Summary of the invention
The embodiment of the present invention provides a kind of multitone area wake-up test method, apparatus and computer readable storage medium, so thatOne or more technical problems in the prior art are solved less.
In a first aspect, the embodiment of the invention provides a kind of multitone area wake-up test methods, comprising:
The information in the first sound area is recorded, first sound area is tone testing file in the tone testing environment in multitone areaPlay position where sound area；
Obtain the information by playing the second sound area that the tone testing file triggering wakes up；
The information in second sound area and the information in first sound area are compared；
Wake-up test result is determined according to comparing result.
In one embodiment, further includes:
The tone testing file is played using the voice playing device for being set to each sound area, wherein the voice is broadcastThe specified setting orientation that device is set to each sound area is put, the specified setting orientation includes specified setting height and/or specifiesSetting direction.
In one embodiment, the letter by playing the second sound area that the tone testing file triggering wakes up is obtainedBreath, comprising:
After playing the tone testing file triggering wake-up, the information in the sound area that the triggering wakes up is output to prisonIt controls in log；
The information in second sound area is obtained from the monitoring log.
In one embodiment, wake-up test result is determined according to comparing result, comprising:
If the information in second sound area is identical as the information in first sound area, it is determined that wake up successfully；
If the information in second sound area is not identical as the information in first sound area, it is determined that wake up failure.
In one embodiment, after determining wake-up test result according to comparing result, further includes:
According to the tone testing file respectively in the test result in each sound area, the success of multitone area wake-up test is countedRate.
In one embodiment, after determining wake-up test result according to comparing result, further includes:
According to each of multiple tone testing files tone testing file respectively in the test result in each sound area, systemCount the success rate of multitone area wake-up test.
In one embodiment, after determining wake-up test result according to comparing result, further includes:
In the case where the wake-up test result is determined as waking up failure, test crash information is recorded, the test is lostLosing information includes the tone testing file, the information in second sound area and the information in first sound area that test uses.
Second aspect, the embodiment of the invention provides a kind of multitone area wake-up test devices, comprising:
First recording unit, for recording the information in the first sound area, first sound area is tone testing file in multitoneSound area where play position in the tone testing environment in area；
Acquiring unit passes through the information for playing the second sound area that the tone testing file triggering wakes up for obtaining；
Comparison unit, for the information in second sound area and the information in first sound area to compare；
Determination unit, for determining wake-up test result according to comparing result.
In one embodiment, further include broadcast unit, be used for:
The tone testing file is played using the voice playing device for being set to each sound area, wherein the voice is broadcastThe specified setting orientation that device is set to each sound area is put, the specified setting orientation includes specified setting height and/or specifiesSetting direction.
In one embodiment, the acquiring unit is used for:
After playing the tone testing file triggering wake-up, the information in the sound area that the triggering wakes up is output to prisonIt controls in log；
The information in second sound area is obtained from the monitoring log.
In one embodiment, the determination unit is used for:
If the information in second sound area is identical as the information in first sound area, it is determined that wake up successfully；
If the information in second sound area is not identical as the information in first sound area, it is determined that wake up failure.
In one embodiment, further include statistic unit, be used for:
According to the tone testing file respectively in the test result in each sound area, the success of multitone area wake-up test is countedRate.
In one embodiment, further include statistic unit, be used for:
According to each of multiple tone testing files tone testing file respectively in the test result in each sound area, systemCount the success rate of multitone area wake-up test.
In one embodiment, further include the second recording unit, be used for:
In the case where the wake-up test result is determined as waking up failure, test crash information is recorded, the test is lostLosing information includes the tone testing file, the information in second sound area and the information in first sound area that test uses.
The third aspect, the embodiment of the invention provides a kind of multitone area wake-up test device, the function of described device can be withBy hardware realization, corresponding software realization can also be executed by hardware.The hardware or software include it is one or more withThe corresponding module of above-mentioned function.
It include processor and memory in the structure of described device in a possible design, the memory is used forStorage supports described device to execute the program of the above method, the processor is configured to storing in the memory for executingProgram.Described device can also include communication interface, be used for and other equipment or communication.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage mediums, are stored with computer program,The program realizes any method in above-mentioned first aspect when being executed by processor.
Above-mentioned technical proposal has the following advantages that or the utility model has the advantages that can comment for the application scenarios of multitone area speech recognitionThe wake-up effect for estimating multitone area, obtained wake-up accuracy test result can be used for optimizing multitone area algorithm, reduceThe time loss of test, saves human cost.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to be limited in any way.Except foregoing descriptionSchematical aspect, except embodiment and feature, by reference to attached drawing and the following detailed description, the present invention is furtherAspect, embodiment and feature, which will be, to be readily apparent that.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize thatLike that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes.Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
Fig. 1 is the flow chart of multitone area wake-up test method provided in an embodiment of the present invention.As shown in Figure 1, the present invention is realThe multitone area wake-up test method for applying example includes:
Step S110 records the information in the first sound area, and first sound area is voice of the tone testing file in multitone areaSound area where testing the play position in environment；
Step S120 obtains the information by playing the second sound area that the tone testing file triggering wakes up；
Step S130 compares the information in second sound area and the information in first sound area；
Step S140 determines wake-up test result according to comparing result.
During carrying out the wake-up accuracy test in multitone area, if according to the test method of the prior art, moreThe area Ge Yin carries out test operation in different sound area positions respectively by multiple testers, needs to consume more manpower.In view of this, in embodiments of the present invention, tone testing file can be recorded in advance before carrying out multitone area wake-up test.It may include by the corpus of the wake-up word of more individual recordings in the tone testing file recorded in advance, wherein everyone can record moreIt is secondary, and the wake-up corpus of recording is stored in tone testing file.Such as it records 10 people in advance and says 100 times " small respectivelySpend small degree " wake up word.Then it carries out waking up accuracy test using the multiple tone testing files recorded in advance.
When carrying out multitone area wake-up test, the above-mentioned voice recorded can be played in the tone testing environment in multitone areaTest file.Then in step s 110, the information in the first sound area where tone testing file playing position is recorded.Play languageIt can be triggered after sound test file and wake up multitone area voice system.In the step s 120, it can be obtained from multitone area voice systemTake the information by playing the second sound area that above-mentioned tone testing file triggering wakes up.In step S130 and step S140, lead toIt is whether identical as the information in above-mentioned first sound area to cross the information for comparing above-mentioned second sound area, determines whether this wake-up succeeds.
During stating the test of multiple tone testing files in use, a kind of embodiment is, each time can be neverIt randomly selects out a recording therein in the tone testing file of test to be tested, until tone testing file all playsComplete, i.e. whole process test is completed.In another embodiment, can also sequentially it be surveyed using multiple tone testing filesExamination, until recording file all plays.
In one embodiment, further includes:
The tone testing file is played using the voice playing device for being set to each sound area, wherein the voice is broadcastThe specified setting orientation that device is set to each sound area is put, the specified setting orientation includes specified setting height and/or specifiesSetting direction.
Such as in vehicle-mounted four sound area scene, can the position where four areas Ge Yin in the car four loudspeaker are respectively set,And loudspeaker are adjusted to suitable height and direction to simulate the height and angle that passenger speaks, keep the effect of simulation trueerIt is real.
In one embodiment, the path of each file in the tone testing file recorded in advance can be stored in appearanceIn device.The container for saving tone testing file can be named as to wakeupfiles (waking up file).Fig. 2 is another reality of the present inventionThe flow chart of the multitone area wake-up test method of example offer is provided.In step S210 as shown in Figure 2, tone testing file is loadedInto wakeupfiles container.In step S220 and step S230, random (random) function randomly evacuation container is usedIn a tone testing file, be respectively transmitted in the loudspeaker of the position where four areas Ge Yin, take turns stream broadcasting respectively.It is playingSound area SpeakPosition (play position) under can record when tone testing file where the position of currently playing loudspeaker,The namely information in the first sound area.
In one embodiment, the letter by playing the second sound area that the tone testing file triggering wakes up is obtainedBreath, comprising:
After playing the tone testing file triggering wake-up, the information in the sound area that the triggering wakes up is output to prisonIt controls in log；
The information in second sound area is obtained from the monitoring log.
In above-mentioned test process, after loudspeaker play wake-up word, triggering wakes up multitone area voice system.Triggering is more after waking upSound area voice system will wake up result and be written in monitoring log.Wherein, wake up in result includes being surveyed by playing the voiceTry the information in the second sound area that file triggering wakes up.It obtains and is waken up as a result, and obtaining by playing institute's predicate from monitoring logThe information in the second sound area that the triggering of sound test file wakes up, and be that WakeupPosition (is called out by the information preservation in the second sound areaAwake position).Referring to fig. 2, after step S230, step S240 is executed, position WakeupPosition will be waken up and plays positionSpeakPosition is set to compare.
In one embodiment, wake-up test result is determined according to comparing result, comprising:
If the information in second sound area is identical as the information in first sound area, it is determined that wake up successfully；
If the information in second sound area is not identical as the information in first sound area, it is determined that wake up failure.
In this embodiment, wake-up test result indexed variable can be preset, for recording wake-up test resultWhether succeed.Such as test result indexed variable can be named as Wakeupsuccess (successfully waking up).In above-mentioned steps S240In, if it is identical as play position SpeakPosition to wake up position WakeupPosition, it is determined that wake up successfully, andWakeupsuccess is labeled as 1.If waking up position WakeupPosition and play position SpeakPosition not phaseTogether, it is determined that wake up failure, be recorded as false wake-up, and wakeupsuccess is labeled as 0.
Such as in vehicle-mounted four sound area scene, full vehicle is divided into four areas Ge Yin, is A sound area, B sound area, C sound area and D respectivelySound area.In one example, certain test plays tone testing file 1 in A sound area, then records the first sound area of this testInformation be A sound area.It is also A sound area by playing the sound area that the triggering of tone testing file 1 wakes up, then is obtained from monitoring logThe information in the second sound area be also A sound area.The information in the second sound area is identical as the information in the first sound area in this test, determinesTo wake up successfully, and wakeupsuccess is labeled as 1.
In another example, certain test plays tone testing file 2 in B sound area, then records the of this testThe information in one sound area is B sound area.It but is C sound area by playing the sound area that the triggering of tone testing file 2 wakes up, then from monitoring logThe information in the second sound area of middle acquisition is C sound area.The information in the information in the second sound area and the first sound area not phase in this testTogether, it is determined as waking up failure, is recorded as false wake-up, and wakeupsuccess is labeled as 0.
Referring to fig. 2, step S250 is next executed, this wake-up test result record new as a line is stored in thisIn geo-statistic file.In the wake-up test result record of preservation, it may include Wakeupsuccess flag bit can also include broadcastingIt puts position SpeakPosition and wakes up position WakeupPosition.
After step S250, repeat the test of next tone testing file, circulation executes step S220 to stepRapid S250, until all tone testing files all complete by test, i.e. whole process test is completed.Whole process test is completedStep S260 is executed afterwards, counts wake-up test result and is exported.Wake-up test result may include multitone area wake-up test atPower and/or the details of false wake-up failure.
In one embodiment, further include statistic unit, be used for:
According to the tone testing file respectively in the test result in each sound area, the success of multitone area wake-up test is countedRate.Such as in the scene in vehicle-mounted four sound area, a tone testing file is randomly extracted from multiple tone testing files, pointIt is not transferred in the loudspeaker of the position where four areas Ge Yin, takes turns stream broadcasting respectively.After four areas Ge Yin are tested respectively, systemCount the success rate of wake-up test.
Fig. 3 is the flow chart for the multitone area wake-up test method that further embodiment of this invention provides.As shown in figure 3, oneIn kind embodiment, the step S140 in Fig. 1 further includes step after determining wake-up test result according to comparing resultS150:
According to each of multiple tone testing files tone testing file respectively in the test result in each sound area, systemCount the success rate of multitone area wake-up test.
Survey is waken up it has been observed that can be used and carry out multitone area by the tone testing file of the specified wake-up word of more individual recordingsExamination.For example, everyone, which can record, can also repeatedly record different wake-up words, such as " hello ", " good morning ".Through excessiveAfter secondary test, test result is counted, calculating and waking up the ratio between successful number and total testing time is multitone areaThe success rate of wake-up test.
In another embodiment, some can also be counted and wake up the successfully tested rate of word, or count some soundThe successfully tested rate in area.For example, wherein how many time test result counted in multiple tone testing files that A sound area playsIt is to wake up successfully, the wake-up test success rate for A sound area can be calculated.Further more, also statistics available the case where waking up failureUnder, the sound area of false wake-up and corresponding number etc..
In one embodiment, after determining wake-up test result according to comparing result, further includes:
In the case where the wake-up test result is determined as waking up failure, test crash information is recorded, the test is lostLosing information includes the tone testing file, the information in second sound area and the information in first sound area that test uses.
It has been observed that counting wake-up test result after the completion of test and exporting.In addition to success in the wake-up test result of statisticsRate can also include missing test crash information.Wherein, test crash information can include: false wake-up fails the language of corresponding broadcastingSound area SpeakPosition (information in the first sound area) where sound test file and loudspeaker play position and wake-up position instituteWakeupPosition (information in the second sound area) in sound area.
Further, wake-up test result can be exported to research staff to be optimized to multitone area algorithm.Wherein, excellentChange can include:
1) after each adjustment algorithm, the accuracy whether adjustment of this algorithm improves wake-up is assessed.
2) according to the test crash information of false wake-up, the producing cause of false wake-up failure is analyzed, to multitone area isolationAlgorithm is further improved and is corrected.
Above-mentioned technical proposal has the following advantages that or the utility model has the advantages that can comment for the application scenarios of multitone area speech recognitionThe wake-up effect for estimating multitone area, obtained wake-up accuracy test result can be used for optimizing multitone area algorithm, reduceThe time loss of test, saves human cost.
Fig. 4 is the structural block diagram of multitone area wake-up test device provided in an embodiment of the present invention.As shown in figure 4, of the inventionThe multitone area wake-up test device of embodiment includes:
First recording unit 100, for recording the information in the first sound area, first sound area is tone testing file moreSound area where play position in the tone testing environment in sound area；
Acquiring unit 200 passes through the information for playing the second sound area that the tone testing file triggering wakes up for obtaining；
Comparison unit 300, for the information in second sound area and the information in first sound area to compare；
Determination unit 400, for determining wake-up test result according to comparing result.
Fig. 5 be another embodiment of the present invention provides multitone area wake-up test device structural block diagram.As shown in figure 5,In a kind of embodiment, further includes broadcast unit 500, is used for:
The tone testing file is played using the voice playing device for being set to each sound area, wherein the voice is broadcastThe specified setting orientation that device is set to each sound area is put, the specified setting orientation includes specified setting height and/or specifiesSetting direction.
In one embodiment, the acquiring unit 200 is used for:
After playing the tone testing file triggering wake-up, the information in the sound area that the triggering wakes up is output to prisonIt controls in log；
The information in second sound area is obtained from the monitoring log.
In one embodiment, the determination unit 400 is used for:
If the information in second sound area is identical as the information in first sound area, it is determined that wake up successfully；
If the information in second sound area is not identical as the information in first sound area, it is determined that wake up failure.
Referring to Fig. 5, in one embodiment, further includes statistic unit 600, is used for:
According to the tone testing file respectively in the test result in each sound area, the success of multitone area wake-up test is countedRate.
In one embodiment, further include statistic unit 600, be used for:
According to each of multiple tone testing files tone testing file respectively in the test result in each sound area, systemCount the success rate of multitone area wake-up test.
In one embodiment, further include the second recording unit 700, be used for:
In the case where the wake-up test result is determined as waking up failure, test crash information is recorded, the test is lostLosing information includes the tone testing file, the information in second sound area and the information in first sound area that test uses.
The function of each unit may refer to the correlation of the above method in the multitone area wake-up test device of the embodiment of the present inventionDescription, details are not described herein.
It is described including processor and memory in the structure of multitone area wake-up test device in a possible designMemory is used to store the program for supporting multitone area wake-up test device to execute above-mentioned multitone area wake-up test method, the processingDevice is configurable for executing the program stored in the memory.The multitone area wake-up test device can also include communicationInterface, multitone area wake-up test device and other equipment or communication.
Fig. 6 is the structural block diagram for the multitone area wake-up test device that further embodiment of this invention provides.As shown in fig. 6, shouldDevice includes: memory 101 and processor 102, and the computer journey that can be run on the processor 102 is stored in memory 101Sequence.The processor 102 realizes the multitone area wake-up test method in above-described embodiment when executing the computer program.It is describedThe quantity of memory 101 and processor 102 can be one or more.
The device further include:
Communication interface 103 carries out data interaction for being communicated with external device.
Memory 101 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-Volatile memory), a for example, at least magnetic disk storage.
If memory 101, processor 102 and the independent realization of communication interface 103, memory 101,102 and of processorCommunication interface 103 can be connected with each other by bus and complete mutual communication.The bus can be Industry Standard ArchitectureStructure (ISA, Industry Standard Architecture) bus, external equipment interconnection (PCI, PeripheralComponent) bus or extended industry-standard architecture (EISA, Extended Industry StandardComponent) bus etc..The bus can be divided into address bus, data/address bus, control bus etc..For convenient for expression, Fig. 6In only indicated with a thick line, it is not intended that an only bus or a type of bus.
Optionally, in specific implementation, if memory 101, processor 102 and communication interface 103 are integrated in one piece of coreOn piece, then memory 101, processor 102 and communication interface 103 can complete mutual communication by internal interface.
Another aspect, the embodiment of the invention provides a kind of computer readable storage mediums, are stored with computer program,The program realizes any method in above-mentioned multitone area wake-up test method when being executed by processor.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically showThe description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or examplePoint is included at least one embodiment or example of the invention.Moreover, particular features, structures, materials, or characteristics describedIt may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, thisThe technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examplesSign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importanceOr implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hiddenIt include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwiseClear specific restriction.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includesIt is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portionPoint, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitableSequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the inventionEmbodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered useIn the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, forInstruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instructionThe instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or setIt is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or passDefeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipmentIt sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wiringsInterconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable read-only memory(CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other suitable JieMatter, because can then be edited, be interpreted or when necessary with other for example by carrying out optical scanner to paper or other mediaSuitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentionedIn embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storageOr firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardwareAny one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signalDiscrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), sceneProgrammable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carriesIt suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage mediumIn matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing moduleIt is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mouldBlock both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such asFruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computerIn readable storage medium storing program for executing.The storage medium can be read-only memory, disk or CD etc..
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, anyThose familiar with the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement,These should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor of the claimIt protects subject to range.