CN103383844B - Phoneme synthesizing method and system - Google Patents
Phoneme synthesizing method and system Download PDFInfo
- Publication number
- CN103383844B CN103383844B CN201210138028.2A CN201210138028A CN103383844B CN 103383844 B CN103383844 B CN 103383844B CN 201210138028 A CN201210138028 A CN 201210138028A CN 103383844 B CN103383844 B CN 103383844B
- Authority
- CN
- China
- Prior art keywords
- speech synthesis
- task
- casting
- processed
- 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.)
- Active
Links
Abstract
The present invention relates to a kind of phoneme synthesizing method and systems, which comprises default speech synthesis task, external speech synthesis application call and submit speech synthesis task；Various speech synthesis tasks are deployed and generate the speech synthesis task list to be processed by sequence；It is selected from speech synthesis task list to be processed and comes most preceding speech synthesis task to be processed progress current speech synthesis and casting；It repeats the above steps up to no speech synthesis task is submitted and speech synthesis task list to be processed is sky, various speech synthesis demands in the application of different external speech syntheses can be transferred to an independent speech synthesis application processing by the present invention, speech synthesis is normalized, external speech synthesis applies the function of using speech synthesis if necessary, the speech-sound synthesizing function that speech synthesis can be called to apply by way of far call, resource redundancy and waste are reduced, also simplifies the exploitation complexity of external speech synthesis application to a certain extent.
Description
Technical field
The present invention relates to a kind of phoneme synthesizing method and systems.
Background technique
Along with the rapid development of computer technology, speech synthesis system has also obtained huge progress, present synthesis
Effect can meet the needs of daily in intelligibility, naturalness, have already appeared many as reading news, reading novel, weather are broadcast
The products relevant to speech synthesis such as report, short message are broadcasted, e-book is read aloud, for each application, as long as being related to voice conjunction
At, necessarily there is a module to carry out special disposal speech synthesis, this will lead to the severely redundant of resource and waste, if there is 10
The application of speech synthesis, then requiring 10 duplicate voice synthetic modules.
Present most of speech synthesis related applications (also referred to as external speech synthesis application) are nothing more than two kinds of application scenarios:
Under the first application scenarios, each voice related application has the non-serviceable voice of other speech synthesis related application to close
At module, more parts of voice synthetic modules are then needed for a variety of different speech synthesis related applications, will cause storage money in this way
Source and exploitative serious waste；Under second of application scenarios, each speech synthesis related application can be connect by network
The unified interface that mouth calls others to issue, but this application then requires to necessarily require on energy when using speech-sound synthesizing function
Net, and need downloading synthesis voice that can generate many data traffics.
Summary of the invention
The purpose of the present invention is to provide a kind of phoneme synthesizing method and systems, can answer different external speech syntheses
Various speech synthesis demands in transfer to an independent speech synthesis application processing, i.e., normalize speech synthesis, external
Speech synthesis applies the function of using speech synthesis if necessary, speech synthesis can be called to answer by way of far call
Speech-sound synthesizing function can greatly reduce resource redundancy and waste in this way, also simplify external language to a certain extent
The exploitation complexity of sound synthesis application.
To solve the above problems, the present invention provides a kind of phoneme synthesizing method, comprising:
Step 1: default speech synthesis task；
Step 2: external speech synthesis application calls and submits the speech synthesis task；
The speech synthesis task to be processed that step 3: deploying various speech synthesis tasks and generates by sequence arranges
Table；And
Step 4: it is selected from the speech synthesis task list to be processed and comes most preceding speech synthesis task to be processed
Carry out current speech synthesis and casting.
It further, in the above-mentioned methods, further include repeating the above steps one to four up to no language after the step 4
Sound synthesizes task submission and the speech synthesis task list to be processed is sky.
Further, in the above-mentioned methods, selected from the speech synthesis task list to be processed come it is most preceding to
Further include monitoring telephone situation while handling speech synthesis task progress speech synthesis, when listening to phone, stops current
Speech synthesis and casting restart current speech synthesis and casting when listening to telephone finished.
Further, in the above-mentioned methods, selected from the speech synthesis task list to be processed come it is most preceding to
It further include monitoring telephone situation while handling speech synthesis task progress speech synthesis, when listening to phone, pause is current
Speech synthesis and casting, when listening to telephone finished, current speech synthesis and casting since the place of pause.
Further, in the above-mentioned methods, stop current speech synthesis and casting or the synthesis of pause current speech and casting
The step of after, further include transmission task processing status (start to broadcast, terminate casting) to the external speech synthesis apply with
Just its logic state for modifying oneself.
Further, in the above-mentioned methods, restart current speech synthesis and casting or work as since the place of pause
It further include that transmission task processing status is applied to the external speech synthesis so as to it after the step of preceding speech synthesis and casting
Modify the logic state of oneself.
Further, in the above-mentioned methods, selected from the speech synthesis task list to be processed come it is most preceding to
Handle speech synthesis task carry out speech synthesis while, send task processing status to the external speech synthesis apply so as to
Its logic state for modifying oneself.
Further, in the above-mentioned methods, the speech synthesis task includes the permission activation of external speech synthesis application
Task submits casting task, stops casting task, pause casting task and delete its all casting task.
Further, in the above-mentioned methods, the current speech is carried out using the parameterised speech synthetic method based on HMM
Synthesis and casting.
Further, in the above-mentioned methods, using the phoneme synthesizing method based on formant or based on the wave of Big-corpus
Shape concatenative speech synthesis method carries out the current speech synthesis.
Further, in the above-mentioned methods, using first in first out, the queuing mechanism of last-in, last-out is to the voice to be processed
Synthesis task list is ranked up.
Further, in the above-mentioned methods, using important preceding, secondary posterior queuing mechanism is to the voice to be processed
Synthesis task list is ranked up.
Further, in the above-mentioned methods, the current speech is synthesized and adjusted in broadcasting including intonation, word speed adjusts,
Made tone color adjustment with the method for the change of voice, reverberation effect is added with the method for echo or improved sound effect with the method for balanced device.
Another side according to the present invention provides a kind of mobile terminal, carries out speech synthesis using above-mentioned phoneme synthesizing method.
Further, in above-mentioned mobile terminal, the speech synthesis application run on including symbian, android,
On the operating system system of ios, linux or mtk.
Another side according to the present invention provides a kind of speech synthesis system, comprising:
The voice is called and submitted to interface module for presetting speech synthesis task, and for the application of external speech synthesis
Synthesis task；
Task processing module, for being deployed to various speech synthesis tasks and generating the voice to be processed by sequence
Synthesize task list；And
Compositing Engine comes most preceding voice to be processed conjunction for selecting from the speech synthesis task list to be processed
Current speech synthesis and casting are carried out at task and broadcast situation to the external speech synthesis application report.
Further, in above system, the speech synthesis task includes the permission activation of external speech synthesis application
Task submits casting task, stops casting task, pause casting task and delete its all casting task.
Further, in above system, further include monitoring module, be used for monitoring telephone situation, when listening to phone,
It notifies the Compositing Engine to stop current speech synthesis and casting, when listening to telephone finished, notifies the Compositing Engine weight
It is new to start current speech synthesis and casting.
Further, in above system, the monitoring module is also used to monitoring telephone situation, when listening to phone,
Notify Compositing Engine pause current speech synthesis and casting, when listening to telephone finished, notify the Compositing Engine from
The place of pause starts current speech synthesis and casting.
Further, it in above system, monitors module and is also used to send task processing status to the external voice conjunction
At application so that it modifies the logic state of oneself.
Further, in above system, the Compositing Engine is also used to stop current speech synthesis and casting, opens again
Beginning current speech synthesis and casting, pause current speech synthesis and casting or since pause place start current speech synthesize and broadcast
Report.
Another side according to the present invention provides a kind of mobile terminal, including above-mentioned speech synthesis system carries out speech synthesis.
Compared with prior art, the present invention is called and is submitted by presetting speech synthesis task, external speech synthesis application
Then the speech synthesis task deploys various speech synthesis tasks and generates the speech synthesis to be processed by sequence
Task list, and selected from the speech synthesis task list to be processed and come most preceding speech synthesis task to be processed progress
Current speech synthesis and casting, and repeat the above steps up to no speech synthesis task and the speech synthesis task to be processed
List is empty, an independent voice can be transferred to close the various speech synthesis demands in the application of different external speech syntheses
It handles, i.e., normalizes speech synthesis at application, external speech synthesis is applied uses the function of speech synthesis if necessary, can be with
The speech-sound synthesizing function for calling speech synthesis to apply by way of far call, can greatly reduce resource redundancy in this way
And waste, the exploitation complexity of external speech synthesis application is also simplified to a certain extent.
In addition, user does not need to surf the Internet by speech synthesis system of the invention in running of mobile terminal, it will not generate and appoint
What data traffic is conducive to push advancing for speech synthesis technique.
In addition, by presetting speech synthesis task, so that the application of external speech synthesis is called and submits the speech synthesis
Speech synthesis application integrating can be applied at for the unified of different mobile terminal equipment, be different from traditional voice and close by task
At application, the speech synthesis application that mobile terminal device only needs the present invention to be mounted unified, if external speech synthesis is applied
It needs using speech-sound synthesizing function, then can have by calling unified speech synthesis task that speech-sound synthesizing function can be realized
Effect reduces storage and exploits natural resources.
Detailed description of the invention
Fig. 1 is the flow chart of the phoneme synthesizing method of the embodiment of the present invention one；
Fig. 2 is the flow chart of the phoneme synthesizing method of the embodiment of the present invention two；
Fig. 3 is the external phoneme synthesizing method schematic diagram of the embodiment of the present invention two；
Fig. 4 is the functional block diagram of the speech synthesis system of the embodiment of the present invention four；
Fig. 5 is the process flow diagram of the speech synthesis system of the embodiment of the present invention four；
Fig. 6 is the functional block diagram of the speech synthesis system of the embodiment of the present invention five；
Fig. 7 is the process flow diagram of the speech synthesis system of the embodiment of the present invention five.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
Embodiment one
As shown in Figure 1, the present invention provides a kind of phoneme synthesizing method, comprising:
Step S11 presets speech synthesis task；Wherein, the speech synthesis task includes what external speech synthesis was applied
Permission activates task, submits casting task, stops casting task, pause casting task and delete all casting tasks；
Step S12, the speech synthesis task is called and is submitted in external speech synthesis application, specifically, by presetting language
Sound synthesizes task, can be by speech synthesis using whole so that the speech synthesis task is called and submitted in the application of external speech synthesis
Synthesis is different from traditional speech synthesis application, terminal device only needs to be mounted for the unified application of different terminal equipment
The unified speech synthesis application of the present invention, external speech synthesis are applied if necessary to use speech-sound synthesizing function, then can pass through tune
Speech-sound synthesizing function can be realized with preset speech synthesis task, effectively reduce storage and exploit natural resources；
Step S13 deploys various speech synthesis tasks and generates the speech synthesis task to be processed by sequence
List, to guarantee that speech synthesis on the terminal device orderly carries out；The queuing mechanism pair of first in first out, last-in, last-out can be used
The speech synthesis task list to be processed is ranked up, alternatively, using it is important in preceding, secondary posterior queuing mechanism to described
Speech synthesis task list to be processed is ranked up；
Step S14 is selected from the speech synthesis task list to be processed and is come most preceding speech synthesis to be processed times
Business carries out current speech synthesis and casting；The parameterised speech synthetic method based on HMM can be used and carry out the current speech conjunction
At and casting, the amount of storage of this method and the requirement of operand be not high, and synthesize voice intelligibility and naturalness all
It is very high, the speech synthesis application on various mobile terminals is complied fully with, due to the parameterised speech synthesis application based on HMM
Through widespread, so specific introduction is not done here, in addition, the phoneme synthesizing method based on formant can also be used or be based on big
The waveform concatenation phoneme synthesizing method progress current speech synthesis of corpus, but the Speech Synthesis Algorithm based on formant
Effect can be lacking in intelligibility and naturalness, be only applicable to speech synthesis situation of less demanding, be based on Big-corpus
Waveform concatenation Speech Synthesis Algorithm calculation amount and amount of storage require can it is relatively high, can be used in the higher terminal of processing capacity set
It is standby upper；It include intonation adjustment, word speed tune in the current speech synthesis and casting to keep speech synthesis effect more abundant
It is whole, make tone color adjustment with the method for the change of voice, reverberation effect added with the method for echo or improves sound with the method for balanced device and is imitated
Fruit；While executing this step, also transmittable task processing status such as starts to broadcast, and terminates casting etc. and closes to the external voice
At application so that it modifies the logic state of oneself；
Step S15, judge whether no speech synthesis task submit and the speech synthesis task list to be processed whether be
Sky, if so, S16 is thened follow the steps, if it is not, then repeating step S11 to step S15；
Step S16 terminates to exit.
Various speech synthesis demands in the application of different external speech syntheses can be transferred to an independence by the present embodiment
Speech synthesis application processing, i.e., speech synthesis is normalized, external speech synthesis using using speech synthesis if necessary
Function, the speech-sound synthesizing function that speech synthesis can be called to apply by way of far call, can greatly subtract in this way
Few resource redundancy and waste also simplify the exploitation complexity of external speech synthesis application to a certain extent.
Embodiment two
The difference between this embodiment and the first embodiment lies in being selected from the speech synthesis task list to be processed executing
It comes the step of most preceding speech synthesis task to be processed carries out current speech synthesis and casting simultaneously, increases monitoring telephone feelings
Condition and the step of make corresponding specially treated, so that phoneme synthesizing method of the invention is suitable for the shifting that the needs such as mobile phone receive calls
Dynamic terminal device, telephony feature reaches normal use during guaranteeing speech synthesis.
As shown in Fig. 2, the present invention provides another phoneme synthesizing method, comprising:
Step S21 presets speech synthesis task, specifically, the speech synthesis task includes external speech synthesis application
Permission activation task, submit casting task, stop casting task, pause casting task and delete all casting tasks；；
Step S22, external speech synthesis application call and submit the speech synthesis task；
Step S23 deploys various speech synthesis tasks and generates the speech synthesis task to be processed by sequence
List, to guarantee that speech synthesis on the terminal device orderly carries out, optionally, using first in first out, the queuing of last-in, last-out
Mechanism is ranked up the speech synthesis task list to be processed, or using important in preceding, secondary posterior queuing mechanism pair
The speech synthesis task list to be processed is ranked up；
Step S24 is selected from the speech synthesis task list to be processed and is come most preceding speech synthesis to be processed times
Business carries out current speech synthesis and casting, and monitoring telephone situation, when listening to phone, stops current speech synthesis and broadcasts
Report restarts current speech synthesis and casting when listening to telephone finished；In addition, when listening to phone, it can also be temporary
Ready preceding speech synthesis and casting, when listening to telephone finished, current speech synthesis and casting since the place of pause；
Step S25 sends task processing status and applies to the external speech synthesis so that it modifies the logic shape of oneself
State, specifically, the external speech synthesis apply according to the various task processing statuses during speech synthesis such as start casting,
Stop casting, pause is broadcasted, restart current speech casting, the states such as current speech casting are realized since the place of pause
The logic of oneself, external speech synthesis applies the casting state of oneself as described in modification；
Step S26, judge whether no speech synthesis task submit or the speech synthesis task list to be processed whether be
Sky, if it is not, then repeating step S22 to step S26, is not required to if so, thening follow the steps S27 if presetting speech synthesis task here
It resets, then can execute directly since step S22 to step S26, omit and re-execute the steps S21；
Step S27 terminates to exit.
As shown in figure 3, using the present invention produce a normalized speech synthesis platform, the platform can be realized listen it is short
The speech synthesis demand of various external speech syntheses applications such as believe, answer a call, listen novel, listen novel, listen news, listen weather.
Various speech synthesis demands in the application of different external speech syntheses can be transferred to an independence by the present embodiment
Speech synthesis application processing, i.e., speech synthesis is normalized, external speech synthesis using using speech synthesis if necessary
Function, the speech-sound synthesizing function that speech synthesis can be called to apply by way of far call, can greatly subtract in this way
Few resource redundancy and waste also simplify the exploitation complexity of external speech synthesis application, in addition, this implementation to a certain extent
Telephony feature reaches normal use during example can also guarantee speech synthesis.
Embodiment three
The present invention also provides a kind of mobile terminals, use the phoneme synthesizing method as described in embodiment one or embodiment two
Speech synthesis is carried out, optionally, the speech synthesis application is run on including symbian, android, ios, linux or mtk
Operating system system on.
The present embodiment can be set by speech synthesis application integrating at an individual application product for different mobile terminals
Standby, mobile terminal system includes but is not limited to symbian, android, ios, and linux, mtk etc. pacify on these terminal devices
After having filled unified speech synthesis application, the external speech synthesis in these equipment, which is applied, itself then no longer needs respective independence
Speech synthesis application, calling directly the unified speech synthesis application of the present invention can be realized speech-sound synthesizing function, finally, be formed
One is directed to the unified speech synthesis platform of terminal device.
Example IV
As shown in figure 4, the present invention also provides speech synthesis system 1, in normalized speech synthesis system most importantly
Interface module 11, task processing module 12 and Compositing Engine 13.
Institute's predicate is called and submitted to interface module 11 using 14 for presetting speech synthesis task, and for external speech synthesis
Sound synthesizes task, and optionally, the speech synthesis task includes the permission activation task of external speech synthesis application, submits casting
Task stops casting task, pause casting task and deletes all casting tasks.Specifically, interface module 11 is mainly responsible for outside
Connect speech synthesis application control input, for external speech synthesis application call, such as call submit casting task with
Start casting, call stopping casting task to terminate casting etc..It can be whole by speech synthesis system 1 by setting interface module 11
Synthesis is directed to the unified application system of different terminal equipment, is different from traditional speech synthesis system, terminal device only needs to pacify
The unified speech synthesis system of the present invention of dress, external speech synthesis are applied if necessary to use speech-sound synthesizing function, then can be led to
It crosses and calls unified interface module 11 that speech-sound synthesizing function can be realized, effectively reduce storage and exploit natural resources.
Wherein, permission activation task (activate), to activate the speech synthesis related application to obtain Compositing Engine
Processing authority；It submits casting task (speak), to submit speech synthesis task；Stop casting task (stop), to stop
The casting task for the external speech synthesis application currently broadcasted, the external speech synthesis application cannot stop other casting and appoint
Business；All casting tasks (stopAll) are deleted, all tasks submitted to delete current external speech synthesis application.It is external
The calling of speech synthesis task can be realized using the 14 above interface modules 11 of calling for speech synthesis.
Task processing module 12 is for deploying various speech synthesis tasks and generating the language to be processed by sequence
Sound synthesizes task list, and task processing module 12 is mainly to cope with the treatment mechanism of various speech synthesis tasks, guarantees in terminal
Speech synthesis in equipment is orderly, because normalized speech synthesis system needs to handle different external connection, speech synthesis application was sent out
The speech synthesis task come, so task processing module 12 will guarantee that the order of synthesis task, task processing module 12 can adopt
Come front with arriving first for task, arriving afterwards for task comes subsequent queuing mechanism, for Compositing Engine 13 handle in sequence to
Handle speech synthesis task.
Compositing Engine 13 comes most preceding voice to be processed for selecting from the speech synthesis task list to be processed
Synthesis task carries out current speech synthesis and casting and broadcasts situation to the external speech synthesis application report.Compositing Engine 13
It is mainly responsible for and speech synthesis is carried out to the text of input and is broadcasted, when synthesis task starts to broadcast and terminate casting, synthesis is drawn
Holding up 13 can all notify external speech synthesis to apply so that respective handling is done by task call side.The Compositing Engine 13 is also used to send
Task processing status such as starts casting, terminates casting to the external speech synthesis using so that it modifies the logic shape of oneself
State.
As shown in fig. 5, it is assumed that current, there are three speech synthesis tasks to be processed to upload to normalization speech synthesis platform, puts down
Platform is given according to task uplink time works as first three speech synthesis task ranking to be processed, assumes external speech synthesis application in Fig. 5
Two speech synthesis task to be processed ranks the first, to be processed speech synthesis task of the Compositing Engine 13 from task processing module 12
Current task of first speech synthesis task to be processed as Compositing Engine 13 is taken out in list, when starting to process, is closed
Message that one starts casting can be sent out to external speech synthesis using two at engine 12, external speech synthesis can be with using two at this time
The logic of oneself, such as modification casting state etc. are realized with this message, then starts the content of casting task, when casting is tied
After beam, the message ended processing can equally issue the corresponding external speech synthesis application of current task, then Compositing Engine 13
It goes to obtain second speech synthesis task to be processed in speech synthesis task list to be processed again, continues same processing.
This implementation can by different external speech syntheses apply in various speech synthesis demands transfer to one it is independent
Speech synthesis system processing, i.e., normalize speech synthesis, and external speech synthesis applies the function for using speech synthesis if necessary
Can, the speech-sound synthesizing function of speech synthesis system can be called by way of far call, can greatly be reduced in this way
Resource redundancy and waste also simplify the exploitation complexity of external speech synthesis system to a certain extent.
Embodiment five
As shown in fig. 6, the present invention also provides another speech synthesis system 2, the difference of the present embodiment and example IV exists
Module 24 is monitored in increasing, so that speech synthesis system of the invention is suitable for the mobile terminal that the needs such as mobile phone receive calls
Equipment, telephony feature reaches normal use during guaranteeing speech synthesis.
Institute's predicate is called and submitted to interface module 21 using 25 for presetting speech synthesis task, and for external speech synthesis
Sound synthesizes task, and optionally, the speech synthesis task includes the permission activation task of external speech synthesis application, submits casting
Task stops casting task, pause casting task and deletes all casting tasks.
Task processing module 22 is for deploying various speech synthesis tasks and generating the language to be processed by sequence
Sound synthesizes task list.Task processing module 22 is mainly to cope with the treatment mechanism of various synthesis tasks, is guaranteed in terminal device
On speech synthesis it is orderly because normalized speech synthesis system needs to handle what different external connection speech synthesis application was sent
Synthesis task, so this module will guarantee that the task row arrived first can be used in the order of synthesis task, task processing module 22
In front, arriving afterwards for task comes subsequent queuing mechanism, handles speech synthesis to be processed in sequence for Compositing Engine 23 and appoints
Business, and specially treated is also needed for mobile phone, phone period needs to suspend other all speech synthesis tasks to guarantee phone
It can normal use.
Compositing Engine 23 comes most preceding voice to be processed for selecting from the speech synthesis task list to be processed
Synthesis task carries out current speech synthesis and casting and broadcasts situation to the external speech synthesis application report.In order to it is described
It monitors module 24 to cooperate, the Compositing Engine 23 is also used to stop current speech synthesis and casting, restarts current speech conjunction
At with casting, pause current speech synthesis and casting or since pause place start current speech synthesis and broadcast when.The conjunction
It is also used to send task processing status at engine 23 to apply to the external speech synthesis so that it modifies the logic state of oneself.
It monitors module 24 and is used for monitoring telephone situation, when listening to phone, the Compositing Engine is notified to stop current language
Sound synthesis and casting notify the Compositing Engine to restart current speech synthesis and casting when listening to telephone finished.Separately
Outside, the monitoring module 24 can also notify the Compositing Engine pause current speech synthesis and casting when listening to phone, when
When listening to telephone finished, the Compositing Engine current speech synthesis and casting since the place of pause are notified.In mobile phone etc.
On mobile terminal, then normalized speech synthesis system needs whether a telephone monitoring module 24 has phone at this time to monitor,
If there is phone, then interrupting current synthesis task, and a signal being interrupted by phone call is sent to the outer of current task
Speech synthesis is connect using 25, takes next speech synthesis to be processed to appoint after telephone finished, then in synthesis semantic task list
Business is handled.
As shown in fig. 7, increasing a telephone monitoring device in figure as module 24 is monitored, when telephone monitoring device has listened to electricity
It, can be by Compositing Engine 23 to interrupt speech synthesis and casting when words.That is, here when listening to phone or remove electricity
When, then all speech synthesis tasks of Compositing Engine 23 will block, casting can be also stopped, after telephone finished, task
It will be again started up, 23 engine of Compositing Engine handles remaining speech synthesis task to be processed in sequence, and normalized voice closes
It needs easy-to-use stopping to broadcast mode at platform to allow users to easily stop casting.
In order to keep speech synthesis platform effect more abundant, one can be done on the basis of speech synthesis engine 23 on basis
A little extensions, such as the adjustment about intonation and word speed, the adjustment of tone color is made of the method for the change of voice, is added with the method for echo mixed
Effect is rung, improves sound effect with the method for balanced device, extension includes but is not limited to content listed above.
Various speech synthesis demands in the application of different external speech syntheses not only can be transferred to one by the present embodiment
Independent speech synthesis system processing, i.e., normalize speech synthesis, and external speech synthesis is closed using voice is used if necessary
At function, the speech-sound synthesizing function of speech synthesis system can be called by way of far call, in this way can be significantly
Reduction resource redundancy and waste, also simplify the exploitation complexity of other external speech synthesis systems to a certain extent, also
Telephony feature reaches normal use during can guaranteeing speech synthesis.
Embodiment six
The present invention also provides a kind of mobile terminal, including the speech synthesis system as described in example IV or embodiment five into
Row speech synthesis.
Speech synthesis system can be integrated into an individual application product by the present embodiment, be set for different mobile terminals
It is standby, under identical speech synthesis engine, it is packaged into the speech synthesis application that may operate under this system, mobile terminal system
Including but not limited to symbian, android, ios, linux, mtk etc. are mounted with unified voice on these terminal devices
After synthesis system, the external speech synthesis application in these equipment does not need speech synthesis processing module independent then,
The interface i.e. module for calling directly unified speech synthesis system can realize speech-sound synthesizing function, ultimately form one for terminal
The unified speech synthesis platform of equipment can not only effectively reduce storage and exploit natural resources, speech synthesis engine can also be made to be
In local runtime, user's online is not needed, any data traffic will not be generated.
The present invention calls by presetting speech synthesis task, external speech synthesis application and the speech synthesis is submitted to appoint
Then the speech synthesis task list to be processed by sequence is deployed and generated to various speech synthesis tasks by business, and from
It is selected in the speech synthesis task list to be processed and comes most preceding speech synthesis task to be processed progress current speech synthesis
And casting, and repeat the above steps up to no speech synthesis task and the speech synthesis task list to be processed is sky, it can
The various speech synthesis demands in different external speech synthesis applications are transferred to an independent speech synthesis application processing,
Speech synthesis is normalized, external speech synthesis applies the function of using speech synthesis if necessary, then can pass through
The mode of far call can greatly reduce resource redundancy and wave come the speech-sound synthesizing function for calling speech synthesis to apply in this way
Take, also simplifies the exploitation complexity of other external speech synthesis applications to a certain extent.
In addition, will not be produced by the way that by speech synthesis system of the invention, in running of mobile terminal, user does not need to surf the Internet
Raw any data traffic is conducive to push advancing for speech synthesis technique.
In addition, by presetting speech synthesis task, so that the application of external speech synthesis is called and submits the speech synthesis
Speech synthesis system can be integrated into the unified application for different mobile terminal equipment, be different from traditional voice and close by task
At application, the speech synthesis application that mobile terminal device only needs the present invention to be mounted unified, if external speech synthesis is applied
It needs to use speech-sound synthesizing function, then can have by calling the unified speech synthesis task that connects that speech-sound synthesizing function can be realized
Effect reduces storage and exploits natural resources.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment
For, due to corresponding to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part illustration
?.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
Obviously, those skilled in the art can carry out various modification and variations without departing from spirit of the invention to invention
And range.If in this way, these modifications and changes of the present invention belong to the claims in the present invention and its equivalent technologies range it
Interior, then the invention is also intended to include including these modification and variations.
Claims (18)
1. a kind of phoneme synthesizing method characterized by comprising
Step 1: default speech synthesis task；
Step 2: external speech synthesis application calls and submits the speech synthesis task；
Step 3: deploying various speech synthesis tasks, using first in first out, last-in, last-out queuing mechanism to described each
Kind speech synthesis task is ranked up, and generates the speech synthesis task list to be processed by sequence；And
Step 4: it is selected from the speech synthesis task list to be processed and comes most preceding speech synthesis task to be processed, adopted
With the phoneme synthesizing method of parameterised speech synthetic method or formant based on HMM or based on the waveform of Big-corpus
Concatenative speech synthesis method carries out current speech synthesis and casting；
Step 5: one to four is repeated the above steps up to no speech synthesis task is submitted and the speech synthesis task column to be processed
Table is sky.
2. phoneme synthesizing method as described in claim 1, which is characterized in that from the speech synthesis task list to be processed
It selects while come most preceding speech synthesis task to be processed and carry out speech synthesis, further includes monitoring telephone situation, work as monitoring
When to phone, stop current speech synthesis and casting, when listening to telephone finished, restarts current speech synthesis and broadcast
Report.
3. phoneme synthesizing method as described in claim 1, which is characterized in that from the speech synthesis task list to be processed
It selects while come most preceding speech synthesis task to be processed and carry out speech synthesis, further includes monitoring telephone situation, work as monitoring
When to phone, the synthesis of pause current speech and casting start current speech conjunction since the place of pause when listening to telephone finished
At and casting.
4. phoneme synthesizing method as claimed in claim 2 or claim 3, which is characterized in that stop current speech synthesis and casting or temporary
After the step of ready preceding speech synthesis and casting, further include transmission task processing status to the external speech synthesis apply with
Just its logic state for modifying oneself.
5. phoneme synthesizing method as claimed in claim 2 or claim 3, which is characterized in that restart current speech synthesis and casting
Or after the step of place of pause starts current speech synthesis and casting, further include transmission task processing status to it is described outside
Speech synthesis is connect to apply so that it modifies the logic state of oneself.
6. phoneme synthesizing method as described in claim 1, which is characterized in that from the speech synthesis task list to be processed
It selects while come most preceding speech synthesis task to be processed and carry out speech synthesis, sends task processing status to described external
Speech synthesis is applied so that it modifies the logic state of oneself.
7. phoneme synthesizing method as described in claim 1, which is characterized in that the speech synthesis task includes that external voice closes
At the permission activation task of application, casting task is submitted, casting task, pause casting task are stopped and deletes its all casting and is appointed
Business.
8. phoneme synthesizing method as described in claim 1, which is characterized in that using important in preceding, secondary posterior queue machine
System is ranked up the speech synthesis task list to be processed.
9. phoneme synthesizing method as described in claim 1, which is characterized in that include language in the current speech synthesis and casting
Tune is whole, word speed adjustment, with the method for the change of voice make tone color adjustment, reverberation effect is added with the method for echo or with the side of balanced device
Method improves sound effect.
10. a kind of mobile terminal, which is characterized in that carried out using phoneme synthesizing method as described in any one of claim 1 to 9
Speech synthesis.
11. mobile terminal as claimed in claim 10, which is characterized in that the speech synthesis application run on including
On the operating system system of symbian, android, ios, linux or mtk.
12. a kind of speech synthesis system characterized by comprising
The speech synthesis is called and submitted to interface module for presetting speech synthesis task, and for the application of external speech synthesis
Task；
Task processing module, for being deployed to various speech synthesis tasks, using the queue machine of first in first out, last-in, last-out
System is ranked up the various speech synthesis tasks, and generates the speech synthesis task list to be processed by sequence；And
Compositing Engine comes most preceding speech synthesis to be processed times for selecting from the speech synthesis task list to be processed
Business carries out current speech synthesis and casting and broadcasts situation to the external speech synthesis application report.
13. speech synthesis system as claimed in claim 12, which is characterized in that the speech synthesis task includes external voice
The permission activation task of synthesis application submits casting task, stops casting task, pause casting task and delete its all casting
Task.
14. speech synthesis system as claimed in claim 12, which is characterized in that further include monitoring module, be used for monitoring telephone
Situation notifies the Compositing Engine to stop current speech synthesis and casting when listening to phone, when listening to telephone finished
When, notify the Compositing Engine to restart current speech synthesis and casting.
15. speech synthesis system as claimed in claim 14, which is characterized in that the monitoring module is also used to monitoring telephone
Situation notifies Compositing Engine pause current speech synthesis and casting when listening to phone, when listening to telephone finished
When, notify the Compositing Engine current speech synthesis and casting since the place of pause.
16. the speech synthesis system as described in claims 14 or 15, which is characterized in that the Compositing Engine, which is also used to send, appoints
Business processing status is applied to the external speech synthesis so that it modifies the logic state of oneself.
17. the speech synthesis system as described in claims 14 or 15, which is characterized in that the Compositing Engine is also used to stop to work as
Preceding speech synthesis and casting restart current speech synthesis and casting, the synthesis of pause current speech and casting or from pause
Place starts current speech synthesis and casting.
18. a kind of mobile terminal, which is characterized in that including the described in any item speech synthesis systems of such as claim 12 to 17 into
Row speech synthesis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210138028.2A CN103383844B (en) | 2012-05-04 | 2012-05-04 | Phoneme synthesizing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210138028.2A CN103383844B (en) | 2012-05-04 | 2012-05-04 | Phoneme synthesizing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103383844A CN103383844A (en) | 2013-11-06 |
| CN103383844B true CN103383844B (en) | 2019-01-01 |
Family
ID=49491618
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210138028.2A Active CN103383844B (en) | 2012-05-04 | 2012-05-04 | Phoneme synthesizing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103383844B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104575487A (en) * | 2014-12-11 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Voice signal processing method and device |
| CN107342084A (en) * | 2017-07-10 | 2017-11-10 | 绵阳美菱软件技术有限公司 | A kind of intelligent refrigerator and communication means and system based on intelligent refrigerator |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1438626A (en) * | 2002-02-15 | 2003-08-27 | 佳能株式会社 | Information processing apparatus with speech-sound synthesizing function and method thereof |
| CN1455386A (en) * | 2002-11-01 | 2003-11-12 | 中国科学院声学研究所 | Imbedded voice synthesis method and system |
| US6661889B1 (en) * | 2000-01-18 | 2003-12-09 | Avaya Technology Corp. | Methods and apparatus for multi-variable work assignment in a call center |
| CN1719513A (en) * | 2005-08-08 | 2006-01-11 | 北京中星微电子有限公司 | Audio frequency sequence device and sound document treatment method |
| CN101046956A (en) * | 2006-03-28 | 2007-10-03 | 国际商业机器公司 | Interactive audio effect generating method and system |
| CN101192203A (en) * | 2006-11-30 | 2008-06-04 | 中兴通讯股份有限公司 | Mobile phones audio frequency playing method |
| CN101266554A (en) * | 2008-04-22 | 2008-09-17 | 中兴通讯股份有限公司 | Embedded terminal multimedia application processing method and embedded terminal |
| CN101299332A (en) * | 2008-06-13 | 2008-11-05 | 嘉兴闻泰通讯科技有限公司 | Method for implementing speech synthesis function by GSM mobile phone |
| CN101355766A (en) * | 2008-09-11 | 2009-01-28 | 青岛海信移动通信技术股份有限公司 | Mobile terminal and control method for playing multimedia thereof |
| CN101778158A (en) * | 2009-12-29 | 2010-07-14 | 闻泰集团有限公司 | Method for processing audio conflict of mobile phone |
| CN102117221A (en) * | 2009-12-31 | 2011-07-06 | 上海博泰悦臻电子设备制造有限公司 | Audio frequency application conflict management method and manager |
| CN102262879A (en) * | 2010-05-24 | 2011-11-30 | 乐金电子(中国)研究开发中心有限公司 | Voice command competition processing method and device as well as voice remote controller and digital television |
| CN102360543A (en) * | 2007-08-20 | 2012-02-22 | 微软公司 | HMM-based bilingual (mandarin-english) TTS techniques |
| CN102402457A (en) * | 2010-09-17 | 2012-04-04 | 希姆通信息技术（上海）有限公司 | Method for processing mobile phone application program alterative events |
-
2012
- 2012-05-04 CN CN201210138028.2A patent/CN103383844B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6661889B1 (en) * | 2000-01-18 | 2003-12-09 | Avaya Technology Corp. | Methods and apparatus for multi-variable work assignment in a call center |
| CN1438626A (en) * | 2002-02-15 | 2003-08-27 | 佳能株式会社 | Information processing apparatus with speech-sound synthesizing function and method thereof |
| CN1455386A (en) * | 2002-11-01 | 2003-11-12 | 中国科学院声学研究所 | Imbedded voice synthesis method and system |
| CN1719513A (en) * | 2005-08-08 | 2006-01-11 | 北京中星微电子有限公司 | Audio frequency sequence device and sound document treatment method |
| CN101046956A (en) * | 2006-03-28 | 2007-10-03 | 国际商业机器公司 | Interactive audio effect generating method and system |
| CN101192203A (en) * | 2006-11-30 | 2008-06-04 | 中兴通讯股份有限公司 | Mobile phones audio frequency playing method |
| CN102360543A (en) * | 2007-08-20 | 2012-02-22 | 微软公司 | HMM-based bilingual (mandarin-english) TTS techniques |
| CN101266554A (en) * | 2008-04-22 | 2008-09-17 | 中兴通讯股份有限公司 | Embedded terminal multimedia application processing method and embedded terminal |
| CN101299332A (en) * | 2008-06-13 | 2008-11-05 | 嘉兴闻泰通讯科技有限公司 | Method for implementing speech synthesis function by GSM mobile phone |
| CN101355766A (en) * | 2008-09-11 | 2009-01-28 | 青岛海信移动通信技术股份有限公司 | Mobile terminal and control method for playing multimedia thereof |
| CN101778158A (en) * | 2009-12-29 | 2010-07-14 | 闻泰集团有限公司 | Method for processing audio conflict of mobile phone |
| CN102117221A (en) * | 2009-12-31 | 2011-07-06 | 上海博泰悦臻电子设备制造有限公司 | Audio frequency application conflict management method and manager |
| CN102262879A (en) * | 2010-05-24 | 2011-11-30 | 乐金电子(中国)研究开发中心有限公司 | Voice command competition processing method and device as well as voice remote controller and digital television |
| CN102402457A (en) * | 2010-09-17 | 2012-04-04 | 希姆通信息技术（上海）有限公司 | Method for processing mobile phone application program alterative events |
Non-Patent Citations (6)
| Title |
|---|
| 《基于HMM的可训练中文语音合成》;吴义坚等;《中文信息学报》;20060731;第20卷(第4期);第75-81页 |
| 《基于共振峰过渡的协同发音语音合成算法》;康广玉等;《天津大学学报》;20100930;第43卷(第9期);第810-814页 |
| 《基于波形拼接的语音合成技术研究》;苏珊珊;《福建电脑》;20081031(第10期);第104-105页 |
| 《基于语音生成和发音模型的语音合成新方法的探讨》;俞振利;《声学学报》;20000930;第25卷(第5期);第455-462页 |
| 《改进的HMM系统在英语语音合成中的研究》;张雪英等;《太原理工大学学报》;20120131;第43卷(第1期);第16-19页 |
| 《语音合成技术及其研究进展》;阿日木扎等;《内蒙古科技与经济》;20100930(第18期);第31-33页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103383844A (en) | 2013-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9911415B2 (en) | Executing a voice command during voice input | |
| WO2016205338A1 (en) | Managing interactions between users and applications | |
| JP4917884B2 (en) | System and method for text speech processing in a portable device | |
| CN108364645A (en) | A kind of method and device for realizing page interaction based on phonetic order | |
| CN106504742B (en) | Synthesize transmission method, cloud server and the terminal device of voice | |
| WO2015094907A1 (en) | Attribute-based audio channel arbitration | |
| WO2005076789B1 (en) | A system for computer-based, calendar-controlled message creation and delivery | |
| CN109977218A (en) | A kind of automatic answering system and method applied to session operational scenarios | |
| CN105721492B (en) | A kind of method, apparatus and terminal of speech processes | |
| KR102639526B1 (en) | Method for providing speech video | |
| CN106373566A (en) | Data transmission control method and device | |
| CN113748460A (en) | Bandwidth extension of incoming data using neural networks | |
| CN109005190A (en) | A method of full-duplex voice dialogue and page control are realized based on webpage | |
| CN103383844B (en) | Phoneme synthesizing method and system | |
| CN110428811B (en) | Data processing method and device and electronic equipment | |
| CN108986810A (en) | A kind of method and device for realizing interactive voice by earphone | |
| CN101299332B (en) | Method for implementing speech synthesis function by GSM mobile phone | |
| CN109326288A (en) | A kind of AI speech dialogue system | |
| CN110335610A (en) | The control method and display of multimedia translation | |
| CN108012030A (en) | A kind of mobile terminal downloading management method | |
| CN102438086A (en) | Intelligent voice system in converged communication and realization method | |
| CN104023114A (en) | Method for information processing and electronic equipment | |
| CN105653229A (en) | Method and device for implementing voice control | |
| CN106170032A (en) | The way of recording of a kind of speech data and device | |
| CN111754974A (en) | Information processing method, device, equipment and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| ASS | Succession or assignment of patent right |
Owner name: SHANGHAI GUOKE ELECTRONIC CO., LTD. Free format text: FORMER OWNER: SHENGYUE INFORMATION TECHNOLOGY (SHANGHAI) CO., LTD. Effective date: 20140919 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20140919 Address after: 201203, room 1, building 380, 108 Yin Yin Road, Shanghai, Pudong New Area Applicant after: Shanghai Guoke Electronic Co., Ltd. Address before: 201203 Shanghai Guo Shou Jing Road, Zhangjiang High Tech Park of Pudong New Area No. 356 building 3 Room 102 Applicant before: Shengle Information Technology (Shanghai) Co., Ltd. |
|
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 127, building 3, 356 GuoShouJing Road, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai, 200120 Patentee after: SHANGHAI GEAK ELECTRONICS Co.,Ltd. Address before: Room 108, building 1, 380 Yinbei Road, Pudong New Area, Shanghai 201203 Patentee before: Shanghai Nutshell Electronics Co.,Ltd. |