CN103383844A - Voice synthesis method and system - Google Patents
Voice synthesis method and system Download PDFInfo
- Publication number
- CN103383844A CN103383844A CN2012101380282A CN201210138028A CN103383844A CN 103383844 A CN103383844 A CN 103383844A CN 2012101380282 A CN2012101380282 A CN 2012101380282A CN 201210138028 A CN201210138028 A CN 201210138028A CN 103383844 A CN103383844 A CN 103383844A
- Authority
- CN
- China
- Prior art keywords
- phonetic synthesis
- task
- report
- synthesis
- 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.)
- Granted
Links
Images
Abstract
The invention relates to a voice synthesis method and system. The method includes the steps that voice synthesis tasks are preset, an externally-connected voice synthesis application calls and then submits the voice synthesis tasks; deploying is conducted on the various voice synthesis tasks and voice synthesis task lists which are ranked and to be processed are generated; the voice synthesis task which is to be processed and is ranked in the most front is selected from the voice synthesis task lists to be processed to undergo current voice synthesis and broadcast; the steps are repeated till no voice synthesis task is submitted and the voice synthesis task lists to be processed are empty. The method can enable various voice synthesis demands in different externally-connected voice synthesis applications to be processed through an independent voice synthesis application, so that the voice synthesis is normalized, if the externally-connected voice synthesis applications need the voice synthesis function, a long-distance calling method can be used for calling the voice synthesis function of the voice synthesis applications, resource redundancy and waste are reduced and the development complexness of the externally-connected voice synthesis application can also be simplified to a certain degree.
Description
Technical field
The present invention relates to a kind of phoneme synthesizing method and system.
Background technology
be accompanied by the develop rapidly of computer technology, speech synthesis system has also obtained huge progress, present synthetic effect is in intelligibility, can satisfy daily demand on naturalness, occurred a lot as reading news, read novel, weather is reported, note is reported, e-book such as reads aloud at the product relevant to phonetic synthesis, for each application, as long as the phonetic synthesis of relating to, must there be a module to come the special disposal phonetic synthesis, this will cause serious redundancy and the waste of resource, if the application of 10 phonetic syntheses is arranged, so just the voice synthetic module of 10 repetitions need to be arranged.
Present most of phonetic synthesis related application (using also referred to as external phonetic synthesis) is nothing more than two kinds of application scenarioss: under the first application scenarios, each voice related application has an out of use voice synthetic module of other phonetic synthesis related application, need many parts of voice synthetic modules for multiple different phonetic synthesis related application, can cause like this storage resources and exploitative serious waste; Under the second application scenarios, each phonetic synthesis related application can be called by network interface the unified interface of others' issue, but this application requires to necessarily require and can surf the Net when using speech-sound synthesizing function, and needs the download synthetic speech can produce many data traffics.
Summary of the invention
The object of the present invention is to provide a kind of phoneme synthesizing method and system, various phonetic synthesis demands in different external phonetic syntheses can being used are transferred to an independently phonetic synthesis application processing, be about to phonetic synthesis normalization, if external phonetic synthesis is used the function that need to use phonetic synthesis, can call the speech-sound synthesizing function that phonetic synthesis is used by the mode of far call, can reduce greatly resource redundancy and waste like this, also simplify to a certain extent the exploitation complexity that external phonetic synthesis is used.
For addressing the above problem, the invention provides a kind of phoneme synthesizing method, comprising:
Step 1: default phonetic synthesis task;
Step 2: external phonetic synthesis application call is also submitted described phonetic synthesis task to;
Step 3: to various phonetic synthesis tasks allocate and generate through the sequence pending phonetic synthesis task list; And
Step 4: select from described pending phonetic synthesis task list and come the most front pending phonetic synthesis task to carry out current speech synthetic and report.
Further, in said method, also comprise after described step 4, repeat above-mentioned steps one to four until be empty without phonetic synthesis job invocation and described pending phonetic synthesis task list.
Further, in said method, select from described pending phonetic synthesis task list when coming the most front pending phonetic synthesis task and carry out phonetic synthesis, also comprise the monitoring telephone situation, when listening to phone, stop current speech and synthesize and report, when listening to telephone finished, restart current speech and synthesize and report.
Further, in said method, select from described pending phonetic synthesis task list when coming the most front pending phonetic synthesis task and carry out phonetic synthesis, also comprise the monitoring telephone situation, when listening to phone, suspend current speech and synthesize and report, when listening to telephone finished, begin current speech from the place of suspending and synthesize and report.
Further, in said method, stop current speech synthetic and report or suspend the synthetic and step reported of current speech after, comprise that also transmission task treatment state (begin to report, finish to report) uses so that it revises the logic state of oneself to described external phonetic synthesis.
Further, in said method, restart current speech synthetic and report or after the place of suspending begins the synthetic and step reported of current speech, comprise that also transmission task treatment state uses so that it revises the logic state of oneself to described external phonetic synthesis.
Further, in said method, select from described pending phonetic synthesis task list when coming the most front pending phonetic synthesis task and carry out phonetic synthesis, send the task treatment state and use so that it revises the logic state of oneself to described external phonetic synthesis.
Further, in said method, described phonetic synthesis task comprises authority activate a task that external phonetic synthesis uses, submits the report task to, stops the report task, suspends the report task and delete its all report tasks.
Further, in said method, employing is carried out described current speech based on the parameterised speech synthetic method of HMM and is synthesized and report.
Further, in said method, adopt based on the phoneme synthesizing method of resonance peak or to carry out described current speech based on the waveform concatenation phoneme synthesizing method of Big-corpus synthetic.
Further, in said method, adopt first in first out, the queuing mechanism of last-in, last-out sorts to described pending phonetic synthesis task list.
Further, in said method, adopt important in front, less important after queuing mechanism described pending phonetic synthesis task list is sorted.
Further, in said method, described current speech is synthetic and report and comprise intonation adjustment, word speed adjustment, do the tone color adjustment, add reverberation effect or with the method raising sound effect of balanced device with the method for echo with the method for the change of voice.
According to another side of the present invention, a kind of mobile terminal is provided, use above-mentioned phoneme synthesizing method to carry out phonetic synthesis.
Further, in above-mentioned mobile terminal, described phonetic synthesis is used and is run on the operating system system that comprises symbian, android, ios, linux or mtk.
According to another side of the present invention, a kind of speech synthesis system is provided, comprising:
Interface module is used for default phonetic synthesis task, and for external phonetic synthesis application call and the described phonetic synthesis task of submission;
The task processing module is for the pending phonetic synthesis task list of various phonetic synthesis tasks being allocated and being generated through sequence; And
Compositing Engine is used for selecting from described pending phonetic synthesis task list and comes the most front pending phonetic synthesis task to carry out current speech synthetic and report and report situation to described external phonetic synthesis application report.
Further, in said system, described phonetic synthesis task comprises authority activate a task that external phonetic synthesis uses, submits the report task to, stops the report task, suspends the report task and delete its all report tasks.
Further, in said system, also comprise the monitoring module, be used for the monitoring telephone situation, when listening to phone, notify described Compositing Engine to stop current speech and synthesize and report, when listening to telephone finished, notify described Compositing Engine to restart current speech and synthesize and report.
Further, in said system, described monitoring module, also be used for the monitoring telephone situation, when listening to phone, notify described Compositing Engine to suspend current speech and synthesize and report, when listening to telephone finished, notify described Compositing Engine to begin current speech from the place of suspending and synthesize and report.
Further, in said system, monitor module and also use so that it revises the logic state of oneself to described external phonetic synthesis for transmission task treatment state.
Further, in said system, it is synthetic and report, restart that current speech is synthetic and to report, suspend current speech synthetic and report or begin current speech from the place of suspending synthetic and report that described Compositing Engine also is used for stopping current speech.
According to another side of the present invention, a kind of mobile terminal is provided, comprise that above-mentioned speech synthesis system carries out phonetic synthesis.
compared with prior art, the present invention is by default phonetic synthesis task, external phonetic synthesis application call is also submitted described phonetic synthesis task to, then to various phonetic synthesis tasks allocate and generate through the sequence pending phonetic synthesis task list, and select from described pending phonetic synthesis task list and come the most front pending phonetic synthesis task to carry out current speech synthetic and report, and repeat above-mentioned steps until be empty without phonetic synthesis task and described pending phonetic synthesis task list, various phonetic synthesis demands in different external phonetic syntheses can being used are transferred to an independently phonetic synthesis application processing, be about to phonetic synthesis normalization, if external phonetic synthesis is used the function that need to use phonetic synthesis, can call the speech-sound synthesizing function that phonetic synthesis is used by the mode of far call, can reduce greatly resource redundancy and waste like this, also simplified to a certain extent the exploitation complexity that external phonetic synthesis is used.
In addition, at running of mobile terminal, the user does not need online, can not produce any data traffic yet, is conducive to promote advancing of speech synthesis technique with speech synthesis system of the present invention.
In addition, by default phonetic synthesis task, for external phonetic synthesis application call and submit described phonetic synthesis task to, phonetic synthesis can be used be integrated into for the unified of different mobile terminal equipment and use, being different from traditional phonetic synthesis uses, the unified phonetic synthesis of the present invention that mobile terminal device only need to be installed is used, if using, external phonetic synthesis needs to use speech-sound synthesizing function, can can realize speech-sound synthesizing function by calling unified phonetic synthesis task, effectively reduce storage and exploit natural resources.
Description of drawings
Fig. 1 is the process flow diagram of the phoneme synthesizing method of the embodiment of the present invention one;
Fig. 2 is the process flow diagram 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 processing flow chart 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 processing flow chart of the speech synthesis system of the embodiment of the present invention five.
Embodiment
For above-mentioned purpose of the present invention, feature and advantage can be become apparent more, the present invention is further detailed explanation below in conjunction with the drawings and specific embodiments.
Embodiment one
As shown in Figure 1, the invention provides a kind of phoneme synthesizing method, comprising:
Step S11, default phonetic synthesis task; Wherein, described phonetic synthesis task comprises authority activate a task that external phonetic synthesis uses, submits the report task to, stops the report task, suspends the report task and delete all report tasks;
step S12, external phonetic synthesis application call is also submitted described phonetic synthesis task to, concrete, by default phonetic synthesis task, for external phonetic synthesis application call and submit described phonetic synthesis task to, phonetic synthesis can be used be integrated into for the unified of different terminal equipment and use, being different from traditional phonetic synthesis uses, the unified phonetic synthesis of the present invention that terminal device only need to be installed is used, if using, external phonetic synthesis needs to use speech-sound synthesizing function, can can realize speech-sound synthesizing function by calling default phonetic synthesis task, effectively reduce storage and exploit natural resources,
Step S13, to various phonetic synthesis tasks allocate and generate through the sequence pending phonetic synthesis task list, carry out in order to guarantee the phonetic synthesis on terminal device; Can adopt the queuing mechanism of first in first out, last-in, last-out that described pending phonetic synthesis task list is sorted, perhaps, adopt important front, less important after queuing mechanism described pending phonetic synthesis task list is sorted;
step S14 selects from described pending phonetic synthesis task list and comes the most front pending phonetic synthesis task to carry out current speech synthetic and report, can adopt that to carry out described current speech based on the parameterised speech synthetic method of HMM synthetic and report, the memory space of this method and the requirement of operand are not high, and the intelligibility of synthetic speech and naturalness all very high, the phonetic synthesis that meets fully on various mobile terminals is used, because synthesizing, the parameterised speech based on HMM uses widespread, so do not do concrete introduction here, in addition, also can adopt based on the phoneme synthesizing method of resonance peak or to carry out described current speech based on the waveform concatenation phoneme synthesizing method of Big-corpus synthetic, but based on the effect of the Speech Synthesis Algorithm of resonance peak can be on intelligibility and naturalness shortcoming to some extent, be only applicable to the less demanding situation of phonetic synthesis, requiring based on the calculated amount of the waveform concatenation Speech Synthesis Algorithm of Big-corpus and memory space can be higher, can be used on the higher terminal device of processing power, in order to make the phonetic synthesis effect abundanter, described current speech is synthetic and report and comprise intonation adjustment, word speed adjustment, do the tone color adjustment, add reverberation effect or with the method raising sound effect of balanced device with the method for echo with the method for the change of voice, when carrying out this step, also can send the task treatment state and report as beginning, finish to report to wait to described external phonetic synthesis and use so that it revises the logic state of oneself,
Step S15 judges whether whether without phonetic synthesis job invocation and described pending phonetic synthesis task list be empty, if, execution in step S16, if not, repeating step S11 is to step S15;
Step S16 finishes to withdraw from.
Various phonetic synthesis demands during the present embodiment can be used different external phonetic syntheses are transferred to an independently phonetic synthesis application processing, be about to phonetic synthesis normalization, if external phonetic synthesis is used the function that need to use phonetic synthesis, can call the speech-sound synthesizing function that phonetic synthesis is used by the mode of far call, can reduce greatly resource redundancy and waste like this, also simplify to a certain extent the exploitation complexity that external phonetic synthesis is used.
Embodiment two
The difference of the present embodiment and embodiment one is, come the most front pending phonetic synthesis task and carry out the synthetic and step reported of current speech simultaneously carrying out to select from described pending phonetic synthesis task list, increase the monitoring telephone situation and made the step of corresponding special processing, so that phoneme synthesizing method of the present invention is applicable to the mobile terminal device that mobile phone etc. need to receive calls, guarantee that in the process of phonetic synthesis, telephony feature is enough normally used.
As shown in Figure 2, the invention provides another kind of phoneme synthesizing method, comprising:
Step S21, default phonetic synthesis task, concrete, described phonetic synthesis task comprises authority activate a task that external phonetic synthesis uses, submits the report task to, stops the report task, suspends the report task and delete all report tasks;
Step S22, external phonetic synthesis application call is also submitted described phonetic synthesis task to;
Step S23, to various phonetic synthesis tasks allocate and generate through the sequence pending phonetic synthesis task list, carry out in order to guarantee the phonetic synthesis on terminal device, optionally, adopt first in first out, the queuing mechanism of last-in, last-out sorts to described pending phonetic synthesis task list, or adopt important in front, less important after queuing mechanism described pending phonetic synthesis task list is sorted;
Step S24, select from described pending phonetic synthesis task list and come the most front pending phonetic synthesis task to carry out current speech synthetic and report, and monitoring telephone situation, when listening to phone, stopping current speech synthesizing and reports, when listening to telephone finished, restart current speech and synthesize and report; In addition, when listening to phone, also can suspend current speech and synthesize and report, when listening to telephone finished, begin current speech from the place of suspending and synthesize and report;
Step S25, transmission task treatment state is used so that it revises the logic state of oneself to described external phonetic synthesis, concrete, described external phonetic synthesis is used according to the logic of the various task treatment states in the phonetic synthesis process as beginning to report, stop reporting, suspend report, restart the current speech report, begin the state realizations oneself such as current speech report from the place of suspending, as described in revising, external phonetic synthesis is used the report state of oneself;
Step S26, judge whether whether without phonetic synthesis job invocation or described pending phonetic synthesis task list be empty, if, execution in step S27, if not, repeating step S22 is to step S26, if default phonetic synthesis task does not need to reset here, can directly begin to carry out to step S26 from step S22, omit and re-executed step S21;
Step S27 finishes to withdraw from.
As shown in Figure 3, use the present invention can generate a normalized phonetic synthesis platform, the phonetic synthesis demand that this platform can be realized a tin note, answer a call, listens novel, listens novel, listens news, listens the various external phonetic syntheses application such as weather.
various phonetic synthesis demands during the present embodiment can be used different external phonetic syntheses are transferred to an independently phonetic synthesis application processing, be about to phonetic synthesis normalization, if external phonetic synthesis is used the function that need to use phonetic synthesis, can call the speech-sound synthesizing function that phonetic synthesis is used by the mode of far call, can reduce greatly resource redundancy and waste like this, also simplified to a certain extent the exploitation complexity that external phonetic synthesis is used, in addition, the present embodiment can also guarantee that in the process of phonetic synthesis, telephony feature is enough normally used.
Embodiment three
The present invention also provides a kind of mobile terminal, use the phoneme synthesizing method described in embodiment one or embodiment two to carry out phonetic synthesis, optionally, described phonetic synthesis is used and is run on the operating system system that comprises symbian, android, ios, linux or mtk.
The present embodiment can be used phonetic synthesis and be integrated into an independent application product, for different mobile terminal devices, mobile terminal system includes but not limited to symbian, android, ios, linux, mtk etc., after unified phonetic synthesis application has been installed on these terminal devices, external phonetic synthesis application itself on these equipment no longer needs separately independently phonetic synthesis application, directly call the unified phonetic synthesis application of the present invention and can realize speech-sound synthesizing function, final, formed a unified phonetic synthesis platform for terminal device.
Embodiment four
As shown in Figure 4, the present invention also provides speech synthesis system 1, most importantly interface module 11, task processing module 12 and Compositing Engine 13 in normalized speech synthesis system.
Interface module 11 is used for default phonetic synthesis task, and use 14 for external phonetic synthesis and call and submit to described phonetic synthesis task, optionally, described phonetic synthesis task comprises authority activate a task that external phonetic synthesis uses, submits the report task to, stops the report task, suspends the report task and delete all report tasks.Concrete, interface module 11 is main is responsible for the control inputs that external phonetic synthesis is used, and is used for to external phonetic synthesis application call, submits to the report task to stop the report task and report etc. finishing to begin to report, to call such as call.By being set, interface module 11 speech synthesis system 1 can be integrated into unified application system for different terminal equipment, be different from traditional speech synthesis system, the speech synthesis system that the present invention that terminal device only need to be installed is unified, if using, external phonetic synthesis needs to use speech-sound synthesizing function, can can realize speech-sound synthesizing function by calling unified interface module 11, effectively reduce storage and exploit natural resources.
Wherein, authority activate a task (activate) is in order to activate this phonetic synthesis related application to obtain the Compositing Engine processing authority; Submit report task (speak) to, in order to submit the phonetic synthesis task to; Stop report task (stop), the report task of using in order to stop the current external phonetic synthesis of reporting, this external phonetic synthesis is used and can not be stopped other report task; Delete all report tasks (stopAll), use in order to delete current external phonetic synthesis all tasks of submitting to.External phonetic synthesis application 14 is called above interface module 11 and can be realized calling of phonetic synthesis task.
task processing module 12 is for the pending phonetic synthesis task list of various phonetic synthesis tasks being allocated and being generated through sequence, task processing module 12 is mainly the treatment mechanism of the various phonetic synthesis tasks of reply, guarantee that the phonetic synthesis on terminal device is orderly, because normalized speech synthesis system need to be processed the different external connection phonetic synthesis and use the phonetic synthesis task that sends, so task processing module 12 will guarantee the order of synthetic task, task processing module 12 can adopt arriving first of task to come the front, afterwards to task come the queuing mechanism of back, process in order pending phonetic synthesis task for Compositing Engine 13.
Compositing Engine 13 is used for selecting from described pending phonetic synthesis task list and comes the most front pending phonetic synthesis task to carry out current speech synthetic and report and report situation to described external phonetic synthesis application report.Main being responsible for of Compositing Engine 13 carried out phonetic synthesis and reports the text of input, and when synthetic task began to report and finishes to report, Compositing Engine 13 all can notify external phonetic synthesis to use so that respective handling is done by task call side.Described Compositing Engine 13 also be used for transmission task treatment state as begin to report, finish to report to as described in external phonetic synthesis use so that it revises the logic state of oneself.
as shown in Figure 5, supposing currently has three pending phonetic synthesis tasks to upload to normalization phonetic synthesis platform, platform is given when first three pending phonetic synthesis task ranking according to the task uplink time, in Fig. 5, the pending phonetic synthesis task of the external phonetic synthesis application two of hypothesis ranks the first, Compositing Engine 13 is taken out first pending phonetic synthesis task as the current task of Compositing Engine 13 from the pending phonetic synthesis task list of task processing module 12, when beginning to process, Compositing Engine 12 can be sent out a message that begins to report and use two to external phonetic synthesis, this moment, external phonetic synthesis application two can realize with this message the logic of oneself, such as revising report state etc., then begin the content of the task of reporting, after reporting end, the message of end process can be issued equally external phonetic synthesis corresponding to current task and use, then Compositing Engine 13 goes to obtain in pending phonetic synthesis task list second pending phonetic synthesis task again, continue same processing.
Various phonetic synthesis demands during this enforcement can be used different external phonetic syntheses are transferred to an independently speech synthesis system processing, be about to phonetic synthesis normalization, if external phonetic synthesis is used the function that need to use phonetic synthesis, can call by the mode of far call the speech-sound synthesizing function of speech synthesis system, can reduce greatly resource redundancy and waste like this, also simplify to a certain extent the exploitation complexity of external speech synthesis system.
Embodiment five
As shown in Figure 6, the present invention also provides another kind of speech synthesis system 2, the difference of the present embodiment and embodiment four is to have increased monitoring module 24, so that speech synthesis system of the present invention is applicable to the mobile terminal device that mobile phone etc. need to receive calls, guarantee that in the process of phonetic synthesis, telephony feature is enough normally used.
Interface module 21 is used for default phonetic synthesis task, and use 25 for external phonetic synthesis and call and submit to described phonetic synthesis task, optionally, described phonetic synthesis task comprises authority activate a task that external phonetic synthesis uses, submits the report task to, stops the report task, suspends the report task and delete all report tasks.
Task processing module 22 is for the pending phonetic synthesis task list of various phonetic synthesis tasks being allocated and being generated through sequence.task processing module 22 is mainly the treatment mechanism of the various synthetic tasks of reply, guarantee that the phonetic synthesis on terminal device is orderly, because normalized speech synthesis system need to be processed the different external connection phonetic synthesis and use the synthetic task that sends, so this module will guarantee the order of synthetic task, task processing module 22 can adopt arriving first of task to come the front, afterwards to task come the queuing mechanism of back, process in order pending phonetic synthesis task for Compositing Engine 23, and also need special processing for mobile phone, phone need to suspend other all phonetic synthesis tasks to guarantee that phone can normally use period.
Compositing Engine 23 is used for selecting from described pending phonetic synthesis task list and comes the most front pending phonetic synthesis task to carry out current speech synthetic and report and report situation to described external phonetic synthesis application report.In order to coordinate with described monitoring module 24, it is synthetic and report, restart that current speech is synthetic and to report, suspend current speech synthetic and report or begin current speech from the place of suspending synthetic and when reporting that described Compositing Engine 23 also is used for stopping current speech.Described Compositing Engine 23 also is used for transmission task treatment state and uses so that it revises the logic state of oneself to described external phonetic synthesis.
Monitor module 24 and be used for the monitoring telephone situation, when listening to phone, notify described Compositing Engine to stop current speech and synthesize and report, when listening to telephone finished, notify described Compositing Engine to restart current speech and synthesize and report.In addition, described monitoring module 24 also can be notified described Compositing Engine to suspend current speech and synthesizes and report when listening to phone, when listening to telephone finished, notifies described Compositing Engine to begin current speech from the place of suspending and synthesizes and report.On the mobile terminals such as mobile phone, whether normalized speech synthesis system needs a telephone monitoring module 24 to monitor phone this moment, if phone is arranged, interrupt so current synthetic task, and send one and used 25 by the signal of phone call to the external phonetic synthesis of current task, after telephone finished, then take next pending phonetic synthesis task to process in the synthetic speech task list.
As shown in Figure 7, increased by a telephone monitoring device in figure as monitoring module 24, when the telephone monitoring device has listened to phone, can be by Compositing Engine 23 to interrupt phonetic synthesis and report.That is to say, here when listening to phone or removing electricity, Compositing Engine 23 all phonetic synthesis tasks will be blocked so, report and also can be stopped, after telephone finished, task will start again, and Compositing Engine 23 engines are processed remaining pending phonetic synthesis task in order, and normalized phonetic synthesis platform need to facilitate the easy-to-use report mode that stops to make the user can stop easily reporting.
In order to make phonetic synthesis platform effect abundanter, can do some expansions on the basis of the speech synthesis engine 23 on basis, such as about the adjustment of intonation and word speed, make the adjustment of tone color of the method for the change of voice, method with echo is added reverberation effect, method with balanced device improves sound effect, and expansion includes but not limited to the above content of enumerating.
Various phonetic synthesis demands during the present embodiment not only can be used different external phonetic syntheses are transferred to an independently speech synthesis system processing, be about to phonetic synthesis normalization, if external phonetic synthesis is used the function that need to use phonetic synthesis, can call by the mode of far call the speech-sound synthesizing function of speech synthesis system, can reduce greatly resource redundancy and waste like this, also simplified to a certain extent the exploitation complexity of other external speech synthesis systems, can also guarantee that in the process of phonetic synthesis, telephony feature is enough normally used.
Embodiment six
The present invention also provides a kind of mobile terminal, comprises as embodiment four or the described speech synthesis system of embodiment five carrying out phonetic synthesis.
the present embodiment can be integrated into speech synthesis system an independent application product, for different mobile terminal devices, under identical speech synthesis engine, being packaged into the phonetic synthesis that may operate under this system uses, mobile terminal system includes but not limited to symbian, android, ios, linux, mtk etc., after on these terminal devices, unified speech synthesis system being installed, external phonetic synthesis on these equipment is used and is not needed separately independently phonetic synthesis processing module, the interface that directly calls unified speech synthesis system is that module can realize speech-sound synthesizing function, finally formed a unified phonetic synthesis platform for terminal device, not only can effectively reduce storage and exploit natural resources, also can make speech synthesis engine is at local runtime, do not need the user to surf the Net, can not produce any data traffic.
the present invention is by default phonetic synthesis task, external phonetic synthesis application call is also submitted described phonetic synthesis task to, then to various phonetic synthesis tasks allocate and generate through the sequence pending phonetic synthesis task list, and select from described pending phonetic synthesis task list and come the most front pending phonetic synthesis task to carry out current speech synthetic and report, and repeat above-mentioned steps until be empty without phonetic synthesis task and described pending phonetic synthesis task list, various phonetic synthesis demands in different external phonetic syntheses can being used are transferred to an independently phonetic synthesis application processing, be about to phonetic synthesis normalization, if external phonetic synthesis is used the function that need to use phonetic synthesis, so just can call the speech-sound synthesizing function that phonetic synthesis is used by the mode of far call, can reduce greatly resource redundancy and waste like this, also simplified to a certain extent the exploitation complexity that other external phonetic syntheses are used.
In addition, by with speech synthesis system of the present invention at running of mobile terminal, the user do not need the online, can not produce any data traffic yet, be conducive to promote advancing of speech synthesis technique.
In addition, by default phonetic synthesis task, for external phonetic synthesis application call and submit described phonetic synthesis task to, speech synthesis system can be integrated into for the unified of different mobile terminal equipment and use, being different from traditional phonetic synthesis uses, the unified phonetic synthesis of the present invention that mobile terminal device only need to be installed is used, if using, external phonetic synthesis needs to use speech-sound synthesizing function, can unified connect the phonetic synthesis task and can realize speech-sound synthesizing function by calling, effectively reduce storage and exploit natural resources.
In this instructions, each embodiment adopts the mode of going forward one by one to describe, and what each embodiment stressed is and the difference of other embodiment that between each embodiment, identical similar part is mutually referring to getting final product.For embodiment disclosed system, due to corresponding with the disclosed method of embodiment, so describe fairly simple, relevant part partly illustrates referring to method and gets final product.
The professional can also further recognize, unit and the algorithm steps of each example of describing in conjunction with embodiment disclosed herein, can realize with electronic hardware, computer software or combination both, for the interchangeability of hardware and software clearly is described, composition and the step of each example described in general manner according to function in the above description.These functions are carried out with hardware or software mode actually, depend on application-specific and the design constraint of technical scheme.The professional and technical personnel can specifically should be used for realizing described function with distinct methods to each, but this realization should not thought and exceeds scope of the present invention.
Obviously, those skilled in the art can carry out various changes and modification and not break away from the spirit and scope of the present invention invention.Like this, if within of the present invention these were revised and modification belongs to the scope of claim of the present invention and equivalent technologies thereof, the present invention also was intended to comprise these change and modification.
Claims (22)
1. a phoneme synthesizing method, is characterized in that, comprising:
Step 1: default phonetic synthesis task;
Step 2: external phonetic synthesis application call is also submitted described phonetic synthesis task to;
Step 3: to various phonetic synthesis tasks allocate and generate through the sequence pending phonetic synthesis task list; And
Step 4: select from described pending phonetic synthesis task list and come the most front pending phonetic synthesis task to carry out current speech synthetic and report.
2. phoneme synthesizing method as claimed in claim 1, is characterized in that, also comprises after described step 4, repeats above-mentioned steps one to four until be empty without phonetic synthesis job invocation and described pending phonetic synthesis task list.
3. phoneme synthesizing method as claimed in claim 1, it is characterized in that, select from described pending phonetic synthesis task list when coming the most front pending phonetic synthesis task and carry out phonetic synthesis, also comprise the monitoring telephone situation, when listening to phone, stop current speech and synthesize and report, when listening to telephone finished, restart current speech and synthesize and report.
4. phoneme synthesizing method as claimed in claim 1, it is characterized in that, select from described pending phonetic synthesis task list when coming the most front pending phonetic synthesis task and carry out phonetic synthesis, also comprise the monitoring telephone situation, when listening to phone, suspend current speech and synthesize and report, when listening to telephone finished, begin current speech from the place of suspending and synthesize and report.
5. phoneme synthesizing method as described in claim 3 or 4, it is characterized in that, stop current speech synthetic and report or suspend the synthetic and step reported of current speech after, comprise that also transmission task treatment state uses so that it revises the logic state of oneself to described external phonetic synthesis.
6. phoneme synthesizing method as described in claim 3 or 4, it is characterized in that, restart current speech synthetic and report or after the place of suspending begins the synthetic and step reported of current speech, comprise that also transmission task treatment state uses so that it revises the logic state of oneself to described external phonetic synthesis.
7. phoneme synthesizing method as claimed in claim 1, it is characterized in that, select from described pending phonetic synthesis task list when coming the most front pending phonetic synthesis task and carry out phonetic synthesis, send the task treatment state and use so that it revises the logic state of oneself to described external phonetic synthesis.
8. phoneme synthesizing method as claimed in claim 1, is characterized in that, described phonetic synthesis task comprises authority activate a task that external phonetic synthesis uses, submits the report task to, stops the report task, suspends the report task and delete its all report tasks.
9. phoneme synthesizing method as claimed in claim 1, is characterized in that, employing is carried out described current speech based on the parameterised speech synthetic method of HMM and synthesized and report.
10. phoneme synthesizing method as claimed in claim 1, is characterized in that, adopts based on the phoneme synthesizing method of resonance peak or to carry out described current speech based on the waveform concatenation phoneme synthesizing method of Big-corpus synthetic.
11. phoneme synthesizing method as claimed in claim 1 is characterized in that, adopts the queuing mechanism of first in first out, last-in, last-out that described pending phonetic synthesis task list is sorted.
12. phoneme synthesizing method as claimed in claim 1 is characterized in that, adopt important front, less important after queuing mechanism described pending phonetic synthesis task list is sorted.
13. phoneme synthesizing method as claimed in claim 1, it is characterized in that, described current speech is synthetic and report and comprise intonation adjustment, word speed adjustment, do the tone color adjustment, add reverberation effect or with the method raising sound effect of balanced device with the method for echo with the method for the change of voice.
14. a mobile terminal is characterized in that, uses phoneme synthesizing method as described in claim 1 to 13 any one to carry out phonetic synthesis.
15. mobile terminal as claimed in claim 14 is characterized in that, described phonetic synthesis is used and is run on the operating system system that comprises symbian, android, ios, linux or mtk.
16. a speech synthesis system is characterized in that, comprising:
Interface module is used for default phonetic synthesis task, and for external phonetic synthesis application call and the described phonetic synthesis task of submission;
The task processing module is for the pending phonetic synthesis task list of various phonetic synthesis tasks being allocated and being generated through sequence; And
Compositing Engine is used for selecting from described pending phonetic synthesis task list and comes the most front pending phonetic synthesis task to carry out current speech synthetic and report and report situation to described external phonetic synthesis application report.
17. speech synthesis system as claimed in claim 16 is characterized in that, described phonetic synthesis task comprises authority activate a task that external phonetic synthesis uses, submits the report task to, stops the report task, suspends the report task and delete its all report tasks.
18. speech synthesis system as claimed in claim 16, it is characterized in that, also comprise the monitoring module, be used for the monitoring telephone situation, when listening to phone, notify described Compositing Engine to stop current speech and synthesize and report, when listening to telephone finished, notify described Compositing Engine to restart current speech and synthesize and report.
19. speech synthesis system as claimed in claim 18, it is characterized in that, described monitoring module, also be used for the monitoring telephone situation, when listening to phone, notify described Compositing Engine to suspend current speech and synthesize and report, when listening to telephone finished, notify described Compositing Engine to begin current speech from the place of suspending and synthesize and report.
20. speech synthesis system as described in claim 18 or 19 is characterized in that, described Compositing Engine also is used for transmission task treatment state and uses so that it revises the logic state of oneself to described external phonetic synthesis.
21. speech synthesis system as described in claim 18 or 19, it is characterized in that, it is synthetic and report, restart that current speech is synthetic and to report, suspend current speech synthetic and report or begin current speech from the place of suspending synthetic and report that described Compositing Engine also is used for stopping current speech.
22. a mobile terminal is characterized in that, comprises that speech synthesis system as described in claim 16 to 21 any one carries out phonetic 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 true CN103383844A (en) | 2013-11-06 |
| CN103383844B 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) |
Cited By (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 |
|---|
| 俞振利: "《基于语音生成和发音模型的语音合成新方法的探讨》", 《声学学报》 * |
| 吴义坚等: "《基于HMM的可训练中文语音合成》", 《中文信息学报》 * |
| 康广玉等: "《基于共振峰过渡的协同发音语音合成算法》", 《天津大学学报》 * |
| 张雪英等: "《改进的HMM系统在英语语音合成中的研究》", 《太原理工大学学报》 * |
| 苏珊珊: "《基于波形拼接的语音合成技术研究》", 《福建电脑》 * |
| 阿日木扎等: "《语音合成技术及其研究进展》", 《内蒙古科技与经济》 * |
Cited By (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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103383844B (en) | 2019-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105183698B (en) | A kind of control processing system and method based on multi-core DSP | |
| CN104754536A (en) | Method and system for realizing communication between different languages | |
| CN105955748B (en) | The return scene process method and device of application program | |
| CA2585295A1 (en) | System and method for synchronous processing of media data on an asynchronous processor | |
| CN101661392B (en) | Method, device and equipment for operating special interface tool on mobile terminal | |
| CN1874603A (en) | Methods and systems for cross-platform message exchange | |
| CN104778950A (en) | Microphone signal delay compensation control method based on echo cancellation | |
| CN104580532A (en) | Cross-platform application system | |
| CN105204816A (en) | Method and device for controlling audios in multisystem | |
| CN111524516A (en) | Control method based on voice interaction, server and display device | |
| CN103383844A (en) | Voice synthesis method and system | |
| CN101527755B (en) | Voice interactive method based on VoiceXML movable termination and movable termination | |
| CN111916055A (en) | Speech synthesis method, platform, server and medium for outbound system | |
| CN101335651B (en) | Simulated testing system and method for expanding terminal by the same system | |
| CN103543982A (en) | Clock frequency management method and mobile device | |
| CN101299332B (en) | Method for implementing speech synthesis function by GSM mobile phone | |
| CN102946498B (en) | Multi-thread and multi-channel parallel interactive voice response (IVR) intelligent voice telephone group calling control method | |
| US20030212732A1 (en) | Application parallel processing system and application parallel processing method | |
| CN113035246B (en) | Audio data synchronous processing method and device, computer equipment and storage medium | |
| CN113608845A (en) | Data processing method and device | |
| CN106354556A (en) | Audio transmission method and electronic device | |
| CN112003991A (en) | Outbound method and related equipment | |
| CN105120532A (en) | RIL processing method based on multiplexing and wireless communication module | |
| CN104795072A (en) | Method and device for coding audio data | |
| CN109857472A (en) | Towards the exchange method and device for having screen equipment |
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 |
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. |
|
| CP03 | Change of name, title or address |