Summary of the invention
The problem that the present invention solves provides a kind of speech type music controller, controls the application of local music by voice, also can promote user's experience when improving traffic safety.
For addressing the above problem, the invention provides a kind of speech type music controller, comprising:
Voice input module is used for receiving speech information;
Sound identification module connects voice input module, is used for the voice messaging that receives is identified processing, and obtains phonetic feature information;
Instruction forms module, connects sound identification module, forms corresponding phonetic order information based on the phonetic feature information that receives, and described phonetic order information comprises function command information or content instruction information;
Local music processing module, link order form module, when obtaining function command information, start the application of local music, and carry out corresponding operating when follow-up acquisition content instruction information; Perhaps, when obtaining content instruction information, start the application of local music, and according to content instruction information and executing corresponding operating.
Alternatively, described sound identification module comprises:
The phonetic feature recognition unit connects voice input module, is used for the voice messaging that receives is identified to draw phonetic feature information;
The phonetic feature storehouse is used for a plurality of phonetic feature information of storage;
Search unit, connect phonetic feature storehouse, phonetic feature recognition unit and instruction and form module, be used for searching out from the phonetic feature storehouse phonetic feature information corresponding with the phonetic feature information that receives, and the phonetic feature information that searches out is sent to instruction forms module.
Alternatively, described instruction formation module comprises:
The phonetic order collection is used for a plurality of phonetic order information of storage, and wherein, described phonetic order information comprises function command information and content instruction information, and has corresponding relation between described phonetic order information and the phonetic feature information;
The instruction recognition unit, connect sound identification module, phonetic order collection and local music processing module, be used for identifying the phonetic order information corresponding with the phonetic feature information that receives from phonetic order is concentrated, and the phonetic order information that identifies is sent to the local music processing module.
Alternatively, the speech type music controller also comprises: reminding module, the link order recognition unit is used for pointing out according to the recognition result of instruction recognition unit.
Alternatively, described recognition result according to the instruction recognition unit is pointed out and is comprised: unidentified during to phonetic order information at the instruction recognition unit, and the prompting that described reminding module fails to identify.
Alternatively, the speech type music controller also comprises: the response message memory module, connect reminding module, and be used for the storage response message; Described recognition result according to the instruction recognition unit is pointed out and is comprised: when the instruction recognition unit draws phonetic order information, described reminding module searches out the response message corresponding with phonetic order information from the response message memory module, and points out according to described corresponding response message.
Alternatively, the speech type music controller also comprises: trigger module starts described speech type music controller based on user's solicited message.
Alternatively, described trigger module is for triggering button.
Alternatively, the speech type music controller also comprises:
Timing module is used for timing;
Control module connects local music processing module and timing module, the duration that control timing module record local music processing module is not carried out phonetic order information, when described duration during greater than threshold time, closes the speech type music controller.
Alternatively, described voice input module is microphone.
Alternatively, described local music processing module comprises:
The instruction resolution unit, link order forms module, the phonetic order information that receives is resolved, to identify function command information or content instruction information;
The local music storage unit is used for storage local music information;
The music data detecting unit connects local music storage unit and instruction resolution unit, when the instruction resolution unit identifies content instruction information, detects in the local music storage unit whether have the local music data corresponding with described content instruction information;
The local music functional unit, link order resolution unit and music data detecting unit, receive the instruction resolution unit identify function command information the time, start the application of local music, and detect execution corresponding operating when having the local music data corresponding with described content instruction information at follow-up content instruction information and the music data detecting unit of identifying; Perhaps, receive the instruction resolution unit identify content instruction information the time, start the application of local music, and detect when having the local music data corresponding with described content instruction information according to described content instruction information and executing corresponding operating at the music data detecting unit.
Alternatively, described local music processing module also comprises: the external memory storage recognition unit is used for the identification external memory storage and whether is connected to the speech type music controller; Wherein, after described external memory storage recognition unit identifies external memory storage and is connected to the speech type music controller, the music data detecting unit detects external memory storage, to determine whether there are the local music data corresponding with content instruction information in the external memory storage.
Alternatively, described local music processing module also comprises: the voice broadcast unit, connect described music data detecting unit and external memory storage recognition unit, do not detect the local music data corresponding with content instruction information at the music data detecting unit, perhaps externally storer is not connected to the speech type music controller, when perhaps the music data detecting unit does not detect the music data corresponding with content instruction information when externally storer is connected to the speech type music controller from external memory storage, the prompting of failing to identify.
Alternatively, described local music processing module also comprises the music information recording unit, is used for the music information of playing is carried out record; Described local music functional unit is receiving after the function command information that identifies of instruction resolution unit starts the application of local music, and before receiving the follow-up content instruction information that identifies, the music of the last broadcast of recording in the music information recording unit is play.
Alternatively, the local music processing module also comprises: sequencing unit, connect the music information recording unit, and be used for sorting according to playing the music of frequency to the music information recording unit at least.
Alternatively, described local music functional unit is receiving after the function command information that identifies of instruction resolution unit starts the application of local music, and before receiving the follow-up content instruction information that identifies, play playing the highest music of frequency in the music information recording unit.
Compared with prior art, the present invention has the following advantages at least:
1) speech type music controller of the present invention, by from the voice messaging that receives, identifying phonetic feature information, obtain corresponding phonetic order information according to the phonetic feature information that identifies, and carry out the operation of various local musics according to corresponding command information.In this mode, can replace manually control that the application of local music is controlled by phonetic order, thereby can reduce the dispersion of driver's notice, improve traffic safety; Simultaneously can also promote driving enjoyment.This speech type music controller of what is more important can also be provided convenience and possibility for the disabled controls automobile.
2) in the possibility, the speech type music controller can also comprise reminding module, and described reminding module can carry out corresponding different prompting according to recognition result, thereby convenient for users to use further, and has further improved user's experience.
3) in the possibility, the speech type music controller can also comprise timing module and control module, and in duration that the local music processing module is not carried out phonetic order information during greater than threshold time, control module is closed this speech type music controller.Thereby can realize the comparatively " shut " mode" of intelligence, promote the power consumption that can also reduce this device when the user experiences.
4) in the possibility, the local music processing module can comprise music information recording unit and sequencing unit, and described sequencing unit can sort to the music in the music information recording unit, and will play the highest music of frequency and play.So just convenient for users to use, and improved user's experience effect.
Embodiment
Just as described in the background section, at present user if want enjoy the process of service such as music at automobile more loaded down with trivial details, need realize by the mode of manual control usually.On the one hand, make that easily the user takes sb's mind off sth, be unfavorable for safety; On the other hand, also cause user's experience effect relatively poor.
The invention provides a kind of speech type music controller, make the user can realize the startup of local music application and follow-up operation by the mode of voice.Like this, just liberate user's both hands effectively, reduced the dispersion of user's notice effectively, thereby improved the safety of driving; And the driving that has also promoted the user is effectively experienced.
For above-mentioned purpose of the present invention, feature and advantage can be become apparent more, below in conjunction with accompanying drawing the specific embodiment of the present invention is described in detail.
Set forth a lot of details in the following description so that fully understand the present invention, implement but the present invention can also adopt other to be different from alternate manner described here, so the present invention has not been subjected to the restriction of following public specific embodiment.
Fig. 1 shows the structural representation of a kind of embodiment of speech type music controller of the present invention.As shown in Figure 1, described speech type music controller can comprise: voice input module 10, sound identification module 20, instruction form module 30 and local music processing module 40.
Voice input module 10 is used for receiving speech information.In the present embodiment, described voice input module 10 can be microphone.Certainly, in other embodiments, described voice input module 10 also can be for other install, as long as can realize the collection of voice messaging.
Sound identification module 20 connects described voice input module 10, is used for the voice messaging that receives is identified processing, and obtains phonetic feature information.
Instruction forms module 30, connects described sound identification module 20, obtains corresponding phonetic order information based on the phonetic feature information that receives, and wherein, described phonetic order information comprises function command information or content instruction information.
Local music processing module 40 connects described instruction and forms module 30, when obtaining function command information, starts the application of local music, and carries out corresponding operating when follow-up acquisition content instruction information; Perhaps, when obtaining content instruction information, start the application of local music, and according to content instruction information and executing corresponding operating.
Particularly, the attribute of described function command information is that scene is judged, is used for the application start with certain scene.As a concrete example, in the present embodiment, described function command information can be " opening local music/local music/broadcast local music " etc.Local music processing module 40 is after receiving the above-mentioned functions command information, with the application start of local music.
The attribute of described content instruction information is that object is judged, not only the application start of certain scene can also can be implemented certain and operate particularly after the application start of scene.As a concrete example, in the present embodiment, described content instruction information can for: " play XX song " also can be: " next/change a head ", can also " single broadcast " etc.Particularly, after the application start of local music, local music processing module 40 receives " playing XX (song) " again, for example during the content instruction information of " play chrysanthemum platform ", described local music processing module 40 will be searched for the music information of " chrysanthemum platform " this first song, and it is play searching when existing this song, thereby finish the operation of this time phonetic order.Under the another kind of situation, if the user directly sends instruction: " playing the chrysanthemum platform ", and the application of the local music of this moment does not start as yet, so, local music processing module 40 will be according to the application start of this content instruction information with local music, and then the song of " the chrysanthemum platform " that will search according to this content instruction plays, and finished the operation of a phonetic order so equally.
More than, speech type music controller of the present invention obtains corresponding phonetic order information by identify phonetic feature information from the voice messaging that receives according to the phonetic feature information that identifies, and carries out various operations according to corresponding command information.Replace manually control by phonetic order, can reduce the dispersion of driver's notice effectively, when improving traffic safety, can also promote driving enjoyment; On the other hand, for the handicapped personage of hand, they also can obtain better experience by this speech type music controller.
Fig. 2 shows the synoptic diagram that sound identification module in the speech type music controller of the present invention and instruction form a kind of embodiment of module.With reference to figure 2, in the present embodiment, described sound identification module 20 can comprise: phonetic feature recognition unit 21, phonetic feature storehouse 22 and search unit 23.
Wherein, phonetic feature recognition unit 21 connects voice input module 10, is used for the voice messaging that receives is identified to draw phonetic feature information.
Particularly, 21 pairs of voice messagings that collect of phonetic feature recognition unit carry out filtration treatment, obtain the voice messaging behind the filtering noise; Again the voice messaging behind the filtering noise is carried out frequency analysis, the phonetic feature information that obtains receiving, and can adopt STT (Speech to Test, speech recognition is text) technology, user's voice information is changed into text message.
Phonetic feature storehouse 22 is used for a plurality of phonetic feature information of storage.These phonetic feature information are stored in advance in the phonetic feature storehouse 22, and the phonetic feature information of storage is not changeless in the phonetic feature storehouse 22, and the user can also add more phonetic feature information to described phonetic feature storehouse 22 by modes such as editors.This is well known to those skilled in the art, so do not repeat them here.
Search unit 23, connect phonetic feature storehouse 22, phonetic feature recognition unit 21 and instruction and form module 30, be used for searching out from phonetic feature storehouse 22 the phonetic feature information corresponding with the phonetic feature information that receives, and the phonetic feature information that searches out is sent to instruction forms module 30.
Continuation is with reference to figure 2, and described instruction forms module 30 and can comprise: phonetic order collection 31 and instruction recognition unit 32.
Phonetic order collection 31 is used for a plurality of phonetic order information of storage, and wherein, described phonetic order information comprises function command information and content instruction information, and has corresponding relation between described phonetic order information and the phonetic feature information;
Instruction recognition unit 32, the search unit 23, phonetic order collection 31 and the local music processing module 40 that connect sound identification module 20, be used for identifying the phonetic order information corresponding with the phonetic feature information that receives from phonetic order collection 31, and the phonetic order information that identifies is sent to local music processing module 40.
With reference to figure 3, the speech type music controller can also comprise in the present embodiment: reminding module 50 and response message memory module 60.
Reminding module 50, link order recognition unit 32 is used for pointing out according to the recognition result of instruction recognition unit 32.
Described reminding module 50 can adopt existing TTS (Test to Speech, text-converted is voice) technology to realize corresponding prompting, and this is well known to those skilled in the art, so do not repeat them here.
Response message memory module 60 connects reminding module 50, is used for the storage response message.
Particularly, described recognition result according to instruction recognition unit 32 is pointed out and can be comprised: unidentified during to phonetic order information at instruction recognition unit 32, and the prompting that described reminding module 50 fails to identify.
In addition, described recognition result according to instruction recognition unit 32 is pointed out and can also be comprised: when instruction recognition unit 32 draws phonetic order information, described reminding module 32 searches out the response message corresponding with phonetic order information from response message memory module 60, and points out according to corresponding response message.
As a concrete example, the user says a voice messaging: " broadcast local music ", voice input module 10 receives this voice messaging " broadcast local music " of user, and sends it to the phonetic feature recognition unit 21 in the sound identification module 20.21 pairs of described voice messagings of described phonetic feature recognition unit " broadcast local music " are identified, and in phonetic feature storehouse 22, searching out the text message corresponding with voice messaging " broadcast local music " by search unit 23, text information is sent to instruction recognition unit 32.
Described instruction recognition unit 32 is compared from phonetic order collection 31 according to the text message that receives.If find not exist in the phonetic order collection 31 the phonetic order information corresponding with text information after the comparison, so, reminding module 50 will send the prompting of " failing to identify "; And if through finding to exist in the phonetic order collection 31 the phonetic order information corresponding with text information after the comparison, and local music processing module 40 starts after the application of local music according to this phonetic order information, so, reminding module 50 will be pointed out according to the corresponding response message of storage in the response message memory module 60, for example this response message can be: " OK, local music is opened ".In this case, the user is saying " broadcast local music " afterwards, will receive: the response message of " OK, local music is opened ".
By the corresponding prompting of reminding module 50, can be user-friendly further, and improved user's experience further.
In addition, the speech type music controller can also comprise the trigger module (not shown).Described trigger module starts described speech type music controller based on user's solicited message.In the present embodiment, described trigger module is for triggering button, and the user should trigger after button presses, and just will start the speech type music controller, namely can control the opening or other operation of application of local music by voice.Certainly, trigger module can also have other embodiment, and it is not limited to giving an example of above-mentioned triggering button.
In other embodiments, the speech type music controller can also comprise: timing module and control module.
Described timing module is used for;
Described control module, connect local music processing module 40 and timing module, the duration that control timing module record local music processing module is not carried out phonetic order information, when described duration during greater than threshold time, close the speech type music controller.
Wherein, described threshold time can be the random time that arranges, as: 5 minutes, 10 minutes etc.In this case, the user wants to reuse the speech type music controller, needs by trigger module it to be started again, and after the speech type music controller restarted, the user namely can control the various operations of local music by voice.
By timing module and control module, can be more flexibly and control closing of speech type music controller easily.Thereby when the user fails to send phonetic order in a long time, described speech type music controller will be closed, thereby also can reduce its power consumption.
Fig. 4 shows the structural representation of a kind of embodiment of local music processing module in the speech type music controller of the present invention.With reference to figure 4, described local music processing module 40 can comprise: instruction resolution unit 41, local music storage unit 42, local music functional unit 43, music data detecting unit 44.
Instruction resolution unit 41, link order forms module 30, the phonetic order information that receives is resolved, to identify function command information or content instruction information;
Wherein, content instruction information can comprise song selection command information, collection song command information etc.For example, song selects command information can be " next/change one " etc.; Collection song command information can be " collection song " etc.
Local music storage unit 42 is used for storage local music information.
Music data detecting unit 44, connect local music storage unit 42 and instruction resolution unit 41, when instruction resolution unit 41 identifies content instruction information, detect in the local music storage unit 42 whether have the local music data corresponding with described content instruction information.
Local music functional unit 43, link order resolution unit 41 and music data detecting unit 44, receive the instruction resolution unit 41 identify function command information the time, start the application of local music, and detect execution corresponding operating when having the local music data corresponding with described content instruction information at follow-up content instruction information and the music data detecting unit 44 of identifying; Perhaps, receive the instruction resolution unit 41 identify content instruction information the time, start the application of local music, and detect when having the local music data corresponding with described content instruction information at music data detecting unit 44, according to described content instruction information and executing corresponding operating.
In the present embodiment, local music processing module 40 can also comprise: external memory storage recognition unit 45, voice broadcast unit 46, music information recording unit 47, sequencing unit 48.
Wherein, in the present embodiment, external memory storage recognition unit 45 is used for the identification external memory storage and whether is connected to the speech type music controller; Wherein, after described external memory storage recognition unit 45 identifies external memory storage and is connected to the speech type music controller, 44 pairs of external memory storages of music data detecting unit detect, to determine whether there are corresponding local music data with content instruction information in the external memory storage.
In the present embodiment, the broadcast path of local music not only comprises the music data of storing in the internal storage in the speech type music controller, can also comprise the music data in the external memory storage of external.External memory storage can be arbitrary existing storeies such as USB flash disk, SD card.
The user can download and be stored to external memory storage with the song of oneself liking, USB flash disk for example, the USB flash disk that will store music data then is connected to speech type music controller of the present invention, thereby just can the song in the USB flash disk be play by voice, and can carry out other certain operations, for example carry out " single broadcast " etc.This application mode is well known to those skilled in the art, so do not repeat them here.
Voice broadcast unit 46, connect described music data detecting unit 44 and external memory storage recognition unit 45, do not detect the local music data corresponding with content instruction information at music data detecting unit 44, when perhaps externally memory identification unit 45 is not connected to the speech type music controller, the prompting of failing to identify.
The user can carry out other instructions according to the prompting of voice broadcast unit 46, thereby can improve user's experience further.For example, the user just can know clearly the connection existing problems of external memory storage hearing that voice broadcast unit 46 carries out the prompting of " external memory storage fails to identify " very much, therefore just can be at this problem to operations such as external memory storage reconnect.
Described music information recording unit 47 connects local music functional unit 43, is used for the music information of playing is carried out record; Local music functional unit 43 is receiving after the function command information that identifies of instruction resolution unit 41 starts the application of local music, and before receiving the follow-up content instruction information that identifies, the music of the last broadcast of record in the music information recording unit 47 is play.Thereby can further improve user's experience.
Certainly, when instruction resolution unit 41 parsed the other guide command information that the user sends, local music functional unit 43 just can carry out other operation according to the other guide command information that the user sends out.For example, the user has specified and will play a song, and current in progress song (being the song of the last broadcast of record in the music information recording unit 47) and the song of user's appointment are not inconsistent, so, music data detecting unit 44 just will be in local music storage unit 42 or is externally detected in the storer the not music data corresponding with the song of user's appointment arranged, if when existing this head to sing, local music functional unit 43 just will convert current song to the song of user's appointment according to this content instruction information of user; If do not have this head song, will for example be carried out the prompting of " not detecting corresponding music " by voice broadcast unit 46 so.
Certainly, in other embodiments, when music data detecting unit 44 does not detect the music data corresponding with the song of user's appointment, can also from network, search for, and the music data that searches is downloaded in local music storage unit 42 or the external memory storage, like this, just can play from this locality to the song of user's appointment.
More than the embodiment of two kinds of local musics only for illustrating, those skilled in the art can also carry out other distortion, it should not limit protection scope of the present invention.
In order to improve user's experience better, described local music processing module 40 can also comprise sequencing unit 48.Described sequencing unit 48 connects music information recording unit 47, is used for sorting according to playing the music of frequency to music information recording unit 47 at least.For example, sequencing unit 48 sorts the music in the music information recording unit 47 from high to low according to playing frequency.
Further, local music functional unit 43 is receiving after the function command information that identifies of instruction resolution unit 41 starts the application of local music, and before receiving the follow-up content instruction information that identifies, play playing the highest music of frequency in the music information recording unit 47.Thereby, further improved user's experience.
The course of work to speech type music controller of the present invention elaborates below.
1) user imports voice messagings by voice input module 10, as: " broadcast music ";
2) sound identification module 20 is identified processing to " broadcast music ", obtains corresponding phonetic feature information, and the phonetic feature information of correspondence is sent to instruction formation module 30;
3) the phonetic feature information of instructing formation module 30 to identify based on sound identification module 20 forms corresponding phonetic order information, in this concrete example, the phonetic order information that instruction forms module 30 formation is function command information, for example can be: " broadcast music ";
4) local music processing module 40 forms the function command information that module 30 forms according to instruction: " broadcast music " is with the application start of local music.
After the application start of local music, and local music processing module 40 do not receive before the follow-up content instruction information, a song of playing recently can be play, and can play playing the highest song of frequency yet.
So far, just finished the startup of the application of local music.
5) user continues by voice input module 10 input voice messagings, as: " playing the chrysanthemum platform ";
6) 20 couples of users of sound identification module " play chrysanthemum platform " of assigning identify, and draw its phonetic feature information, and described phonetic feature information is sent to instruction forms module 30;
7) the phonetic feature information of instructing formation module 30 to identify based on sound identification module 20 forms corresponding phonetic order information, and at this moment, the phonetic order information that instruction forms module 30 formation is content instruction information, for example can be: " broadcast chrysanthemum platform ";
8) local music processing module 40 is searched for the music data that whether has " chrysanthemum platform " according to this content instruction information from local music storage unit 42 or external memory storage, and is searching " chrysanthemum platform " afterwards with its broadcast.
So far, the user has just finished the broadcast of a music.
Afterwards, the user can also repeat 5)~8) step, assign other content instruction information, for example " single broadcast ", " loop play ", " single circulation ", " random rotation ", " time-out ", " last head/next " etc.
Certainly, more than only for example understand the user by assigning the process that function command information starts the application of local music, in actual applications, the user can also directly assign content instruction information, for example: " playing the chrysanthemum platform "; " playing the chrysanthemum platform " that 20 couples of users of sound identification module assign identified, and draws its phonetic feature information, and described phonetic feature information is sent to instruction formation module 30; The phonetic feature information that instruction formation module 30 identifies based on sound identification module 20 forms corresponding phonetic order information, and at this moment, the phonetic order information that instruction forms module 30 formation is content instruction information, for example can be: " playing the chrysanthemum platform "; Application with local music starts local music processing module 40 according to this content instruction information, and content-based command information is searched for the music data that whether has " chrysanthemum platform " from local music storage unit 42 or external memory storage, and is searching " chrysanthemum platform " afterwards with its broadcast.In this mode, the user can assign other content instruction information equally, to realize other operation, does not repeat them here.
Though the present invention discloses as above with preferred embodiment, the present invention is defined in this.Any those skilled in the art without departing from the spirit and scope of the present invention, all can do various changes and modification, so protection scope of the present invention should be as the criterion with claim institute restricted portion.