CN105810222A - Defect detection method, device and system for audio equipment - Google Patents
Defect detection method, device and system for audio equipment Download PDFInfo
- Publication number
- CN105810222A CN105810222A CN201410840581.XA CN201410840581A CN105810222A CN 105810222 A CN105810222 A CN 105810222A CN 201410840581 A CN201410840581 A CN 201410840581A CN 105810222 A CN105810222 A CN 105810222A
- Authority
- CN
- China
- Prior art keywords
- audio frequency
- audio
- tonequality
- frequency apparatus
- data
- 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
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a defect detection method, device and system for audio equipment. The method can comprise the steps of recording source audio output by the audio equipment to obtain play audio of the audio equipment; pre-processing the play audio and detecting the tone quality to obtain target audio data; judging whether the target audio data satisfies a tone quality defect condition or not; if satisfying, determining the audio equipment as tone quality defect equipment, and determining the tone quality defect type of the audio equipment; and if not satisfying, determining the audio equipment as tone quality perfect equipment. By adopting the method, the device and the system, the tone quality defect equipment in the audio equipment production process can be detected, and the tone quality defect type of the audio equipment can be determined, so that the detection precision of the audio equipment is improved, and the accuracy of tone quality detection is improved.
Description
Technical field
The present invention relates to computer realm, particularly relate to the defect inspection method of a kind of audio frequency apparatus, Apparatus and system.
Background technology
Audio frequency apparatus is the general name to audio input/output device, audio frequency apparatus is the electronic equipment with audio frequency such as smart mobile phone, car navigation device, television set, notebook computer, panel computer such as, in the production process of audio frequency apparatus, the tonequality of audio frequency apparatus need to be detected.
Tradition tonequality detection is differentiated with artificial audition, along with technical development, available machines used replaces human ear measure and judge, audio frequency apparatus is placed in specific sound insulation environment by sound quality detection method of the prior art, the audio frequency of recording audio device plays, and is compared as entirety with source audio frequency by the audio frequency of recording, to judge the overall integrity that the audio frequency of audio frequency apparatus exports, but to concrete tonequality defect without further detection, the precision of audio frequency apparatus detection is low, and the accuracy rate of tonequality detection is low.
Summary of the invention
It is an object of the invention to provide the defect inspection method of a kind of audio frequency apparatus, Apparatus and system, concrete tonequality defect can be detected, improve the precision of audio frequency apparatus detection, add the accuracy rate of tonequality detection.
First aspect present invention provides the defect inspection method of a kind of audio frequency apparatus, including:
The source audio frequency of audio frequency apparatus output is recorded, obtains the broadcasting audio frequency of described audio frequency apparatus；
Described broadcasting audio frequency is carried out pretreatment and tonequality detection, obtains target audio data；
Judge whether described target audio data meet tonequality defect condition；
If described target audio data fit tonequality defect condition, described audio frequency apparatus is defined as tonequality defect equipment, and determines the tonequality defect type of described audio frequency apparatus；
If described target audio data do not meet tonequality defect condition, described audio frequency apparatus is defined as tonequality perfect facility.
Preferably, described target audio data include: the first voice data of obtaining through described pretreatment and detect the second audio data obtained through described tonequality；
Described described broadcasting audio frequency is carried out pretreatment and tonequality detection, obtain target audio data, including:
Described broadcasting audio conversion is turned to digital audio-frequency data, the digital audio-frequency data of described conversion is carried out preemphasis, obtain described first voice data；
Described first voice data is carried out framing windowing, calculates the short-time energy of each frame；
Short-time energy according to described each frame detects the audio endpoint of described first voice data；
By described audio endpoint, described first voice data is carried out K-means classification and segmentation, and carry out Fourier transformation, obtain described second audio data.
Preferably, described tonequality defect condition includes: described second audio data is inconsistent with described source audio frequency；Wherein, described second audio data includes multiple consonant frequency range；
If described target audio data fit tonequality defect condition, described audio frequency apparatus is defined as tonequality defect equipment, and determines the tonequality defect type of described audio frequency apparatus, including:
In the plurality of consonant frequency range, if it is inconsistent with described source audio frequency to there is at least one consonant frequency range, it is determined that described target audio data fit tonequality defect condition, described tonequality defect type includes: staccato, noise or aphonia.
Preferably, the described source audio frequency to audio frequency apparatus output is recorded, and obtains the broadcasting audio frequency of described audio frequency apparatus, including:
Described source audio frequency play by control signal box, and controls the described signal box voice-grade channel to be detected by described source audio frequency output to described audio frequency apparatus；
By the audio frequency that the voice-grade channel to be detected of audio frequency apparatus described in microphone records exports, obtain the broadcasting audio frequency of described audio frequency apparatus.
Second aspect present invention provides the defect detecting device of a kind of audio frequency apparatus, including:
Recording module, for the source audio frequency of audio frequency apparatus output is recorded, obtains the broadcasting audio frequency of described audio frequency apparatus；
Processing module, for described broadcasting audio frequency carries out pretreatment and tonequality detection, obtains target audio data；
Judge module, is used for judging whether described target audio data meet tonequality defect condition；
First determines module, for when the judged result of described judge module is for being, it is determined that the tonequality defect type of described audio frequency apparatus, and described audio frequency apparatus is defined as tonequality defect equipment；
Second determines module, for when the judged result of described judge module is no, described audio frequency apparatus being defined as tonequality perfect facility.
Preferably, described target audio data include: the first voice data of obtaining through described pretreatment and detect the second audio data obtained through described tonequality；
Described processing module includes:
First processing unit, for described broadcasting audio conversion is turned to digital audio-frequency data, carries out preemphasis to the digital audio-frequency data of described conversion, obtains described first voice data；
Computing unit, for described first voice data is carried out framing windowing, calculates the short-time energy of each frame；
End-point detection unit, detects the audio endpoint of described first voice data for the short-time energy according to described each frame；
Second processing unit, for described first voice data being carried out K-means classification and segmentation by described audio endpoint, and carries out Fourier transformation, obtains described second audio data.
Preferably, described tonequality defect condition includes: described second audio data is inconsistent with described source audio frequency；Wherein, described second audio data includes multiple consonant frequency range；
Described first determine module specifically for: in the plurality of consonant frequency range, if it is inconsistent to there is at least one consonant frequency range and described source audio frequency, it is determined that the judged result of described judge module is yes, and described tonequality defect type includes: staccato, noise or aphonia.
Preferably, described recording module includes:
Control broadcasting unit, play described source audio frequency for control signal box, and control the described signal box voice-grade channel to be detected by described source audio frequency output to described audio frequency apparatus；
Recording elements, for the audio frequency exported by the voice-grade channel to be detected of audio frequency apparatus described in microphone records, obtains the broadcasting audio frequency of described audio frequency apparatus.
Third aspect present invention provides the defect detecting system of a kind of audio frequency apparatus, including audio frequency apparatus, further also includes: detection equipment；Described detection equipment, the device as described in second aspect；Described detection equipment, for detecting the audio frequency of described audio frequency apparatus output.
Preferably, described system also includes: signal box；Described signal box is connected with described audio frequency apparatus, and described detection equipment communicates to connect with described signal box；
Described detection equipment, is additionally operable to control described signal box broadcast source audio frequency, and controls the described signal box voice-grade channel to be detected by described source audio frequency output to described audio frequency apparatus.
Enforcement the method have the advantages that
The source audio frequency of audio frequency apparatus output can be recorded by the embodiment of the present invention, obtain the broadcasting audio frequency of audio frequency apparatus, and then carry out pretreatment and tonequality detection to playing audio frequency, obtain target audio data, then judge whether target audio data meet tonequality defect condition, if meeting tonequality defect condition, audio frequency apparatus is defined as tonequality defect equipment, and determine and the tonequality defect type of audio frequency apparatus if not meeting tonequality defect condition, audio frequency apparatus is defined as tonequality perfect facility.By the embodiment of the present invention, the tonequality defect equipment occurred in audio frequency apparatus production process can be detected, and can determine that the tonequality defect type of audio frequency apparatus, improve the precision of audio frequency apparatus detection, add the accuracy rate of tonequality detection.
Further, detection equipment of the prior art need to set sound insulation environment, therefore need to customize specific sound proof box, opening/closing sound proof box need to be played to allow audio frequency apparatus entry/exit, reduce the efficiency of audio frequency apparatus detection, and to various sizes of audio frequency apparatus, the size of sound proof box is inconsistent, for the audio frequency apparatus that size is big, space bigger on production line need to be taken.And in the embodiment of the present invention, it is not necessary to set sound insulation environment, directly can carry out tonequality detection on the production line of audio frequency apparatus, thus the efficiency of audio frequency apparatus detection can be improved, and be applicable on different audio frequency apparatus production line, improve the suitability of audio frequency apparatus detection.
Accompanying drawing explanation
The flow chart of the defect inspection method of a kind of audio frequency apparatus that Fig. 1 provides for the embodiment of the present invention；
The particular flow sheet of the sound quality detection method that Fig. 2 provides for the embodiment of the present invention；
The defects detection schematic diagram of the audio frequency apparatus that Fig. 3 provides for the embodiment of the present invention；
The structural representation of the defect detecting device of a kind of audio frequency apparatus that Fig. 4 provides for the embodiment of the present invention；
The structural representation of the processing module that Fig. 5 provides for the embodiment of the present invention；
The structural representation of the defect detecting system of a kind of audio frequency apparatus that Fig. 6 provides for the embodiment of the present invention.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein is only in order to explain the present invention, is not intended to limit the present invention.
The embodiment of the present invention provides the defect inspection method of a kind of audio frequency apparatus, Apparatus and system, wherein, audio frequency apparatus is the general name to audio input/output device, and audio frequency apparatus is the electronic equipment with audio frequency such as smart mobile phone, car navigation device, television set, notebook computer, panel computer such as.The defects detection scheme of audio frequency apparatus that the embodiment of the present invention provides can be applicable to before audio frequency apparatus dispatches from the factory, tonequality defects detection link on a production line, pass through the embodiment of the present invention, the tonequality defect equipment occurred in audio frequency apparatus production process can be detected, and can determine that the tonequality defect type of audio frequency apparatus, improve the precision of audio frequency apparatus detection, add the accuracy rate of tonequality detection.
Further, detection equipment of the prior art need to set sound insulation environment, therefore need to customize specific sound proof box, opening/closing sound proof box need to be played to allow audio frequency apparatus entry/exit, reduce the efficiency of audio frequency apparatus detection, and to various sizes of audio frequency apparatus, the size of sound proof box is inconsistent, for the audio frequency apparatus that size is big, space bigger on production line need to be taken.And in the embodiment of the present invention, it is not necessary to set sound insulation environment, directly can carry out tonequality detection on the production line of audio frequency apparatus, thus the efficiency of audio frequency apparatus detection can be improved, and be applicable on different audio frequency apparatus production line, improve the suitability of audio frequency apparatus detection.Following described in detail by specific embodiment.
Referring to Fig. 1, it it is the flow chart of the defect inspection method of a kind of audio frequency apparatus that the embodiment of the present invention provides, the embodiment of the present invention is described with detection equipment for executive agent, as it is shown in figure 1, the defect inspection method of the audio frequency apparatus of embodiment of the present invention offer can include step: S101～S105.
S101, records the source audio frequency of audio frequency apparatus output, obtains the broadcasting audio frequency of audio frequency apparatus.
As the optional embodiment of one, can be recorded by the source audio frequency that audio frequency apparatus is exported by the recording modules such as mike, thus the broadcasting audio frequency of audio frequency apparatus can be obtained.
Further, the source audio frequency of audio frequency apparatus output being recorded, the broadcasting audio frequency obtaining audio frequency apparatus specifically may include that
Control signal box broadcast source audio frequency, and control signal box is by the voice-grade channel to be detected of source audio frequency output to audio frequency apparatus；
By the audio frequency that the voice-grade channel to be detected of microphone records audio frequency apparatus exports, obtain the broadcasting audio frequency of audio frequency apparatus.
In implementing, the tonequality detection on the production line of audio frequency apparatus, source audio frequency can be stored at signal box in advance, wherein, source audio frequency can be the audio frequency of predeterminated frequency, concrete, and source audio frequency can be the audio frequency including multiple different frequency range.Further, every audio frequency apparatus one signal box of pairing on production line, when detecting that audio frequency apparatus passes through conveyer belt arrival detection region, detection equipment can send to signal box and play indication signal, thus signal box can when receiving broadcasting indication signal, signal box broadcast source audio frequency, source audio frequency also can be exported the voice-grade channel to be detected to audio frequency apparatus by control signal box by detection equipment.
Further alternative, audio frequency apparatus can include multiple voice-grade channel to be detected, wherein, play indication signal and may further indicate that specifically by source audio frequency exports which voice-grade channel to be detected to audio frequency apparatus, thus can realize any one voice-grade channel to be detected of audio frequency apparatus is detected.
Concrete, source audio frequency can be exported the voice-grade channel to be detected to audio frequency apparatus by control signal box by detection equipment, the then voice-grade channel output source audio frequency to be detected of audio frequency apparatus, the audio frequency that detection equipment can be exported by the voice-grade channel to be detected of microphone records audio frequency apparatus, and then the broadcasting audio frequency of audio frequency apparatus can be obtained.
Further alternative, referring to Fig. 3, for the defects detection schematic diagram of the audio frequency apparatus that the embodiment of the present invention provides, as it can be seen, 300 is the conveyer belt on production line, conveyer belt 300 has N platform audio frequency apparatus, wherein N is the positive integer more than 1, concrete, 310 ... 31N is audio frequency apparatus.Every audio frequency apparatus one signal box of pairing, then total N number of signal box, concrete, and 320 ... 32N is signal box.330 is detection equipment, and detection equipment 330 also includes mike 3301, concrete, and mike 3301 can include left mike and right mike, it is also possible to only have a mike, specifically not by the restriction of the embodiment of the present invention.Detection equipment 330 can communicate wirelessly with signal box 32N.Signal box 32N and audio frequency apparatus 31N passes through wired connection.
Detection equipment 330 is when detecting that audio frequency apparatus 31N arrives detection region by conveyer belt 330, detection equipment 330 can send to signal box 32N and play indication signal, thus signal box 32N can when receiving broadcasting indication signal, signal box 32N broadcast source audio frequency, source audio frequency also can be exported the voice-grade channel to be detected to audio frequency apparatus 31N by control signal box 32N by detection equipment 330, and then the audio frequency that detection equipment 330 can be exported by the voice-grade channel to be detected of mike 3301 recording audio equipment 31N, and then the audio frequency recorded is detected.Further, can pass through whether the various ways such as infrared signal, image procossing detection audio frequency apparatus enters detection region, specifically not by the restriction of the embodiment of the present invention.
S102, carries out pretreatment and tonequality detection to playing audio frequency, obtains target audio data.
As the optional embodiment of one, detection equipment, after the broadcasting audio frequency obtaining audio frequency apparatus, carries out pretreatment and tonequality detection to playing audio frequency, obtains target audio data.Wherein, target audio data include: the first voice data of obtaining through pretreatment and detect the second audio data obtained through tonequality.
Further, referring to Fig. 2, particular flow sheet for the sound quality detection method that the embodiment of the present invention provides, concrete, embodiment shown in Fig. 2 is the concrete steps of step S102 in the embodiment shown in Fig. 1, as in figure 2 it is shown, the concrete steps of the sound quality detection method of embodiment of the present invention offer include: S201～S204.
S201, turns to digital audio-frequency data by broadcasting audio conversion, the digital audio-frequency data converted is carried out preemphasis, obtains the first voice data.
S202, carries out framing windowing to the first voice data, calculates the short-time energy of each frame.
S203, detects the audio endpoint of the first voice data according to the short-time energy of each frame.
S204, is carried out K-means classification and segmentation by audio endpoint, and carries out Fourier transformation, obtain second audio data the first voice data.
In implementing, the source audio frequency of audio frequency apparatus output is analogue signal, the broadcasting audio frequency of the audio frequency apparatus that the source audio frequency of recording audio equipment output obtains is analogue signal, A/D (AnalogtoDigitalConverter can be passed through, analog-digital converter) convert analog signals into digital signal, then by A/D, broadcasting audio conversion can be changed to digital audio-frequency data.The digital audio-frequency data converted is carried out preemphasis, specifically such as: high-frequency signal is increased the weight of, strengthens sound high frequency resolution, the digital audio-frequency data waveform standardization that maybe will convert so that the boundary of voiced portions and unvoiced section becomes apparent from.The first voice data can be obtained after the digital audio-frequency data converted is carried out preemphasis.
Further, acoustical signal has the feature of short-term stationarity, but all there is interference in too long of acoustical signal or too short acoustical signal, the broadcasting audio frequency collected is discrete voice signal, each centrifugal pump likely changes from positive to negative, and interference is big, it is therefore desirable to carry out framing windowing, such as desirable frame length 10～30ms etc., specifically not by the restriction of the embodiment of the present invention.Further, the short-time energy of each frame also can be calculated, concrete, can to squared after the amplitude weighting of each frame and obtain the short-time energy of each frame.
Further, can detecting the audio endpoint of the first voice data according to the short-time energy of each frame, sound audio frequency and noiseless audio frequency amplitude of waveform in short-time energy there are differences, and then audio endpoint can be detected according to the short-time energy of each frame.
Concrete, by audio endpoint, the first voice data can be carried out K-means classification, first voice data is the audio frequency that there is acoustical signal, can pass through amplitude is detection audible signal or un-voiced signal from n class to the process that 2 classes progressively converge, the sorting algorithm of the available K-means of each of which time circulation, wherein, K-means algorithm is using Euclidean distance as similarity measure, it is to seek corresponding a certain initial cluster center vector V optimal classification, making evaluation index J minimum, algorithm adopts error sum of squares criterion function as clustering criteria function.
Further, audio endpoint can determine that start position and the endpoint location of the first voice data sound intermediate frequency, therefore by audio endpoint, the first voice data can be carried out segmentation, for instance fixing audio band can be set and carry out segmentation.The waveform that also can intercept different time different frequency carries out Fourier transformation, from time domain waveform to frequency-domain waveform, obtains second audio data.
S103, it is judged that whether target audio data meet tonequality defect condition.If the judged result of step S103 is yes, perform step S104, if the judgement structure of step S103 is no, perform step S105.
As the optional embodiment of one, can determine whether whether target audio data meet tonequality defect condition, wherein, tonequality defect condition comprises the steps that second audio data and source audio frequency are inconsistent.In implementing, second audio data can include multiple consonant frequency range, can each consonant frequency range be contrasted one by one with diaphone frequency range in the audio frequency of source, it may be judged whether consistent.
S104, is defined as audio frequency apparatus tonequality defect equipment, and determines the tonequality defect type of audio frequency apparatus.
As the optional embodiment of one, if target audio data fit tonequality defect condition, audio frequency apparatus is defined as tonequality defect equipment, and determines the tonequality defect type of audio frequency apparatus.In implementing, in multiple consonant frequency ranges, if it is inconsistent with source audio frequency to there is at least one consonant frequency range, it is determined that target audio data fit tonequality defect condition, tonequality defect type includes: staccato, noise or aphonia.Further alternative, tonequality defect type is not limited to the above-mentioned type, it is also possible to for other tonequality defect types, specifically not by the restriction of the embodiment of the present invention.
Further, if in a certain consonant frequency range, target audio data are absent from voice data, and source audio frequency exists voice data at this audio section, then can determine that tonequality defect type is staccato.If target audio data are absent from voice data in the sub-audio section of continuous print at least 2, and there is voice data in the audio frequency of source, then can determine that tonequality defect type is aphonia.If in a certain consonant frequency range, there is voice data in target audio data, and source audio frequency exists voice data at this audio section, but target audio data are inconsistent at this audio section and source voice data, then can determine that tonequality defect type is noise.
S105, is defined as tonequality perfect facility by audio frequency apparatus.
As the optional embodiment of one, if target audio data fit tonequality defect condition, audio frequency apparatus is defined as tonequality perfect facility.
Further alternative, it is also possible to the tonequality examining report of output audio frequency apparatus.Concrete, the tonequality examining report of audio frequency apparatus can be generated, including: the mark of audio frequency apparatus, the voice-grade channel to be detected of audio frequency apparatus, voice-grade channel to be detected tonequality defect type etc., specifically not by the restriction of the embodiment of the present invention.
The embodiment of the present invention provides the defect inspection method of a kind of audio frequency apparatus, the source audio frequency of audio frequency apparatus output can be recorded, obtain the broadcasting audio frequency of audio frequency apparatus, and then carry out pretreatment and tonequality detection to playing audio frequency, obtain target audio data, judge whether target audio data meet tonequality defect condition again, if meeting tonequality defect condition, audio frequency apparatus is defined as tonequality defect equipment, and determine the tonequality defect type of audio frequency apparatus, if not meeting tonequality defect condition, audio frequency apparatus is defined as tonequality perfect facility.By the embodiment of the present invention, the tonequality defect equipment occurred in audio frequency apparatus production process can be detected, and can determine that the tonequality defect type of audio frequency apparatus, improve the precision of audio frequency apparatus detection, add the accuracy rate of tonequality detection.
Further, detection equipment of the prior art need to set sound insulation environment, therefore need to customize specific sound proof box, opening/closing sound proof box need to be played to allow audio frequency apparatus entry/exit, reduce the efficiency of audio frequency apparatus detection, and to various sizes of audio frequency apparatus, the size of sound proof box is inconsistent, for the audio frequency apparatus that size is big, space bigger on production line need to be taken.And in the embodiment of the present invention, without setting sound insulation environment, directly can carry out tonequality detection on the production line of audio frequency apparatus, the embodiment of the present invention can adopt the source audio frequency of predeterminated frequency, and then the audio frequency of characteristic frequency can be detected, thus the efficiency of audio frequency apparatus detection can be improved, and it is applicable on different audio frequency apparatus production line, improves the suitability of audio frequency apparatus detection.
Below in conjunction with accompanying drawing 4 and accompanying drawing 5, the defect detecting device of the audio frequency apparatus that the embodiment of the present invention provides is described in detail, it should be noted that, device shown in accompanying drawing 4, for the method performing Fig. 1 of the present invention and embodiment illustrated in fig. 2, for the ease of illustrating, illustrate only the part relevant to the embodiment of the present invention, concrete ins and outs do not disclose, and refer to the embodiment shown in embodiment of the present invention Fig. 1 and Fig. 2.
Refer to Fig. 4, for the structural representation of defect detecting device of a kind of audio frequency apparatus that the embodiment of the present invention provides.As shown in Figure 4, the defect detecting device of audio frequency apparatus that the embodiment of the present invention provides comprises the steps that recording module 41, processing module 42, first determines that module 43 and second determines module 44.
Recording module 41, for the source audio frequency of audio frequency apparatus output is recorded, obtains the broadcasting audio frequency of audio frequency apparatus.
As the optional embodiment of one, recording module 41 can be recorded by the source audio frequency that audio frequency apparatus is exported by the recording modules such as mike, thus the broadcasting audio frequency of audio frequency apparatus can be obtained.In implementing, recording module 41 may include that control broadcasting unit and recording elements, wherein:
Controlling broadcasting unit, for control signal box broadcast source audio frequency, and control signal box is by the voice-grade channel to be detected of source audio frequency output to audio frequency apparatus；
Recording elements, for the audio frequency exported by the voice-grade channel to be detected of microphone records audio frequency apparatus, obtains the broadcasting audio frequency of audio frequency apparatus.
In implementing, the tonequality detection on the production line of audio frequency apparatus, source audio frequency can be stored at signal box in advance, wherein, source audio frequency can be the audio frequency of predeterminated frequency, concrete, and source audio frequency can be the audio frequency including multiple different frequency range.Further, audio frequency apparatus one signal box of coupling on production line, when detecting that audio frequency apparatus passes through conveyer belt arrival detection region, can send to signal box and play indication signal, thus signal box can when receiving broadcasting indication signal, signal box broadcast source audio frequency, also can export the voice-grade channel to be detected to audio frequency apparatus by source audio frequency by control signal box.
Further alternative, audio frequency apparatus can include multiple voice-grade channel to be detected, wherein, play indication signal and may further indicate that specifically by source audio frequency exports which voice-grade channel to be detected to audio frequency apparatus, thus can realize any one voice-grade channel to be detected of audio frequency apparatus is detected.
Concrete, control broadcasting unit and control signal box source audio frequency can be exported the voice-grade channel to be detected to audio frequency apparatus, the then voice-grade channel output source audio frequency to be detected of audio frequency apparatus, the audio frequency that recording elements can be exported by the voice-grade channel to be detected of microphone records audio frequency apparatus, and then the broadcasting audio frequency of audio frequency apparatus can be obtained.
Processing module 42, for broadcasting audio frequency carries out pretreatment and tonequality detection, obtains target audio data.
As the optional embodiment of one, the broadcasting audio frequency that recording module 41 obtains can be carried out pretreatment and tonequality detection by processing module 42, obtains target audio data.Wherein, target audio data include: the first voice data of obtaining through pretreatment and detect the second audio data obtained through tonequality.
Further alternative, referring to Fig. 5, for the structural representation of processing module that the embodiment of the present invention provides, as it is shown in figure 5, the processing module that the embodiment of the present invention provides may include that the first processing unit 51, computing unit 52, end-point detection unit 53 and the second processing unit 54.
First processing unit 51, for broadcasting audio conversion is turned to digital audio-frequency data, carries out preemphasis to the digital audio-frequency data converted, obtains the first voice data；
Computing unit 52, for the first voice data is carried out framing windowing, calculates the short-time energy of each frame；
End-point detection unit 53, for detecting the audio endpoint of the first voice data according to the short-time energy of each frame；
Second processing unit 54, for the first voice data carrying out K-means classification and segmentation by audio endpoint, and carries out Fourier transformation, obtains second audio data.
In implementing, the source audio frequency of audio frequency apparatus output is analogue signal, the broadcasting audio frequency of the audio frequency apparatus that the source audio frequency of recording audio equipment output obtains is analogue signal, can convert analog signals into digital signal by A/D, then broadcasting audio conversion can be changed to digital audio-frequency data by A/D by the first processing unit 51.The digital audio-frequency data converted is carried out preemphasis by the first processing unit 51, specifically such as: high-frequency signal is increased the weight of, strengthen sound high frequency resolution, the digital audio-frequency data waveform standardization that maybe will convert so that the boundary of voiced portions and unvoiced section becomes apparent from.The first voice data can be obtained after the digital audio-frequency data converted is carried out preemphasis.
Further, acoustical signal has the feature of short-term stationarity, but all there is interference in too long of acoustical signal or too short acoustical signal, the broadcasting audio frequency collected is discrete voice signal, each centrifugal pump likely converts from positive to negative, and interference is big, it is therefore desirable to carry out framing windowing, such as desirable frame length 10～30ms etc., specifically not by the restriction of the embodiment of the present invention.Further, computing unit 52 also can calculate the short-time energy of each frame, concrete, can to squared after the amplitude weighting of each frame and obtain the short-time energy of each frame.
Further, end-point detection unit 53 can detect the audio endpoint of the first voice data according to the short-time energy of each frame, sound audio frequency and noiseless audio frequency amplitude of waveform in short-time energy there are differences, and then audio endpoint can be detected according to the short-time energy of each frame.
Concrete, first voice data can be carried out K-means classification by audio endpoint by the second processing unit 54, first voice data is the audio frequency that there is acoustical signal, can pass through amplitude is detection audible signal or un-voiced signal from n class to the process that 2 classes progressively converge, the sorting algorithm of the available K-means of each of which time circulation, wherein, K-means algorithm is using Euclidean distance as similarity measure, it is to seek corresponding a certain initial cluster center vector V optimal classification, making evaluation index J minimum, algorithm adopts error sum of squares criterion function as clustering criteria function.
Further, audio endpoint can determine that start position and the endpoint location of the first voice data sound intermediate frequency, therefore by audio endpoint, the first voice data can be carried out segmentation, for instance fixing audio band can be set and carry out segmentation.The waveform that also can intercept different time different frequency carries out Fourier transformation, from time domain waveform to frequency-domain waveform, obtains second audio data.
Judge module 43, is used for judging whether target audio data meet tonequality defect condition.
As the optional embodiment of one, it is judged that module 43 can determine whether whether target audio data meet tonequality defect condition, wherein, tonequality defect condition comprises the steps that second audio data and source audio frequency are inconsistent.In implementing, second audio data can include multiple consonant frequency range, can each consonant frequency range be contrasted one by one with diaphone frequency range in the audio frequency of source, it may be judged whether consistent.
First determines module 44, for when the judged result of judge module 43 is for being, it is determined that the tonequality defect type of audio frequency apparatus, and audio frequency apparatus is defined as tonequality defect equipment.
As the optional embodiment of one, if target audio data fit tonequality defect condition, audio frequency apparatus is defined as tonequality defect equipment, and determines the tonequality defect type of audio frequency apparatus.In implementing, first determine module 44 specifically for: in multiple consonant frequency ranges, if it is inconsistent to there is at least one consonant frequency range and source audio frequency, it is determined that the judged result of judge module 43 is yes, and tonequality defect type includes: staccato, noise or aphonia.Further alternative, tonequality defect type is not limited to above-mentioned, it is also possible to for other tonequality defect types, specifically not by the restriction of the embodiment of the present invention.
Further, if in a certain consonant frequency range, target audio data are absent from voice data, and source audio frequency exists voice data at this audio section, then can determine that tonequality defect type is minor.If target audio data are absent from voice data in the sub-audio section of continuous print at least 2, and there is voice data in the audio frequency of source, then can determine that tonequality defect type is aphonia.If in a certain consonant frequency range, there is voice data in target audio data, and source audio frequency exists voice data at this audio section, but target audio data are inconsistent at this audio section and source voice data, then can determine that tonequality defect type is noise.
Second determines module 45, for when the judged result of judge module 43 is no, audio frequency apparatus being defined as tonequality perfect facility.
As the optional embodiment of one, if the judged result of judge module 43 is no, then target audio data fit tonequality defect condition, then second determines that audio frequency apparatus can be defined as tonequality perfect facility by module 45.
Further alternative, it is also possible to the tonequality examining report of output audio frequency apparatus.Concrete, the tonequality examining report of audio frequency apparatus can be generated, including the voice-grade channel to be detected of: the mark of audio frequency apparatus, audio frequency apparatus, tonequality defect type of voice-grade channel to be detected etc., specifically not by the restriction of the embodiment of the present invention.
The embodiment of the present invention provides the defect detecting device of a kind of audio frequency apparatus, the source audio frequency of audio frequency apparatus output can be recorded by recording module, obtain the broadcasting audio frequency of audio frequency apparatus, processing module can carry out pretreatment and tonequality detection to playing audio frequency, obtain target audio data, judge module can determine whether whether target audio data meet tonequality defect condition, if the judged result of judge module is yes, first determines that audio frequency apparatus can be defined as tonequality defect equipment by module, and determine the tonequality defect type of audio frequency apparatus, if the judged result of judge module is no, second determines that audio frequency apparatus can be defined as tonequality perfect facility by module.By the embodiment of the present invention, the tonequality defect equipment occurred in audio frequency apparatus production process can be detected, and can determine that the tonequality defect type of audio frequency apparatus, improve the precision of audio frequency apparatus detection, add the accuracy rate of tonequality detection.
Further, detection equipment of the prior art need to set sound insulation environment, therefore need to customize specific sound proof box, opening/closing sound proof box need to be played to allow audio frequency apparatus entry/exit, reduce the efficiency of audio frequency apparatus detection, and to various sizes of audio frequency apparatus, the size of sound proof box is inconsistent, for the audio frequency apparatus that size is big, space bigger on production line need to be taken.And in the embodiment of the present invention, without setting sound insulation environment, directly can carry out tonequality detection on the production line of audio frequency apparatus, the embodiment of the present invention can adopt the source audio frequency of predeterminated frequency, and then the audio frequency of characteristic frequency can be detected, thus the efficiency of audio frequency apparatus detection can be improved, and it is applicable on different audio frequency apparatus production line, improves the suitability of audio frequency apparatus detection.
The embodiment of the invention also discloses a kind of detection equipment, concrete, the detection equipment that the embodiment of the present invention provides includes the device shown in Fig. 4 and Fig. 5, and the 26S Proteasome Structure and Function of this detection equipment referring to the associated description of Fig. 4 and embodiment illustrated in fig. 5, can not tire out at this and state.It should be noted that the detection equipment of the present embodiment can be applicable in said method.
Referring to Fig. 6, the structural representation of defect detecting system for a kind of audio frequency apparatus that the embodiment of the present invention provides, as shown in the figure, the defect detecting system of the audio frequency apparatus that the embodiment of the present invention provides includes audio frequency apparatus 61, wherein, the audio frequency apparatus such as electronic equipment with audio frequency such as smart mobile phone, car navigation device, television set, notebook computer, panel computer.Further, it is also possible to include detection equipment 62, detection equipment 62 is for detecting the audio frequency of audio frequency apparatus 61 output.Wherein, detection equipment 62 includes the device shown in Fig. 4 and Fig. 5.
Further, the defect detecting system of the audio frequency apparatus that the embodiment of the present invention provides may also include that signal box 63.Wherein, signal box 63 is connected with audio frequency apparatus 61, and detection equipment 62 and signal box 63 communicate to connect.Concrete, detect equipment 62, be additionally operable to control signal box 63 broadcast source audio frequency, and control signal box 63 is by the voice-grade channel to be detected of source audio frequency output to audio frequency apparatus 61.Further, detection equipment 62 can include mike and then the audio frequency that detection equipment 62 can be exported by the voice-grade channel to be detected of microphone records audio frequency apparatus, and then can the audio frequency of audio frequency apparatus 61 output be detected.
Embodiment described above only have expressed the several embodiments of the present invention, and it describes comparatively concrete and detailed, but therefore can not be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that, for the person of ordinary skill of the art, without departing from the inventive concept of the premise, it is also possible to making some deformation and improvement, these broadly fall into protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. the defect inspection method of an audio frequency apparatus, it is characterised in that described method includes:
The source audio frequency of audio frequency apparatus output is recorded, obtains the broadcasting audio frequency of described audio frequency apparatus；
Described broadcasting audio frequency is carried out pretreatment and tonequality detection, obtains target audio data；
Judge whether described target audio data meet tonequality defect condition；
If described target audio data fit tonequality defect condition, described audio frequency apparatus is defined as tonequality defect equipment, and determines the tonequality defect type of described audio frequency apparatus；
If described target audio data do not meet tonequality defect condition, described audio frequency apparatus is defined as tonequality perfect facility.
2. the method for claim 1, it is characterised in that described target audio data include: the first voice data of obtaining through described pretreatment and detect the second audio data obtained through described tonequality；
Described described broadcasting audio frequency is carried out pretreatment and tonequality detection, obtain target audio data, including:
Described broadcasting audio conversion is turned to digital audio-frequency data, the digital audio-frequency data of described conversion is carried out preemphasis, obtain described first voice data；
Described first voice data is carried out framing windowing, calculates the short-time energy of each frame；
Short-time energy according to described each frame detects the audio endpoint of described first voice data；
By described audio endpoint, described first voice data is carried out K-means classification and segmentation, and carry out Fourier transformation, obtain described second audio data.
3. method as claimed in claim 2, it is characterised in that described tonequality defect condition includes: described second audio data is inconsistent with described source audio frequency；Wherein, described second audio data includes multiple consonant frequency range；
If described target audio data fit tonequality defect condition, described audio frequency apparatus is defined as tonequality defect equipment, and determines the tonequality defect type of described audio frequency apparatus, including:
In the plurality of consonant frequency range, if it is inconsistent with described source audio frequency to there is at least one consonant frequency range, it is determined that described target audio data fit tonequality defect condition, described tonequality defect type includes: staccato, noise or aphonia.
4. the method for claim 1, it is characterised in that the described source audio frequency to audio frequency apparatus output is recorded, and obtains the broadcasting audio frequency of described audio frequency apparatus, including:
Described source audio frequency play by control signal box, and controls the described signal box voice-grade channel to be detected by described source audio frequency output to described audio frequency apparatus；
By the audio frequency that the voice-grade channel to be detected of audio frequency apparatus described in microphone records exports, obtain the broadcasting audio frequency of described audio frequency apparatus.
5. the defect detecting device of an audio frequency apparatus, it is characterised in that described device includes:
Recording module, for the source audio frequency of audio frequency apparatus output is recorded, obtains the broadcasting audio frequency of described audio frequency apparatus；
Processing module, for described broadcasting audio frequency carries out pretreatment and tonequality detection, obtains target audio data；
Judge module, is used for judging whether described target audio data meet tonequality defect condition；
First determines module, for when the judged result of described judge module is for being, it is determined that the tonequality defect type of described audio frequency apparatus, and described audio frequency apparatus is defined as tonequality defect equipment；
Second determines module, for when the judged result of described judge module is no, described audio frequency apparatus being defined as tonequality perfect facility.
6. device as claimed in claim 5, it is characterised in that described target audio data include: the first voice data of obtaining through described pretreatment and detect the second audio data obtained through described tonequality；
Described processing module includes:
First processing unit, for described broadcasting audio conversion is turned to digital audio-frequency data, carries out preemphasis to the digital audio-frequency data of described conversion, obtains described first voice data；
Computing unit, for described first voice data is carried out framing windowing, calculates the short-time energy of each frame；
End-point detection unit, detects the audio endpoint of described first voice data for the short-time energy according to described each frame；
Second processing unit, for described first voice data being carried out K-means classification and segmentation by described audio endpoint, and carries out Fourier transformation, obtains described second audio data.
7. device as claimed in claim 6, it is characterised in that described tonequality defect condition includes: described second audio data is inconsistent with described source audio frequency；Wherein, described second audio data includes multiple consonant frequency range；
Described first determine module specifically for: in the plurality of consonant frequency range, if it is inconsistent to there is at least one consonant frequency range and described source audio frequency, it is determined that the judged result of described judge module is yes, and described tonequality defect type includes: staccato, noise or aphonia.
8. device as claimed in claim 5, it is characterised in that described recording module includes:
Control broadcasting unit, play described source audio frequency for control signal box, and control the described signal box voice-grade channel to be detected by described source audio frequency output to described audio frequency apparatus；
Recording elements, for the audio frequency exported by the voice-grade channel to be detected of audio frequency apparatus described in microphone records, obtains the broadcasting audio frequency of described audio frequency apparatus.
9. a defect detecting system for audio frequency apparatus, including audio frequency apparatus, it is characterised in that also include: detection equipment；Described detection equipment, the device as described in as arbitrary in claim 5～8；
Described detection equipment, for detecting the audio frequency of described audio frequency apparatus output.
10. system as claimed in claim 9, it is characterised in that described system also includes: signal box；Described signal box is connected with described audio frequency apparatus, and described detection equipment communicates to connect with described signal box；
Described detection equipment, is additionally operable to control described signal box broadcast source audio frequency, and controls the described signal box voice-grade channel to be detected by described source audio frequency output to described audio frequency apparatus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410840581.XA CN105810222A (en) | 2014-12-30 | 2014-12-30 | Defect detection method, device and system for audio equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410840581.XA CN105810222A (en) | 2014-12-30 | 2014-12-30 | Defect detection method, device and system for audio equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105810222A true CN105810222A (en) | 2016-07-27 |
Family
ID=56980941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410840581.XA Pending CN105810222A (en) | 2014-12-30 | 2014-12-30 | Defect detection method, device and system for audio equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105810222A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106323330A (en) * | 2016-08-15 | 2017-01-11 | 中国科学技术大学苏州研究院 | Non-contact-type step count method based on WiFi motion recognition system |
| CN106658332A (en) * | 2016-12-30 | 2017-05-10 | 上海华东电信研究院 | Acoustic automatic testing device and system |
| CN111314536A (en) * | 2020-01-21 | 2020-06-19 | 上海悦易网络信息技术有限公司 | Method and equipment for detecting listening module of terminal equipment |
| US20220130411A1 (en) * | 2020-10-23 | 2022-04-28 | Institute For Information Industry | Defect-detecting device and defect-detecting method for an audio device |
| CN115616082A (en) * | 2022-12-14 | 2023-01-17 | 杭州兆华电子股份有限公司 | Keyboard defect analysis method based on noise detection |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1758226A (en) * | 2004-10-09 | 2006-04-12 | 鸿富锦精密工业（深圳）有限公司 | The method of the automatic detection computations machine of loop-type audio frequency apparatus playing function |
| CN101729635A (en) * | 2009-12-30 | 2010-06-09 | 中兴通讯股份有限公司 | Method and device for testing audio loop of communication terminal |
| CN102568470A (en) * | 2012-01-11 | 2012-07-11 | 广州酷狗计算机科技有限公司 | Acoustic fidelity identification method and system for audio files |
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN103167391A (en) * | 2011-12-12 | 2013-06-19 | 英业达股份有限公司 | Audio test system and audio test method for to-be-tested device |
| CN103578466A (en) * | 2013-11-11 | 2014-02-12 | 清华大学 | Voice and non-voice detection method based on fractional order Fourier transformation |
| CN104050964A (en) * | 2014-06-17 | 2014-09-17 | 公安部第三研究所 | Audio signal reduction degree detecting method and system |
| CN104244161A (en) * | 2014-09-17 | 2014-12-24 | 苏州酷果信息技术有限公司 | Method and device for testing equipment with voice playing function and voice recording function |
-
2014
- 2014-12-30 CN CN201410840581.XA patent/CN105810222A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1758226A (en) * | 2004-10-09 | 2006-04-12 | 鸿富锦精密工业（深圳）有限公司 | The method of the automatic detection computations machine of loop-type audio frequency apparatus playing function |
| CN101729635A (en) * | 2009-12-30 | 2010-06-09 | 中兴通讯股份有限公司 | Method and device for testing audio loop of communication terminal |
| CN103167391A (en) * | 2011-12-12 | 2013-06-19 | 英业达股份有限公司 | Audio test system and audio test method for to-be-tested device |
| CN102568470A (en) * | 2012-01-11 | 2012-07-11 | 广州酷狗计算机科技有限公司 | Acoustic fidelity identification method and system for audio files |
| CN102778358A (en) * | 2012-06-04 | 2012-11-14 | 上海东锐风电技术有限公司 | Failure prediction model establishing method and system as well as fan monitoring pre-warning system and method |
| CN103578466A (en) * | 2013-11-11 | 2014-02-12 | 清华大学 | Voice and non-voice detection method based on fractional order Fourier transformation |
| CN104050964A (en) * | 2014-06-17 | 2014-09-17 | 公安部第三研究所 | Audio signal reduction degree detecting method and system |
| CN104244161A (en) * | 2014-09-17 | 2014-12-24 | 苏州酷果信息技术有限公司 | Method and device for testing equipment with voice playing function and voice recording function |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106323330A (en) * | 2016-08-15 | 2017-01-11 | 中国科学技术大学苏州研究院 | Non-contact-type step count method based on WiFi motion recognition system |
| CN106323330B (en) * | 2016-08-15 | 2019-01-11 | 中国科学技术大学苏州研究院 | Contactless step-recording method based on WiFi motion recognition system |
| CN106658332A (en) * | 2016-12-30 | 2017-05-10 | 上海华东电信研究院 | Acoustic automatic testing device and system |
| CN111314536A (en) * | 2020-01-21 | 2020-06-19 | 上海悦易网络信息技术有限公司 | Method and equipment for detecting listening module of terminal equipment |
| US20220130411A1 (en) * | 2020-10-23 | 2022-04-28 | Institute For Information Industry | Defect-detecting device and defect-detecting method for an audio device |
| CN115616082A (en) * | 2022-12-14 | 2023-01-17 | 杭州兆华电子股份有限公司 | Keyboard defect analysis method based on noise detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220093111A1 (en) | Analysing speech signals | |
| US20200265834A1 (en) | Detection of replay attack | |
| US11042616B2 (en) | Detection of replay attack | |
| US20200227071A1 (en) | Analysing speech signals | |
| CN103578468B (en) | The method of adjustment and electronic equipment of a kind of confidence coefficient threshold of voice recognition | |
| EP3210205B1 (en) | Sound sample verification for generating sound detection model | |
| CN105810222A (en) | Defect detection method, device and system for audio equipment | |
| CN107221325A (en) | Aeoplotropism keyword verification method and the electronic installation using this method | |
| US9959886B2 (en) | Spectral comb voice activity detection | |
| WO2012176199A1 (en) | Method and system for identification of speech segments | |
| JP5948918B2 (en) | Consonant section detecting device and consonant section detecting method | |
| CN105979462A (en) | Test processing method and device based on microphone | |
| CN101114449A (en) | Model training method for unspecified person alone word, recognition system and recognition method | |
| CN110890087A (en) | Voice recognition method and device based on cosine similarity | |
| US20160027438A1 (en) | Concurrent Segmentation of Multiple Similar Vocalizations | |
| CN105825857A (en) | Voiceprint-recognition-based method for assisting deaf patient in determining sound type | |
| CN105336344A (en) | Noise detection method and apparatus thereof | |
| US7908142B2 (en) | Apparatus and method for identifying prosody and apparatus and method for recognizing speech | |
| CN104157288B (en) | With the speech recognition of multiple microphones | |
| US20200227069A1 (en) | Method, device and apparatus for recognizing voice signal, and storage medium | |
| US10839810B2 (en) | Speaker enrollment | |
| CN115620743A (en) | Abnormal sound detection method and device | |
| US11074917B2 (en) | Speaker identification | |
| CN111782860A (en) | Audio detection method and device and storage medium | |
| WO2019073233A1 (en) | Analysing speech signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160727 |
|
| RJ01 | Rejection of invention patent application after publication |