CN110264995A - The tone testing method, apparatus electronic equipment and readable storage medium storing program for executing of smart machine - Google Patents
The tone testing method, apparatus electronic equipment and readable storage medium storing program for executing of smart machine Download PDFInfo
- Publication number
- CN110264995A CN110264995A CN201910578108.1A CN201910578108A CN110264995A CN 110264995 A CN110264995 A CN 110264995A CN 201910578108 A CN201910578108 A CN 201910578108A CN 110264995 A CN110264995 A CN 110264995A
- Authority
- CN
- China
- Prior art keywords
- smart machine
- audio
- memory space
- sub
- testing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 227
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000010485 coping Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/01—Assessment or evaluation of speech recognition systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Debugging And Monitoring (AREA)
Abstract
The embodiment of the present invention provides the tone testing method, apparatus electronic equipment and readable storage medium storing program for executing of a kind of smart machine, the described method includes: to the first smart machine input test audio-frequency information, the testing audio information is identified by first smart machine, the testing audio information first passes through the second smart machine in advance and records to obtain, and first smart machine and second smart machine are the identical smart machine of category；Obtain the test log of first smart machine, test log generation when first smart machine identifies the testing audio information includes speech recognition result of first smart machine to the testing audio information in the test log；According to institute's speech recognition result in the test log, the tone testing result of first smart machine is determined.This method can greatly reduce human cost, hence it is evident that reduce the testing time.
Description
Technical field
The present embodiments relate to intelligent sound technology more particularly to a kind of tone testing method, apparatus of smart machine
Electronic equipment and readable storage medium storing program for executing.
Background technique
With the continuous development of speech recognition technology, there are more and more smart machines for supporting automatic speech recognition,
Such as support speaker, mobile phone, the tablet computer etc. of automatic speech recognition.These support the smart machine of automatic speech recognition going out
Before factory, the automatic speech recognition function to these equipment is needed to test.
In the prior art, it is mainly tested by true man's mode.Specifically, manually being sent out from tester to smart machine
The tested speech such as voice and voice inquirement are waken up out, and smart machine carries out speech recognition according to the voice received, obtains voice
Recognition result analyzes speech recognition result to obtain speech recognition test result in turn.
But using the method for the prior art will lead to speech recognition test human cost is big, time cost is high.
Summary of the invention
The embodiment of the present invention provides the tone testing method, apparatus electronic equipment and readable storage medium of a kind of smart machine
Matter, for solving the problems, such as that the human cost that speech recognition caused by the prior art is tested is big, time cost is high.
First aspect of the embodiment of the present invention provides a kind of tone testing method of smart machine, comprising:
To the first smart machine input test audio-frequency information, by first smart machine to the testing audio information into
Row identification, the testing audio information first passes through the second smart machine in advance and records to obtain, first smart machine and described the
Two smart machines are the identical smart machine of category；
The test log of first smart machine is obtained, the test log is in first smart machine to the survey
Generation when audio-frequency information is identified is tried, includes first smart machine in the test log to the testing audio information
Speech recognition result；
According to institute's speech recognition result in the test log, the tone testing knot of first smart machine is determined
Fruit.
It further, include the first memory space and the second memory space in first smart machine；
It is described to the first smart machine input test audio-frequency information, the testing audio is believed by first smart machine
Breath is identified, comprising:
Alternately sub-audio, the test are inputted into first memory space and second memory space from server
Audio-frequency information is made of multiple chronological sub-audios；
When inputting sub-audio to first memory space by first smart machine from second memory space
Sub-audio is read and identifies, when inputting sub-audio to second memory space by first smart machine from described first
Memory space reads and identifies sub-audio.
Further, it is described read by first smart machine from second memory space and identify sub-audio it
Afterwards, further includes:
The test log is written into the recognition result of the audio of second memory space by first smart machine
In；
It is described read by first smart machine and identify sub-audio from first memory space after, further includes:
The test log is written into the recognition result of the audio of first memory space by first smart machine
In.
Further, it is described when inputting sub-audio to first memory space by first smart machine from described
Second memory space reads and identifies sub-audio, is set when inputting sub-audio to second memory space by first intelligence
It is standby to be read from first memory space and identify sub-audio, comprising:
A sub-audio is inputted respectively to first memory space and second memory space；
A, it is read by first smart machine from first memory space and identifies sub-audio；
If B, the sub-audio reading of first memory space finishes, deposited by first smart machine from described second
Sub-audio is read and identifies in storage space, meanwhile, the first memory space of Xiang Suoshu inputs new sub-audio；
If C, the sub-audio reading of second memory space finishes, new consonant is inputted to second memory space
Frequently, meanwhile, A is executed；
Circulation executes A-C, until the testing audio information input finishes.
It is further, described to before the first smart machine input test audio-frequency information, further includes:
It is received by second smart machine to recorded speech and carries out signal processing to recorded speech to described, obtain institute
State the corresponding testing audio information of voice to be recorded；
Server is uploaded to the corresponding testing audio information of recorded speech by described.
It further, include third memory space and the 4th memory space in second smart machine；
It is described to be uploaded to server to the corresponding testing audio information of recorded speech for described, comprising:
Alternating inputs sub-audio into the third memory space and the 4th memory space, described to recorded speech packet
Multiple sub- voices are included, sub- voice obtains sub-audio by signal processing；
When inputting sub-audio to the third memory space by first smart machine from the 4th memory space
It reads and uploads sub-audio to the server, set when inputting sub-audio to the 4th memory space by first intelligence
It is standby to be read from the third memory space and and upload sub-audio to the server.
Further, institute's speech recognition result according in the test log determines that first intelligence is set
Standby tone testing result, comprising:
According to institute's speech recognition result in the test log, determine first smart machine different editions it
Between testing differentia information.
Second aspect of the embodiment of the present invention provides a kind of tone testing device of smart machine, comprising:
Input module is used for the first smart machine input test audio-frequency information, by first smart machine to described
Testing audio information is identified that the testing audio information first passes through the second smart machine in advance and records to obtain, first intelligence
Can equipment and second smart machine be the identical smart machine of category；
Module is obtained, for obtaining the test log of first smart machine, the test log is in first intelligence
Can equipment generation when being identified to the testing audio information, include first smart machine to institute in the test log
State the speech recognition result of testing audio information；
Determining module, for determining that first intelligence is set according to institute's speech recognition result in the test log
Standby tone testing result.
It further, include the first memory space and the second memory space in first smart machine；
The input module is specifically used for:
Alternately sub-audio, the test are inputted into first memory space and second memory space from server
Audio-frequency information is made of multiple chronological sub-audios；
When inputting sub-audio to first memory space by first smart machine from second memory space
Sub-audio is read and identifies, when inputting sub-audio to second memory space by first smart machine from described first
Memory space reads and identifies sub-audio.
Further, the input module is specifically used for:
The test log is written into the recognition result of the audio of second memory space by first smart machine
In；And
The test log is written into the recognition result of the audio of first memory space by first smart machine
In.
Further, the input module is specifically used for:
A sub-audio is inputted respectively to first memory space and second memory space；
A, it is read by first smart machine from first memory space and identifies sub-audio；
If B, the sub-audio reading of first memory space finishes, deposited by first smart machine from described second
Sub-audio is read and identifies in storage space, meanwhile, the first memory space of Xiang Suoshu inputs new sub-audio；
If C, the sub-audio reading of second memory space finishes, new consonant is inputted to second memory space
Frequently, meanwhile, A is executed；
Circulation executes A-C, until the testing audio information input finishes.
Further, described device further include:
Module is recorded, for being received by second smart machine to recorded speech and carrying out letter to recorded speech to described
Number processing, obtains the corresponding testing audio information of the voice to be recorded；
Uploading module, for being uploaded to server to the corresponding testing audio information of recorded speech for described.
It further, include third memory space and the 4th memory space in second smart machine；
The uploading module is specifically used for:
Alternating inputs sub-audio into the third memory space and the 4th memory space, described to recorded speech packet
Multiple sub- voices are included, sub- voice obtains sub-audio by signal processing；
When inputting sub-audio to the third memory space by first smart machine from the 4th memory space
It reads and uploads sub-audio to the server, set when inputting sub-audio to the 4th memory space by first intelligence
It is standby to be read from the third memory space and and upload sub-audio to the server.
Further, the determining module is specifically used for:
According to institute's speech recognition result in the test log, determine first smart machine different editions it
Between testing differentia information.
The third aspect of the embodiment of the present invention provides a kind of electronic equipment, comprising:
Memory, for storing program instruction；
Processor executes side described in above-mentioned first aspect for calling and executing the program instruction in the memory
Method step.
Fourth aspect of the embodiment of the present invention provides a kind of readable storage medium storing program for executing, and calculating is stored in the readable storage medium storing program for executing
Machine program, the computer program is for executing method described in above-mentioned first aspect.
The tone testing method, apparatus electronic equipment and readable storage medium of smart machine provided by the embodiment of the present invention
Matter is recorded on smart machine identical with tested smart machine category obtain audio-frequency information in advance, to tested intelligence
It when equipment is tested, is directly tested using the audio-frequency information recorded, and believe according to identification audio is devices under
The test log exported when breath determines tone testing as a result, this mode only needs once to record, that is, can be applied to same product
In the speech recognition test of all smart machines of class, it is therefore not necessary to which tissue true man test every time, greatly reduces human cost.
Meanwhile when testing every time, tested smart machine directly identifies audio, receives voice without executing, to voice progress
Signal processing obtains the process of audio-frequency information again, therefore, can significantly reduce the testing time.In addition, for the intelligence of same category
Energy equipment, is tested using same set of audio-frequency information, therefore can guarantee the certainty of test result.
Detailed description of the invention
It, below will be to embodiment or the prior art in order to illustrate more clearly of the present invention or technical solution in the prior art
Attached drawing needed in description is briefly described, it should be apparent that, the accompanying drawings in the following description is of the invention one
A little embodiments for those of ordinary skill in the art without any creative labor, can also be according to this
A little attached drawings obtain other attached drawings.
Fig. 1 is the exemplary system architecture figure of the tone testing method of smart machine provided in an embodiment of the present invention；
Fig. 2 is the flow diagram of the tone testing method of smart machine provided in an embodiment of the present invention；
Fig. 3 is the schematic diagram that the first smart machine receives that testing audio information carries out speech recognition；
Fig. 4 is the flow diagram of the tone testing method of smart machine provided in an embodiment of the present invention；
Fig. 5 is the schematic diagram for alternately inputting sub-audio to the first smart machine and being read by the first smart machine and being identified；
Fig. 6 is the flow diagram of the tone testing method of smart machine provided in an embodiment of the present invention；
Fig. 7 is the schematic diagram that the second smart machine receives that testing audio information carries out speech recognition；
Fig. 8 is the flow diagram of the tone testing method of smart machine provided in an embodiment of the present invention；
Fig. 9 is the function structure chart of the tone testing device of smart machine provided in an embodiment of the present invention；
Figure 10 is the function structure chart of the tone testing device of smart machine provided in an embodiment of the present invention；
Figure 11 is the structural schematic diagram of a kind of electronic equipment 1100 provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached in the embodiment of the present invention
Figure, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Speech recognition test is carried out to smart machine using true man's test method in the prior art, this mode needs every time
Tissue is a large amount of and the personnel of different geographical test, meanwhile, test needs the long period every time, therefore, cause manpower at
This is big, time cost is high.Simultaneously as tested every time using true man, and the acoustic enviroment of the sounding of true man and surrounding is inconsistent,
Therefore, cause the result tested every time that there is uncertainty.
The embodiment of the present invention based on the above issues, proposes a kind of tone testing method of smart machine, in advance with it is tested
It is recorded on the identical smart machine of examination smart machine category and obtains audio-frequency information, when testing tested smart machine,
It is directly tested using the audio-frequency information recorded, and according to the test exported when being devices under identification audio-frequency information
Log determines tone testing as a result, this mode only needs once to record, that is, can be applied to all smart machines of same category
Speech recognition test in, it is therefore not necessary to every time tissue true man test, greatly reduce human cost.Meanwhile when testing every time,
Tested smart machine directly identifies audio, receives voice without executing, and carries out signal processing to voice and obtains sound again
The process of frequency information, therefore, testing time can also significantly reduce.In addition, for the smart machine of same category, using same
A set of audio-frequency information is tested, therefore can guarantee the certainty of test result.
Fig. 1 is the exemplary system architecture figure of the tone testing method of smart machine provided in an embodiment of the present invention, such as Fig. 1
Shown, this method is related to tested smart machine, the smart machine of recording audio information, server and test equipment.Its
In, the smart machine of recording audio information sends server for audio-frequency information and saves, and tested smart machine is from server
It reads audio-frequency information and identifies, test equipment is believed using the method for the embodiment of the present invention to tested smart machine input audio
Breath obtains test log from tested smart machine, the audio-frequency information of the smart machine of recording audio information is uploaded to clothes
Business device etc..Server and test equipment can integrate on same physical equipment, for example, same PC, can be realized simultaneously
The function of above-mentioned server and test equipment.Alternatively, server and test equipment can be deployed on different physical equipments.This
Inventive embodiments are not especially limited this.
Fig. 2 is the flow diagram of the tone testing method of smart machine provided in an embodiment of the present invention, and this method is held
Row main body is above-mentioned test equipment, as shown in Fig. 2, this method comprises:
S201, to the first smart machine input test audio-frequency information, above-mentioned testing audio is believed by first smart machine
Breath identified, above-mentioned testing audio information first passes through the second smart machine in advance and records to obtain, above-mentioned first smart machine with it is upper
Stating the second smart machine is the identical smart machine of category.
Wherein, above-mentioned first smart machine is the smart machine being tested in above-mentioned Fig. 1, and above-mentioned second smart machine is upper
State the smart machine of recording audio information in Fig. 1.In the present embodiment, speech recognition test is carried out to the first smart machine.
First smart machine and the second smart machine belong to same category, and illustratively, the first smart machine and second is set
Standby is the intelligent sound box of certain model.
In the embodiment of the present invention, the first smart machine and the second smart machine can be intelligent sound box, smart phone, intelligence
Wrist-watch etc. has the smart machine of speech identifying function, tool of the embodiment of the present invention to the first smart machine and the second smart machine
Volume morphing is not especially limited.
Optionally, before testing the first smart machine, test equipment first passes through the second smart machine in advance
Recording obtains testing audio information, and by the testing audio information preservation to server.Recording audio and the process for saving audio
It will be described in detail in the following embodiments.Optionally, in this step, test equipment is from server read test audio-frequency information,
And it is input to the first smart machine.
S202, the test log for obtaining above-mentioned first smart machine, the test log is in above-mentioned first smart machine to upper
Generation when testing audio information is identified is stated, includes that above-mentioned first smart machine believes above-mentioned testing audio in the test log
The speech recognition result of breath.
Fig. 3 is the schematic diagram that the first smart machine receives that testing audio information carries out speech recognition, as shown in figure 3, first
The treatment process of smart machine in normal work are as follows: receive voice, to voice carry out signal processing obtain audio, to audio into
Row front-end processing is decoded identification, output recognition result using decoder.And in the present embodiment, it is saved in server
For audio-frequency information, therefore, test equipment is directly by the testing audio information input read from server to front end processing block
Front-end processing is carried out, then executes subsequent identification and output process, receives voice and signal processing without executing again, because
This, the mode of the present embodiment can significantly reduce the testing time of the first smart machine.
In treatment process as shown in Figure 3 above, the first smart machine carries out testing audio information using decoder
After decoding identification, recognition result can be written in test log by the first smart machine or other equipment, in turn, test is set
For available first smart machine to the test log.It optionally, include that the first smart machine is identified in the test log
Every text information out and the temporal information etc. for issuing this information.
S203, according to the upper speech recognition result in above-mentioned test log, determine the voice of above-mentioned first smart machine
Test result.
Optionally, the tone testing result of the first smart machine may include the indexs such as wake-up rate, the quasi- rate of word, the quasi- rate of sentence,
Different smart machines can have different test result indexs.
By taking the first smart machine is intelligent sound box as an example, it is assumed that the test result index of intelligent sound box includes wake-up rate, word
Quasi- rate and the quasi- rate of sentence can be to tone testing results and record after test equipment gets the tone testing result of intelligent sound box
Standard recognition result when sound is matched, and wake-up rate, the quasi- rate of word and the quasi- rate of sentence of intelligent sound box are counted according to matching result.
In the present embodiment, is recorded on smart machine identical with tested smart machine category obtain audio letter in advance
Breath is directly tested using the audio-frequency information recorded when testing tested smart machine, and according to tested
The test log that is exported determines tone testing as a result, this mode only needs once to record when examination equipment identification audio-frequency information,
It can be applied in the speech recognition test of all smart machines of same category, it is therefore not necessary to tissue true man test every time, pole
It is big to reduce human cost.Meanwhile when testing every time, tested smart machine directly identifies audio, without executing reception
Therefore voice, the process for obtaining audio-frequency information again to voice progress signal processing can significantly reduce the testing time.In addition, right
It in the smart machine of same category, is tested using same set of audio-frequency information, therefore can guarantee the determination of test result
Property.
For the smart machines such as intelligent sound box, therefore internal limited storage space is reading sound from server
Frequency information simultaneously can be not take up excessive memory space and protect to data are inputted
Card smart machine persistently receives and identifies audio-frequency information, is problem to be solved.
Optionally, the embodiment of the present invention is inputted and is read to know and solve the above problems otherwise by following alternatings.
Fig. 4 is the flow diagram of the tone testing method of smart machine provided in an embodiment of the present invention, as shown in figure 4,
To the first smart machine input test audio-frequency information in above-mentioned steps S201, the one kind for being read by the first smart machine and being identified can
Select mode are as follows:
S401, alternating input sub-audio, above-mentioned test tone into the first memory space and the second memory space from server
Frequency information is made of multiple chronological sub-audios.
It optionally, may include the first memory space and the second memory space in the first smart machine.Test equipment can be with
Alternately sub-audio is inputted into the two memory spaces.
Wherein, optionally, above-mentioned testing audio information can be the set of sub-audio, and each sub-audio can be one
Audio file, sub-audio in set according to generation Time alignment, when being inputted to the first smart machine, according to generating the time
From morning to night selection sub-audio is inputted.
S402, to above-mentioned first memory space input sub-audio when by above-mentioned first smart machine from it is above-mentioned second storage
Sub-audio is read and identifies in space, when inputting sub-audio to above-mentioned second memory space by above-mentioned first smart machine from above-mentioned
First memory space reads and identifies sub-audio.
I.e. in the present embodiment, sub-audio alternately is inputted to the first memory space and the second memory space, is deposited to first
Identification sub-audio is read from the second memory space by the first smart machine while storing up space input sub-audio, is stored to second
Identification sub-audio is read from the first memory space by the first smart machine while space inputs sub-audio, it is thereby achieved that not
While interruption inputs sub-audio from server, the first smart machine can read identification sub-audio incessantly, so that
In the case where smart machine limited storage space, it still can guarantee that smart machine persistently receives and identifies audio-frequency information.
In a kind of optional way, during above-mentioned alternate treatment, the first smart machine is read from the first memory space every time
After taking and identifying sub-audio, the recognition result of the audio of the first memory space can be written in test log, the first intelligence is set
It is standby read every time and identify sub-audio from the second memory space after, the recognition result of the audio of the second memory space can be written
In test log.
Fig. 5 is the schematic diagram for alternately inputting sub-audio to the first smart machine and being read by the first smart machine and being identified,
As shown in fig. 5, it is assumed that the first memory space is A, the second memory space is B, then the treatment process of above-mentioned steps S402 can be with are as follows:
Firstly, test equipment can input a sub-audio to the first memory space and the second memory space respectively.
Wherein, two of time earliest are generated in the testing audio information that the sub-audio inputted can save for server
Sub-audio, or, or preset content is empty sub-audio.
In turn, constantly circulation executes following A-C, until the testing audio information end of transmission that server saves.
A, it is read by the first smart machine from the first memory space and identifies sub-audio.
If B, the sub-audio reading of the first memory space finishes, read simultaneously by the first smart machine from the second memory space
Identify sub-audio, meanwhile, new sub-audio is inputted to the first memory space.
Read from the second memory space and identify sub-audio with to the first memory space input new sub-audio simultaneously into
Row.
If C, the sub-audio reading of the second memory space finishes, new sub-audio is inputted to the second memory space, meanwhile,
Execute A.
Read from the first memory space and identify sub-audio with to the second memory space input new sub-audio simultaneously into
Row.
Wherein, solid line expression is carrying out processing in above-mentioned Fig. 5, and dotted line expression is not carried out processing.
Explanation is recorded to obtain the process of above-mentioned testing audio information by the second smart machine below.
Fig. 6 is the flow diagram of the tone testing method of smart machine provided in an embodiment of the present invention, as shown in fig. 6,
Before above-mentioned steps S201, further includes:
S601, it is received by above-mentioned second smart machine to recorded speech and recorded speech, which carries out signal processing, to be waited for this, obtained
To the corresponding testing audio information of the voice to be recorded.
S602, server is uploaded to the corresponding testing audio information of recorded speech by above-mentioned.
Optionally, above-mentioned to can be voice continuous in time to recorded speech, i.e. the second smart machine is used in addition to receiving
The voice that family issues, when user does not issue voice, the second smart machine still acquires the sound in ambient enviroment, this mode
Test scene can be really restored, so that test result is more accurate.
Fig. 7 is the schematic diagram that the second smart machine receives that testing audio information carries out speech recognition, as shown in fig. 7, second
The treatment process of smart machine in normal work are as follows: receive voice, to voice carry out signal processing obtain audio, to audio into
Row front-end processing is decoded identification, output recognition result using decoder.And in the present embodiment, the second smart machine master
It is used to generate and upload testing audio information, therefore, after the second smart machine obtains audio to voice progress signal processing,
Audio can be uploaded to server and saved by test equipment.But it is worth noting that, for the second smart machine,
It still can continue the processes such as front-end processing, decoding identification, the voice that these processes obtain according to process shown in Fig. 7
Recognition result can be used for the test of the speech recognition to the second smart machine.
For the smart machines such as intelligent sound box, therefore internal limited storage space generates sound in smart machine
After frequency, how to make audio that can be not take up excessive memory space and smart machine and continue to upload to server
Audio is problem to be solved.
Optionally, the embodiment of the present invention solves the above problems following alternating inputs and by way of uploading.
Fig. 8 is the flow diagram of the tone testing method of smart machine provided in an embodiment of the present invention, as shown in figure 8,
Include: to a kind of optional way that server uploads testing audio information in above-mentioned steps S602
S801, sub-audio is alternately inputted into third memory space and the 4th memory space, it is above-mentioned to recorded speech packet
Multiple sub- voices are included, sub- voice obtains sub-audio by signal processing.
Wherein, optionally, sub according to generating when alternately inputting sub-audio to third memory space and the 4th memory space
The time of audio is from morning to night inputted.
S802, to third memory space input sub-audio when read from the first smart machine from the 4th memory space and to
Server uploads sub-audio, is read by the first smart machine from third memory space when inputting sub-audio to the 4th memory space
And and sub-audio is uploaded to server.
I.e. in the present embodiment, alternately to the first memory space and the input of the second memory space by carrying out signal to voice
Obtained sub-audio is handled, by the first smart machine from the 4th memory space while inputting sub-audio to third memory space
Sub-audio is read and uploads, by the first smart machine from third memory space while inputting sub-audio to the 4th memory space
Sub-audio is read and uploads, it is thereby achieved that uninterruptedly inputting the same of sub-audio to third memory space and the 4th memory space
When, the first smart machine can report sub-audio to server incessantly, so that in smart machine limited storage space
In the case where, it still can guarantee that smart machine continues to report audio-frequency information to server.
The specific implementation procedure of the present embodiment is similar with process exemplified by above-mentioned Fig. 5, is referred to mistake shown in above-mentioned Fig. 5
Journey, details are not described herein again.
As an alternative embodiment, according to the speech recognition result in test log in above-mentioned steps S203, really
When the tone testing result of fixed first smart machine, the first intelligence can be determined according to the speech recognition result in test log
Testing differentia information between the different editions of equipment.
Specifically, can be carried out respectively using above-mentioned testing audio information for the first smart machine of different editions
Test, and the speech recognition result for respectively obtaining each version and tone testing by the voice to different editions as a result, surveyed
Test result is compared, the testing differentia information between available each version.The testing differentia information for example can wrap
It includes: the difference of wake-up rate, the difference of word standard, difference of sentence standard etc..
Fig. 9 is the function structure chart of the tone testing device of smart machine provided in an embodiment of the present invention, as shown in figure 9,
The device includes:
Input module 901 is used for the first smart machine input test audio-frequency information, by first smart machine to institute
Testing audio information to be stated to be identified, the testing audio information first passes through the second smart machine in advance and records to obtain, and described first
Smart machine and second smart machine are the identical smart machine of category.
Module 902 is obtained, for obtaining the test log of first smart machine, the test log is described first
Generation when smart machine identifies the testing audio information includes first smart machine pair in the test log
The speech recognition result of the testing audio information.
Determining module 903, for determining first intelligence according to institute's speech recognition result in the test log
The tone testing result of equipment.
The device is for realizing preceding method embodiment, and it is similar that the realization principle and technical effect are similar, and details are not described herein again.
It include the first memory space and the second memory space in first smart machine in another embodiment；
Input module 901 is specifically used for:
Alternately sub-audio, the test are inputted into first memory space and second memory space from server
Audio-frequency information is made of multiple chronological sub-audios.
When inputting sub-audio to first memory space by first smart machine from second memory space
Sub-audio is read and identifies, when inputting sub-audio to second memory space by first smart machine from described first
Memory space reads and identifies sub-audio.
In another embodiment, input module 901 is specifically used for:
The test log is written into the recognition result of the audio of second memory space by first smart machine
In；And
The test log is written into the recognition result of the audio of first memory space by first smart machine
In.
In another embodiment, input module 901 is specifically used for:
A sub-audio is inputted respectively to first memory space and second memory space.
A, it is read by first smart machine from first memory space and identifies sub-audio.
If B, the sub-audio reading of first memory space finishes, deposited by first smart machine from described second
Sub-audio is read and identifies in storage space, meanwhile, the first memory space of Xiang Suoshu inputs new sub-audio.
If C, the sub-audio reading of second memory space finishes, new consonant is inputted to second memory space
Frequently, meanwhile, A is executed.
Circulation executes A-C, until the testing audio information input finishes.
Figure 10 is the function structure chart of the tone testing device of smart machine provided in an embodiment of the present invention, such as Figure 10 institute
Show, the device further include:
Record module 904, for by second smart machine receive to recorded speech and to it is described to recorded speech into
Row signal processing obtains the corresponding testing audio information of the voice to be recorded.
Uploading module 905, for being uploaded to server to the corresponding testing audio information of recorded speech for described.
It include third memory space and the 4th memory space in second smart machine in another embodiment；
Uploading module 905 is specifically used for:
Alternating inputs sub-audio into the third memory space and the 4th memory space, described to recorded speech packet
Multiple sub- voices are included, sub- voice obtains sub-audio by signal processing.
When inputting sub-audio to the third memory space by first smart machine from the 4th memory space
It reads and uploads sub-audio to the server, set when inputting sub-audio to the 4th memory space by first intelligence
It is standby to be read from the third memory space and and upload sub-audio to the server.
In another embodiment, determining module 903 is specifically used for:
According to institute's speech recognition result in the test log, determine first smart machine different editions it
Between testing differentia information.
It should be noted that it should be understood that the modules of apparatus above division be only a kind of logic function division,
It can completely or partially be integrated on a physical entity in actual implementation, it can also be physically separate.And these modules can be with
All realized by way of processing element calls with software；It can also all realize in the form of hardware；It can also part mould
Block realizes that part of module passes through formal implementation of hardware by way of processing element calls software.For example, determining module can be with
For the processing element individually set up, it also can integrate and realized in some chip of above-mentioned apparatus, in addition it is also possible to program
The form of code is stored in the memory of above-mentioned apparatus, is called by some processing element of above-mentioned apparatus and is executed above true
The function of cover half block.The realization of other modules is similar therewith.Furthermore these modules completely or partially can integrate together, can also
With independent realization.Processing element described here can be a kind of integrated circuit, the processing capacity with signal.In the process of realization
In, each step of the above method or the above modules can by the integrated logic circuit of the hardware in processor elements or
The instruction of software form is completed.
For example, the above module can be arranged to implement one or more integrated circuits of above method, such as:
One or more specific integrated circuits (application specific integrated circuit, ASIC), or, one
Or multi-microprocessor (digital signal processor, DSP), or, one or more field programmable gate array
(field programmable gate array, FPGA) etc..For another example, when some above module dispatches journey by processing element
When the form of sequence code is realized, which can be general processor, such as central processing unit (central
Processing unit, CPU) or it is other can be with the processor of caller code.For another example, these modules can integrate one
It rises, is realized in the form of system on chip (system-on-a-chip, SOC).
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer program
Product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all or
It partly generates according to process or function described in the embodiment of the present invention.The computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage medium
In, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, the computer
Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center
User's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or
Data center is transmitted.The computer readable storage medium can be any usable medium that computer can access or
It is comprising data storage devices such as one or more usable mediums integrated server, data centers.The usable medium can be with
It is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk
Solid state disk (SSD)) etc..
Figure 11 is the structural schematic diagram of a kind of electronic equipment 1100 provided in an embodiment of the present invention.As shown in figure 11, the electricity
Sub- equipment may include: processor 111, memory 112, communication interface 113 and system bus 114, the memory 112 and institute
It states communication interface 113 and connect and complete mutual communication with the processor 111 by the system bus 114, it is described to deposit
Reservoir 112 is for storing computer executed instructions, and the communication interface 113 is used for and other equipment are communicated, the processing
Device 111 realizes the scheme such as above-mentioned Fig. 1 to embodiment illustrated in fig. 8 when executing the computer program.
The system bus mentioned in the Figure 11 can be Peripheral Component Interconnect standard (peripheral component
Interconnect, PCI) bus or expanding the industrial standard structure (extended industry standard
Architecture, EISA) bus etc..The system bus can be divided into address bus, data/address bus, control bus etc..For
Convenient for indicating, only indicated with a thick line in figure, it is not intended that an only bus or a type of bus.Communication interface
For realizing the communication between database access device and other equipment (such as client, read-write library and read-only library).Memory
May include random access memory (random access memory, RAM), it is also possible to further include nonvolatile memory
(non-volatile memory), for example, at least a magnetic disk storage.
Above-mentioned processor can be general processor, including central processor CPU, network processing unit (network
Processor, NP) etc.；It can also be digital signal processor DSP, application-specific integrated circuit ASIC, field programmable gate array
FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
Optionally, the embodiment of the present invention also provides a kind of storage medium, and instruction is stored in the storage medium, when its
When being run on computer, so that computer executes the method such as above-mentioned Fig. 1 to embodiment illustrated in fig. 8.
Optionally, the embodiment of the present invention also provides a kind of chip of operating instruction, and the chip is for executing above-mentioned Fig. 1 extremely
The method of embodiment illustrated in fig. 8.
The embodiment of the present invention also provides a kind of program product, and described program product includes computer program, the computer
Program is stored in a storage medium, at least one processor can read the computer program from the storage medium, described
The method that at least one processor can realize above-mentioned Fig. 1 to embodiment illustrated in fig. 8 when executing the computer program.
In embodiments of the present invention, "at least one" refers to one or more, and " multiple " refer to two or more.
"and/or" describes the incidence relation of affiliated partner, indicates may exist three kinds of relationships, for example, A and/or B, can indicate: single
Solely there are A, A and B are existed simultaneously, the case where individualism B, wherein A, B can be odd number or plural number.The general table of character "/"
Show that forward-backward correlation object is a kind of relationship of "or"；In formula, character "/" indicates that forward-backward correlation object is a kind of " being divided by "
Relationship.At least one of " following (a) " or its similar expression, refer to these in any combination, including individual event (a) or
Any combination of complex item (a).For example, at least one (a) in a, b or c, can indicate: a, b, c, a-b, a-c, b-c,
Or a-b-c, wherein a, b, c can be individually, be also possible to multiple.
It is understood that the area that the various digital numbers being related in embodiments of the present invention only carry out for convenience of description
Point, it is not intended to limit the invention the range of embodiment.
It is understood that in an embodiment of the present invention, magnitude of the sequence numbers of the above procedures are not meant to execute
Sequence it is successive, the execution of each process sequence should be determined by its function and internal logic, the reality without coping with the embodiment of the present invention
It applies process and constitutes any restriction.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (10)
1. a kind of tone testing method of smart machine characterized by comprising
To the first smart machine input test audio-frequency information, the testing audio information is known by first smart machine
Not, the testing audio information first passes through the second smart machine in advance and records to obtain, first smart machine and second intelligence
Energy equipment is the identical smart machine of category；
The test log of first smart machine is obtained, the test log is in first smart machine to the test tone
Generation when frequency information is identified includes language of first smart machine to the testing audio information in the test log
Sound recognition result；
According to institute's speech recognition result in the test log, the tone testing result of first smart machine is determined.
2. the method according to claim 1, wherein in first smart machine include the first memory space and
Second memory space；
It is described to the first smart machine input test audio-frequency information, by first smart machine to the testing audio information into
Row identification, comprising:
Alternately sub-audio, the testing audio are inputted into first memory space and second memory space from server
Information is made of multiple chronological sub-audios；
It is read by first smart machine from second memory space when inputting sub-audio to first memory space
And identify sub-audio, it is stored by first smart machine from described first when inputting sub-audio to second memory space
It reads and identifies sub-audio in space.
3. according to the method described in claim 2, it is characterized in that, described stored by first smart machine from described second
After space reads and identifies sub-audio, further includes:
The recognition result of the audio of second memory space is written in the test log by first smart machine；
It is described read by first smart machine and identify sub-audio from first memory space after, further includes:
The recognition result of the audio of first memory space is written in the test log by first smart machine.
4. according to the method in claim 2 or 3, which is characterized in that described to input consonant to first memory space
Sub-audio is read and identified from second memory space by first smart machine when frequency, to second memory space
It is read by first smart machine from first memory space when inputting sub-audio and identifies sub-audio, comprising:
A sub-audio is inputted respectively to first memory space and second memory space；
A, it is read by first smart machine from first memory space and identifies sub-audio；
It is empty from second storage by first smart machine if B, the sub-audio reading of first memory space finishes
Between read and identify sub-audio, meanwhile, the first memory space of Xiang Suoshu inputs new sub-audio；
If C, the sub-audio reading of second memory space finishes, new sub-audio is inputted to second memory space,
Meanwhile executing A；
Circulation executes A-C, until the testing audio information input finishes.
5. method according to claim 1-4, which is characterized in that described to the first smart machine input test sound
Before frequency information, further includes:
Received by second smart machine to recorded speech and carry out signal processing to recorded speech to described, obtain it is described to
The corresponding testing audio information of recording voice；
Server is uploaded to the corresponding testing audio information of recorded speech by described.
6. according to the method described in claim 5, it is characterized in that, in second smart machine include third memory space and
4th memory space；
It is described to be uploaded to server to the corresponding testing audio information of recorded speech for described, comprising:
Alternating inputs sub-audio into the third memory space and the 4th memory space, and described to recorded speech includes more
A sub- voice, sub- voice obtain sub-audio by signal processing；
It is read by first smart machine from the 4th memory space when inputting sub-audio to the third memory space
And to the server upload sub-audio, to the 4th memory space input sub-audio when by first smart machine from
The third memory space reads and and uploads sub-audio to the server.
7. method according to claim 5 or 6, which is characterized in that the voice according in the test log
Recognition result determines the tone testing result of first smart machine, comprising:
According to institute's speech recognition result in the test log, between the different editions for determining first smart machine
Testing differentia information.
8. a kind of tone testing device of smart machine characterized by comprising
Input module is used for the first smart machine input test audio-frequency information, by first smart machine to the test
Audio-frequency information is identified that the testing audio information first passes through the second smart machine in advance and records to obtain, and first intelligence is set
Standby is the identical smart machine of category with second smart machine；
Module is obtained, for obtaining the test log of first smart machine, the test log is set in first intelligence
It include first smart machine in the test log to the survey for generation when being identified to the testing audio information
Try the speech recognition result of audio-frequency information；
Determining module, for determining first smart machine according to institute's speech recognition result in the test log
Tone testing result.
9. a kind of electronic equipment characterized by comprising
Memory, for storing program instruction；
Processor, for calling and executing the program instruction in the memory, perform claim requires the described in any item sides of 1-7
Method step.
10. a kind of readable storage medium storing program for executing, which is characterized in that be stored with computer program, the meter in the readable storage medium storing program for executing
Calculation machine program requires the described in any item methods of 1-7 for perform claim.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910578108.1A CN110264995A (en) | 2019-06-28 | 2019-06-28 | The tone testing method, apparatus electronic equipment and readable storage medium storing program for executing of smart machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910578108.1A CN110264995A (en) | 2019-06-28 | 2019-06-28 | The tone testing method, apparatus electronic equipment and readable storage medium storing program for executing of smart machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110264995A true CN110264995A (en) | 2019-09-20 |
Family
ID=67923072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910578108.1A Pending CN110264995A (en) | 2019-06-28 | 2019-06-28 | The tone testing method, apparatus electronic equipment and readable storage medium storing program for executing of smart machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110264995A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145737A (en) * | 2018-11-06 | 2020-05-12 | 中移（杭州）信息技术有限公司 | Voice test method and device and electronic equipment |
| CN112860582A (en) * | 2021-03-26 | 2021-05-28 | 成都启英泰伦科技有限公司 | Local voice recognition module production test method |
| CN113470618A (en) * | 2021-06-08 | 2021-10-01 | 阿波罗智联(北京)科技有限公司 | Wake-up test method and device, electronic equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1650272A (en) * | 2002-04-26 | 2005-08-03 | 飞思卡尔半导体公司 | Instruction cache and method for reducing memory conflicts |
| US9093071B2 (en) * | 2012-11-19 | 2015-07-28 | International Business Machines Corporation | Interleaving voice commands for electronic meetings |
| CN107516510A (en) * | 2017-07-05 | 2017-12-26 | 百度在线网络技术（北京）有限公司 | A kind of smart machine automated voice method of testing and device |
| CN108538296A (en) * | 2017-03-01 | 2018-09-14 | 广东神马搜索科技有限公司 | Speech recognition test method and test terminal |
| CN109754801A (en) * | 2019-01-15 | 2019-05-14 | 东莞松山湖国际机器人研究院有限公司 | A kind of voice interactive system and method based on gesture identification |
| CN109920429A (en) * | 2017-12-13 | 2019-06-21 | 上海擎感智能科技有限公司 | It is a kind of for vehicle-mounted voice recognition data processing method and system |
-
2019
- 2019-06-28 CN CN201910578108.1A patent/CN110264995A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1650272A (en) * | 2002-04-26 | 2005-08-03 | 飞思卡尔半导体公司 | Instruction cache and method for reducing memory conflicts |
| US9093071B2 (en) * | 2012-11-19 | 2015-07-28 | International Business Machines Corporation | Interleaving voice commands for electronic meetings |
| CN108538296A (en) * | 2017-03-01 | 2018-09-14 | 广东神马搜索科技有限公司 | Speech recognition test method and test terminal |
| CN107516510A (en) * | 2017-07-05 | 2017-12-26 | 百度在线网络技术（北京）有限公司 | A kind of smart machine automated voice method of testing and device |
| CN109920429A (en) * | 2017-12-13 | 2019-06-21 | 上海擎感智能科技有限公司 | It is a kind of for vehicle-mounted voice recognition data processing method and system |
| CN109754801A (en) * | 2019-01-15 | 2019-05-14 | 东莞松山湖国际机器人研究院有限公司 | A kind of voice interactive system and method based on gesture identification |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145737A (en) * | 2018-11-06 | 2020-05-12 | 中移（杭州）信息技术有限公司 | Voice test method and device and electronic equipment |
| CN111145737B (en) * | 2018-11-06 | 2022-07-01 | 中移（杭州）信息技术有限公司 | Voice test method and device and electronic equipment |
| CN112860582A (en) * | 2021-03-26 | 2021-05-28 | 成都启英泰伦科技有限公司 | Local voice recognition module production test method |
| CN113470618A (en) * | 2021-06-08 | 2021-10-01 | 阿波罗智联(北京)科技有限公司 | Wake-up test method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107516510B (en) | Automatic voice testing method and device for intelligent equipment | |
| US10529336B1 (en) | Filtering sensitive information | |
| CN110264995A (en) | The tone testing method, apparatus electronic equipment and readable storage medium storing program for executing of smart machine | |
| CN108538296A (en) | Speech recognition test method and test terminal | |
| CN110908913B (en) | Test method and device of return visit robot, electronic equipment and storage medium | |
| CN104765689B (en) | A kind of interface capability data supervise method and apparatus in real time | |
| US9361378B2 (en) | Determining reliability of online post | |
| CN107329899A (en) | A kind of application compatibility method of testing and device | |
| CN107239403A (en) | A kind of positioning problems method and apparatus | |
| CN108205476A (en) | A kind of method and device of multithreading daily record output | |
| TW202032466A (en) | User age prediction method, apparatus, and device | |
| CN110164474A (en) | Voice wakes up automated testing method and system | |
| CN109271453B (en) | Method and device for determining database capacity | |
| CN110727664A (en) | Method and device for executing target operation on public cloud data | |
| CN110335628A (en) | The tone testing method, apparatus and electronic equipment of smart machine | |
| US11308273B2 (en) | Prescan device activation prevention | |
| CN112309565A (en) | Method, apparatus, electronic device, and medium for matching drug information and disorder information | |
| CN112069796A (en) | Voice quality inspection method and device, electronic equipment and storage medium | |
| WO2017020794A1 (en) | Voice recognition method applicable to interactive system and device utilizing same | |
| CN110490101A (en) | A kind of picture intercept method, device and computer storage medium | |
| CN113555031B (en) | Training method and device of voice enhancement model, and voice enhancement method and device | |
| CN113609271B (en) | Knowledge graph-based service processing method, device, equipment and storage medium | |
| CN114968725A (en) | Task dependency relationship correction method and device, computer equipment and storage medium | |
| US10986230B1 (en) | Method and apparatus to capture, analyze, organize, and present support chat information | |
| CN104915352B (en) | A kind of method and apparatus that data correctness is handled under verification MapReduce environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190920 Assignee: Shanghai Xiaodu Technology Co.,Ltd. Assignor: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) Co.,Ltd. Contract record no.: X2021990000330 Denomination of invention: Voice test method, device, electronic device and readable storage medium of intelligent device License type: Common License Record date: 20210531 |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190920 |