020-03-03 | 三星电子株式会社 | Electronic device and method for registering new user by authentication of registered user |
| TWI684874B (en) * | 2018-10-18 | 2020-02-11 | 瑞軒科技股份有限公司 | Smart speaker and operation method thereof |
| US11955125B2 (en) | 2018-10-18 | 2024-04-09 | Amtran Technology Co., Ltd. | Smart speaker and operation method thereof |
| CN109040904A (en) * | 2018-10-31 | 2018-12-18 | 北京羽扇智信息科技有限公司 | The audio frequency playing method and device of intelligent sound box |
| CN111339348A (en) * | 2018-12-19 | 2020-06-26 | 北京京东尚科信息技术有限公司 | Information service method, device and system |
| CN112287163A (en) * | 2020-10-29 | 2021-01-29 | 珠海格力电器股份有限公司 | Song playing method and device of intelligent air conditioner |
| CN113126951A (en) * | 2021-04-16 | 2021-07-16 | 深圳地平线机器人科技有限公司 | Audio playing method and device, computer readable storage medium and electronic equipment |
| CN113438564A (en) * | 2021-06-22 | 2021-09-24 | 武汉领普科技有限公司 | Control system, terminal processing method, wireless switch and processing method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609034A (en) | A kind of audio frequency playing method of intelligent sound box, audio playing apparatus and storage medium | |
| CN107360507A (en) | A kind of play parameter Automatic adjustment method, intelligent sound box and storage medium | |
| CN103886857B (en) | A kind of noise control method and equipment | |
| US20170126600A1 (en) | System and method for broadcasting audio tweets | |
| CN107995360B (en) | Call processing method and related product | |
| CN106155470B (en) | A kind of audio file generation method and device | |
| CN102568478A (en) | Video play control method and system based on voice recognition | |
| CN102917119B (en) | Method and system for processing music by mobile terminal according to voice recognition | |
| CN108074557A (en) | Tone regulating method, device and storage medium | |
| CN103188026A (en) | Voice broadcasting control device | |
| CN101739437A (en) | Implementation method for network sound-searching unit and specific device thereof | |
| CN106372246A (en) | Audio playing method and device | |
| CN101867742A (en) | Television system based on sound control | |
| CN107656977A (en) | The acquisition of multimedia file and player method and device | |
| CN104091596A (en) | Music identifying method, system and device | |
| CN111540370A (en) | Audio processing method and device, computer equipment and computer readable storage medium | |
| CN102244750A (en) | Video display apparatus having sound level control function and control method thereof | |
| CN108733341A (en) | A kind of voice interactive method and device | |
| CN109100943A (en) | Speaker and TV at the control method of system, device, equipment and medium | |
| JP3940723B2 (en) | Dialog information analyzer | |
| CN105278684B (en) | A kind of intelligent playing method and device | |
| CN106681713A (en) | Multimedia resource playing operation control method and device | |
| CN110347864A (en) | A kind of intelligence adjusts the method and system of audio frequency parameter | |
| CN106598536A (en) | Record startup method and apparatus for electronic device, and electronic device | |
| CN103366779A (en) | Method and device for automatic setting of sound-effect parameters |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180119 |