CN107580155A - Networking telephone quality determination method, device, computer equipment and storage medium - Google Patents
Networking telephone quality determination method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN107580155A CN107580155A CN201710773750.6A CN201710773750A CN107580155A CN 107580155 A CN107580155 A CN 107580155A CN 201710773750 A CN201710773750 A CN 201710773750A CN 107580155 A CN107580155 A CN 107580155A
- Authority
- CN
- China
- Prior art keywords
- voice
- quality
- voice signal
- gap periods
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Telephonic Communication Services (AREA)
- Telephone Function (AREA)
Abstract
The embodiment of the invention discloses a kind of networking telephone quality determination method, device, computer equipment and storage medium, methods described includes：Obtain the voice signal during network telephone call；Determine the gap periods and voice amplitudes of the voice signal；According to the gap periods and the voice amplitudes, the speech quality of the network telephone call process is determined.The embodiment of the present invention solves the problems, such as that black phone quality evaluation mode can not be directed to IP phone and carry out speech quality evaluation, realizes the effect that can detect speech quality in time in the case where the speech quality of IP phone is bad.
Description
Technical field
The present embodiments relate to speech recognition and voice quality assessment technology, more particularly to a kind of networking telephone quality are true
Determine method, apparatus, computer equipment and storage medium.
Background technology
With the fast development of the communications industry, by the mobile devices such as smart mobile phone, tablet personal computer realize Internet phone-calling into
For a kind of indispensable exchange way, wherein IP phone (Voice Over Internet Protocol, the networking telephone)
Even more turn into a kind of a kind of exchange way of popular favor, and the speech quality of the networking telephone also becomes particularly important.
Currently mainly detected for telephone service voice quality assessment by three kinds of models, including：MOS models,
PSQM models and E models.Wherein, MOS models and PSQM models are all subjective model, i.e., obtain call matter by manually evaluating
The scoring of amount.The thought of E models is to be by negative effect synthesis of a number of factors during voice signal transmission to speech quality
R, to assess the subjective quality of the voice call, wherein, R specific formula is：R=Ro-Is-Id-Ie+ A, Ro make an uproar for background
The interference of sound and current noise, Is are with caused influencing factors of quality, such as by quantifying, connecting noise and side with voice signal
The too strong interference brought of sound, Id are that quality caused by time delay influences, including due to talk echo and interactivity lose bring it is dry
Disturb, Ie is the mass loss introduced using special installation, such as the influence of low bit rate codec and the influence of packet loss.
But in above-mentioned existing technical scheme, MOS models and PSQM models are conversed by manually evaluating
The scoring of quality, artificial subjective factor has a great influence in speech quality scoring, and the parameter in E model formations R is black phone
Transmission in be related to, and IP phone be by network transmission, it is from black phone different by circuit exchange mode transmission,
Obvious E models are inapplicable to be evaluated voice call quality in IP phone.
The content of the invention
The present invention provides a kind of networking telephone quality determination method, device, computer equipment and storage medium, to realize
Speech quality can be detected in time in IP phone call.
In a first aspect, the embodiments of the invention provide a kind of networking telephone quality determination method, this method includes：
Obtain the voice signal during network telephone call；
Determine the gap periods and voice amplitudes of the voice signal；
According to the gap periods and the voice amplitudes, the speech quality of the network telephone call process is determined.
Second aspect, the embodiment of the present invention additionally provide a kind of networking telephone quality determining device, and the device includes：
Voice acquisition module, for obtaining the voice signal during network telephone call；
Parameter determination module, for determining the gap periods and voice amplitudes of the voice signal；
Quality determination module, for according to the gap periods and the voice amplitudes, determining the network telephone call
The speech quality of process.
The third aspect, the embodiment of the present invention additionally provide a kind of computer equipment, and the computer equipment includes：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processing
Device realizes any of the above-described described networking telephone quality determination method.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer-readable recording medium, are stored thereon with computer
Program, the program realize any of the above-described described networking telephone quality determination method when being executed by processor.
The embodiment of the present invention is determined between the voice signal by the voice signal during obtaining network telephone call
Phase and voice amplitudes every other week, and according to the gap periods and the voice amplitudes, determine the network telephone call process
Speech quality, solve the problems, such as that black phone quality evaluation mode can not be directed to IP phone and carry out speech quality evaluation, realize
The effect of speech quality can be detected in time in the case where the speech quality of IP phone is bad.
Brief description of the drawings
Fig. 1 is the flow chart of the networking telephone quality determination method in the embodiment of the present invention one；
Fig. 2 is the flow chart of the networking telephone quality determination method in the embodiment of the present invention two；
Fig. 3 is the flow chart of the networking telephone quality determination method in the embodiment of the present invention three；
Fig. 4 is the structural representation of the networking telephone quality determining device in the embodiment of the present invention four；
Fig. 5 is the structural representation of the computer equipment of the networking telephone quality determining device in the embodiment of the present invention five.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is the flow chart for the networking telephone quality determination method that the embodiment of the present invention one provides, and the present embodiment is applicable
The situation that speech quality determines during the networking telephone, this method can be performed by networking telephone quality determining device, should
Device can be realized by the way of software and/or hardware.As shown in figure 1, the networking telephone quality determination method, including：
Voice signal during step 110, acquisition network telephone call.
Specifically, whether the intelligent terminal such as detection smart mobile phone, tablet personal computer is in the communication process of IP phone, work as intelligence
When energy terminal is in the communication process of IP phone, in view of operator's speech path network circuit question and operator's ticket conversion form
The communicating data of IP phone can be caused to lose so that in-and-out shape occurs in communication process in the speech quality of IP phone
Condition, therefore, intelligent terminal can be conversed in the communication process of IP phone with the voice signal in extract real-time communication process
Quality testing.It should be noted that in the voice signal during obtaining IP phone, the voice signal can pass through intelligence
The voice signal of extract real-time when terminal is conversed, can also be IP phone call after by from corresponding to the call intelligence
The voice signal of the calling record type pulled in the phone lists of terminal.Wherein, the voice of the communication process of IP phone is obtained
During signal, it can be continual acquisition or obtain voice signal according to default time interval.
Step 120, the gap periods and voice amplitudes for determining the voice signal.
Because the essence of the internet used in IP phone communication process is packet switching network, the packet of same information source
Different route transmissions may be passed through to receiving terminal, therefore, the time delay being grouped into up to receiving terminal is also different.During this packet transmission
The difference prolonged is referred to as delay variation, and the presence of delay variation may cause between the decoded voice signal of receiving terminal occurs
It is disconnected, cause to obtain the voice signal in IP phone communication process and produce shake.The detection of voice jitter can be by acquisition
The periodicity of voice signal frequency interruption is judged, if the gap periods of the voice signal of the IP phone communication process obtained
Short and repetition, then be due to that the probability that network signal difference causes speech quality bad is larger.In the present embodiment, it is electric when obtaining IP
After talking about the voice signal in communication process, the gap periods of the voice signal, and one determined as speech quality can be detected
Individual factor.
Specifically, because voice signal is the signal with amplitude on time shaft, according to the change of voice signal amplitude
Situation, the frequency of the interruption of the voice signal obtained can be detected, according between the gap periods and frequency of voice signal
Inverse relation, the gap periods of voice signal can be obtained.Exemplary, due to the voice in the IP phone communication process of acquisition
Signal is amplitude signal, can carry out minimum value detection to the voice signal, the amplitude that voice signal is detected according to minimum value becomes
The result of change determines the frequency of the interruption of voice signal.Wherein minimum value detection has a variety of detection methods, such as to amplitude curve
The methods of derivation, can detect minimum value on the curve of the voice signal, specifically use which kind of minimum value in the present embodiment
Detection method is not construed as limiting here.
Correspondingly, when network is obstructed, in order to ensure the transmission of voice signal bag, voice signal bag can be compressed
Processing, and compression processing can cause voice signal amplitude to be compressed, hearer's subjective feeling is that sound is smaller.In the present embodiment,
After the voice signal in IP phone communication process is obtained, the voice amplitudes of the voice signal can also be detected, and by the voice
The voice amplitudes of signal are as a factor for determining speech quality.
Specifically, voice signal is the letter with amplitude on time shaft due in the communication process of the IP phone of acquisition
Number, can the power of the direct measurement voice signal obtain the voice amplitudes of the voice signal.Exemplary, in order to reduce voice width
The detection time of degree, it is contemplated that in the communication process of the IP phone of acquisition voice signal be a continuous letter in time domain
Number, it can preferably select the voice signal of a cycle then to calculate what the sample obtained in one cycle as sample
The output result that the average of voice signal amplitude detects as voice amplitudes, wherein, the cycle is the above-mentioned voice signal detected
Gap periods, the value of voice amplitudes is directly proportional to the average of voice signal.
Step 130, according to the gap periods and the voice amplitudes, determine the call of the network telephone call process
Quality.
In the present embodiment, the gap periods of the voice signal in IP phone communication process are obtained by above-mentioned steps 120
After voice amplitudes, the speech quality during P telephone relations can be detected according to the gap periods and voice amplitudes,
When the speech quality for detecting IP phone is bad, can timely to detect speech quality situation, and the matter that will converse
Amount situation is fed back.It is exemplary, when determining speech quality using gap periods and voice amplitudes, can to gap periods and
Voice amplitudes are each analyzed the speech quality influence degree of IP phone, and according to gap periods and voice amplitudes to call
The influence degree of quality sets weight proportion, and then calculates the speech quality of current IP phone.When it is determined that IP phone communication process
In speech quality after, the numerical value that speech quality determines can be shown, such as after calculating and determining that speech quality result is A,
It can be carried out according to the corresponding relation of the A values being calculated and speech quality result value set in advance and speech quality situation
Control determines speech quality situation；The quality condition of speech quality can also be directly displayed, for example speech quality is good, speech quality
The representations such as preferably, speech quality is poor and speech quality is poor, specific representation are set according to actual conditions.
The embodiments of the invention provide a kind of networking telephone quality determination method, by during obtaining network telephone call
Voice signal, determine the gap periods and voice amplitudes of the voice signal, and according to the gap periods and the voice
Amplitude, the speech quality of the network telephone call process is determined, IP can not be directed to by solving black phone quality evaluation mode
Phone carries out the problem of speech quality evaluation, and call can be detected in time in the case where the speech quality of IP phone is bad by realizing
The effect of quality.
On the basis of above-described embodiment, the embodiment of the present invention additionally provides a kind of preferred embodiment, described in pair determination
The gap periods and voice amplitudes of voice signal are further detailed as：To voice signal progress amplitude detection, and according to
The result of the amplitude detection determines the gap periods of the voice signal；According to the gap periods to the voice signal
Amplitude is counted, and determines the voice amplitudes of the voice signal.Specifically, the amplitude situation of change pair in voice signal
Voice signal carry out amplitude detection, can obtain voice signal interruption frequency, then according to the gap periods of voice signal with
The frequency relation of voice signal interruption calculates the gap periods of voice signal.Further, select between any voice signal every other week
The voice signal of phase counts the amplitude average of voice signal in the sample as sample, and according to the statistical result of amplitude average
Determine the voice amplitudes of voice signal.
Embodiment two
Fig. 2 is the flow chart for the networking telephone quality determination method that the embodiment of the present invention two provides, and the embodiment of the present invention exists
On the basis of above-described embodiment one, to according to the gap periods and the voice amplitudes, determining the network telephone call mistake
The speech quality of journey is further optimized for：Determine occur the bad word frequency of voice quality in the voice signal；According to described in
Gap periods, the voice amplitudes and the bad word frequency of institute's Voice Quality, determine the logical of the network telephone call process
Talk about quality.As shown in Fig. 2 the networking telephone quality determination method, including：
Voice signal during step 210, acquisition network telephone call.
Step 220, the gap periods and voice amplitudes for determining the voice signal.
In a preferred embodiment of the present embodiment, the gap periods and voice width for determining the voice signal
Degree, is specifically included：Amplitude detection is carried out to the voice signal, and determines that the voice is believed according to the result of the amplitude detection
Number gap periods；The amplitude of the voice signal is counted according to the gap periods, determines the voice signal
Voice amplitudes.
Step 230, determine occur the bad word frequency of voice quality in the voice signal.
In the present embodiment, due to the speech path network circuit question in IP phone communication process or operator's ticket conversion lattice
Formula may result in the second-rate of voice call, and when both call sides run into the bad situation of speech quality, it is most
People can say the similar this language with semantic information such as " not hearing ", " not hearing " and " saying again " in communication process
Sound is conversed, and these voice calls with semantic information can react the quality condition of voice call to a certain extent, when this
Class represents the bad word of voice quality or when sentence occurs, and the quality of voice call may have the bad feelings of speech quality
Condition.
It is bad to there is voice quality in a preferred embodiment of the present embodiment, in the determination voice signal
The word frequency, including：
The voice signal is converted into by text signal using speech recognition technology；
Determine whether occur indicating the bad word of voice quality in the text signal by semantic matches, if occurring,
Calculate the frequency that the mark bad word of voice quality occurs in the text signal.
It is specifically, similar this according to " not the hearing " occurred in communication process, " not hearing " and " saying again " etc.
Specific semantic database is established in voice call with semantic information, and the IP phone of acquisition is conversed by speech recognition technology
During voice signal be converted into writing text, then judge whether language occur in the writing text by semantic matches mode
The similar this voice call with semantic information such as similar " not hearing ", " not hearing " and " saying again " in adopted database
Or word, it is preferable to judge whether occur representing voice quality not similar to above-mentioned in the writing text using synonym matching technique
Good voice call or word with semantic information.When word corresponding to the voice signal in the IP phone communication process of acquisition
Text occurs carrying semantic information similar to this in semantic database similar " not hearing ", " not hearing " and " saying again " etc.
Voice call or during word, calculate the frequency that the voice call of the type or word occur in the IP phone communication process of acquisition
And/or number, and using the voice call of the type or word as the judgement factor for judging speech quality.Wherein, speech recognition
It is prior art with synonym matching technique, is not specifically limited here, for example LSTM can be used as speech recognition
Method.
Step 240, according to the gap periods, the voice amplitudes and the bad word frequency of institute's Voice Quality, it is determined that
The speech quality of the network telephone call process.
In the present embodiment, voice signal in the IP phone communication process of acquisition is determined by step 220 and step 230
, can be using the parameter information of above-mentioned acquisition as influence language after gap periods, voice amplitudes and the bad word frequency of voice quality
The influence factor of sound speech quality, and because above-mentioned several influence factors are to the shadow of voice call quality in IP phone communication process
The degree of sound simultaneously differs, therefore can be to gap periods, voice amplitudes and the bad word frequency of voice quality each to IP phone
Speech quality influence degree analyzed, and gap periods, voice amplitudes and voice matter are determined according to respective influence degree
Measure the weight proportion of the bad word frequency, finally according to gap periods, voice amplitudes and the bad word frequency of voice quality and
Each self-corresponding weight proportion carries out calculating the speech quality for determining IP phone.
The embodiments of the invention provide a kind of networking telephone quality determination method, by the gap periods for determining voice signal
After voice amplitudes, the further frequency for combining the bad word of voice quality that voice call occurs in IP phone communication process
It is secondary, the speech quality in IP phone communication process is detected, solves what speech quality in IP phone communication process determined
Problem, realizing in the case where the speech quality of IP phone is bad can occur according to the bad word of voice quality in voice call
The frequency quickly determine the effect of speech quality.
Embodiment three
Fig. 3 is the flow chart for the networking telephone quality determination method that the embodiment of the present invention three provides, and the embodiment of the present invention exists
On the basis of above-described embodiment one and embodiment two, further optimize it is described according to the gap periods, the voice amplitudes and
The frequency of the bad word of institute's Voice Quality, the step of determining the speech quality of the network telephone call process.Such as Fig. 3 institutes
Show, the networking telephone quality determination method, including：
Voice signal during step 310, acquisition network telephone call.
Step 320, the gap periods and voice amplitudes for determining the voice signal.
In a preferred embodiment of the present embodiment, the gap periods and voice width for determining the voice signal
Degree, including：Amplitude detection is carried out to the voice signal, and the voice signal is determined according to the result of the amplitude detection
Gap periods；The amplitude of the voice signal is counted according to the gap periods, determines the voice of the voice signal
Amplitude.
Step 330, determine occur the bad word frequency of voice quality in the voice signal.
It is bad to there is voice quality in a preferred embodiment of the present embodiment, in the determination voice signal
The word frequency, including：The voice signal is converted into by text signal using speech recognition technology；Institute is determined by semantic matches
State in text signal and whether occur indicating the bad word of voice quality, if occurring, calculate the text signal and logo occur
The frequency of the bad word of sound quality.
Step 340, the white noise probability for determining the voice signal.
In the present embodiment, can be outside voice signal when occurring the bad situation of speech quality in IP phone communication process
White noise signal is produced, therefore, white noise sound detection is carried out by the voice signal in the IP phone communication process to acquisition, and will
White noise testing result is as the evaluation points for determining voice call quality.Wherein, the white noise sound detection of voice signal is known
Method, white noise sound detection can use any of white noise detection method.Exemplary, by using target analyte detection
RCNN networks carry out classification based training, obtained object to the voice containing white noise of demarcation and the speech samples without white noise
The output probability of detection RCNN networks is the output probability of White Noise Model.Wherein, the output of white noise and White Noise Model
Probability is proportional.
Step 350, according to the gap periods, the voice amplitudes, the bad word frequency of institute's Voice Quality and described
White noise probability, determine the speech quality of the network telephone call process.
In the present embodiment, language in the IP phone communication process of acquisition is determined by step 320, step 330 and step 340
, can be by above-mentioned acquisition after the bad word frequency of gap periods, voice amplitudes, voice quality and white noise probability of sound signal
Influence factor of the parameter information as influence voice call quality, and because above-mentioned several influence factors are to IP phone communication process
The influence degree of middle voice call quality simultaneously differs, therefore can be to gap periods, voice amplitudes, the bad word of voice quality
The frequency, white noise probability are analyzed the speech quality influence degree of IP phone respectively, and are determined according to influence degree result
The weight proportion of the bad word frequency of gap periods, voice amplitudes, voice quality and white noise probability, between according to every other week finally
Phase, voice amplitudes, the bad word frequency of voice quality and white noise probability and each self-corresponding weight proportion carry out integrating meter
Calculate the speech quality for determining IP phone.
In a preferred embodiment of the present embodiment, it is described according to the gap periods, it is the voice amplitudes, described
The bad word frequency of voice quality and the white noise probability, the speech quality of the network telephone call process is determined, including：
According to formula Q=- α * N- β * J+ γ * A- δ * S, the speech quality of the network telephone call process is obtained；
Wherein, Q be the network telephone call process speech quality, N be the voice signal white noise probability, J
For the gap periods of the voice signal, A is the voice amplitudes of the voice signal, and S is voice occur in the voice signal
The bad word frequency of quality, α are the weight factor of the white noise probability, and β is the weight factor of the gap periods, and γ is institute
The weight factor of voice amplitudes is stated, δ is the weight factor of the bad word frequency of the quality.
Specifically, on α, beta, gamma, δ is the determination of weight factor, to be obtained in theory by testing, initial value be more than
Zero real number, such as α=2.0, β=2.0, γ=1.0, δ=1.0.By above phone call quality evaluation model Q, then may be used
To judge whether speech quality is bad in IP phone communication process, wherein, speech quality is directly proportional to Q value.Need what is illustrated
It is weight factor α, beta, gamma, δ setting can be restricted here according to actual conditions accommodation.
The embodiments of the invention provide a kind of networking telephone quality determination method, pass through the gap periods of voice signal, language
The frequency and white noise Probabilistic Synthesis of the bad word of sound amplitude, voice quality consider the call matter in IP phone communication process
Amount, in particular by a kind of speech quality definitely model, solve speech quality in IP phone communication process well and determine
The problem of, realize the effect that speech quality can be quickly determined in the case where the speech quality of IP phone is bad.
Example IV
Fig. 4 is the structural representation for the networking telephone quality determining device that the embodiment of the present invention four provides；The device performs
The networking telephone quality determination method that any of the above-described embodiment provides, the device can be real by the way of software and/or hardware
It is existing.As shown in figure 4, the networking telephone quality determining device, including：
Voice acquisition module 410, for obtaining the voice signal during network telephone call.
Parameter determination module 420, for determining the gap periods and voice amplitudes of the voice signal.
In a preferred embodiment of the present embodiment, the parameter determination module includes：
Amplitude detection and cycle determining unit, for carrying out amplitude detection to the voice signal, and according to the amplitude
The result of detection determines the gap periods of the voice signal；
Voice amplitudes determining unit, for being counted according to the gap periods to the amplitude of the voice signal, really
The voice amplitudes of the fixed voice signal.
Quality determination module 430, for according to the gap periods and the voice amplitudes, determining that the networking telephone leads to
The speech quality of words process.
In a preferred embodiment of the present embodiment, the quality determination module includes：
Word frequency detection unit, for determining occur the bad word frequency of voice quality in the voice signal；
Speech quality determining unit, for bad according to the gap periods, the voice amplitudes and institute's Voice Quality
The word frequency, determine the speech quality of the network telephone call process.
Wherein, the word frequency detection unit specifically includes：
Voice transforming subunit, for the voice signal to be converted into text signal using speech recognition technology；Word
Frequency detection sub-unit, for determining whether occur indicating the bad word of voice quality in the text signal by semantic matches
Language, if occurring, calculate the frequency that the mark bad word of voice quality occurs in the text signal.
The speech quality determining unit includes
Noise probability computation subunit, for determining the white noise probability of the voice signal；Speech quality determines that son is single
Member, for general according to the gap periods, the voice amplitudes, the bad word frequency of institute's Voice Quality and the white noise
Rate, determine the speech quality of the network telephone call process.
The speech quality determination subelement specifically includes：
According to formula Q=- α * N- β * J+ γ * A- δ * S, the speech quality of the network telephone call process is obtained；
Wherein, Q be the network telephone call process speech quality, N be the voice signal white noise probability, J
For the gap periods of the voice signal, A is the voice amplitudes of the voice signal, and S is voice occur in the voice signal
The bad word frequency of quality, α are the weight factor of the white noise probability, and β is the weight factor of the gap periods, and γ is institute
The weight factor of voice amplitudes is stated, δ is the weight factor of the bad word frequency of the quality.
The networking telephone quality determining device that the embodiment of the present invention is provided can perform any embodiment of the present invention and be provided
Networking telephone quality determination method, possess and perform the corresponding functional module of this method and beneficial effect.
Embodiment five
Fig. 5 is a kind of structural representation for computer equipment that the embodiment of the present invention five provides.Fig. 5 is shown suitable for being used for
Realize the block diagram of the exemplary computer device 512 of embodiment of the present invention.The computer equipment 512 that Fig. 5 is shown is only one
Individual example, any restrictions should not be brought to the function and use range of the embodiment of the present invention.
As shown in figure 5, computer equipment 512 is showed in the form of universal computing device.The component of computer equipment 512 can
To include but is not limited to：One or more processor 516, system storage 528, connection different system component (including system
Memory 528 and processor 516) bus 518.
Bus 518 represents the one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.Lift
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, MCA (MAC)
Bus, enhanced isa bus, VESA's (VESA) local bus and periphery component interconnection (PCI) bus.
Computer equipment 512 typically comprises various computing systems computer-readable recording medium.These media can be it is any can
The usable medium accessed by computer equipment 512, including volatibility and non-volatile media, moveable and immovable Jie
Matter.
System storage 528 can include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 530 and/or cache memory 532.Computer equipment 512 may further include it is other it is removable/
Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 534 can be used for reading
Write immovable, non-volatile magnetic media (Fig. 5 is not shown, is commonly referred to as " hard disk drive ").Although not shown in Fig. 5,
It can provide for the disc driver to may move non-volatile magnetic disk (such as " floppy disk ") read-write, and to removable non-easy
The CD drive of the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each
Driver can be connected by one or more data media interfaces with bus 518.Memory 528 can include at least one
Program product, the program product have one group of (for example, at least one) program module, and these program modules are configured to perform this
Invent the function of each embodiment.
Program/utility 540 with one group of (at least one) program module 542, can be stored in such as memory
In 528, such program module 542 includes but is not limited to operating system, one or more application program, other program modules
And routine data, the realization of network environment may be included in each or certain combination in these examples.Program module 542
Generally perform the function and/or method in embodiment described in the invention.
Computer equipment 512 can also be with one or more external equipments 514 (such as keyboard, sensing equipment, display
524 etc.) communicate, can also enable a user to the equipment communication interacted with computer equipment 512 with one or more, and/or with
Enable any equipment that the computer equipment 512 communicated with one or more of the other computing device (such as network interface card, modulation
Demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 522.Also, computer equipment 512
Network adapter 520 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public affairs can also be passed through
Common network network, such as internet) communication.As illustrated, network adapter 520 passes through the other of bus 518 and computer equipment 512
Module communicates.It should be understood that although not shown in Fig. 5, computer equipment 512 can be combined and use other hardware and/or software
Module, include but is not limited to：Microcode, device driver, redundant processing unit, external disk drive array, RAID system, magnetic
Tape drive and data backup storage system etc..
Processor 516 is stored in program in system storage 528 by operation, so as to perform various function application and
Data processing, such as the networking telephone quality determination method that the embodiment of the present invention is provided is realized, including：
Obtain the voice signal during network telephone call；
Determine the gap periods and voice amplitudes of the voice signal；
According to the gap periods and the voice amplitudes, the speech quality of the network telephone call process is determined.
Embodiment six
The embodiment of the present invention six additionally provides a kind of computer-readable recording medium, is stored thereon with computer program, should
The networking telephone quality determination method provided such as the embodiment of the present invention is provided when program is executed by processor, including：
Obtain the voice signal during network telephone call；
Determine the gap periods and voice amplitudes of the voice signal；
According to the gap periods and the voice amplitudes, the speech quality of the network telephone call process is determined.
The computer-readable storage medium of the embodiment of the present invention, any of one or more computer-readable media can be used
Combination.Computer-readable medium can be computer-readable signal media or computer-readable recording medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any combination above.The more specifically example (non exhaustive list) of computer-readable recording medium includes：Tool
There are the electrical connections of one or more wires, portable computer diskette, hard disk, random access memory (RAM), read-only storage
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any includes or the tangible medium of storage program, the program can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium beyond storage medium is read, the computer-readable medium, which can send, propagates or transmit, to be used for
By instruction execution system, device either device use or program in connection.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc., or above-mentioned any appropriate combination.
It can be write with one or more programming languages or its combination for performing the computer that operates of the present invention
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Also include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
Fully perform, partly perform on the user computer on the user computer, the software kit independent as one performs, portion
Divide and partly perform or performed completely on remote computer or server on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as carried using Internet service
Pass through Internet connection for business).
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (14)
- A kind of 1. networking telephone quality determination method, it is characterised in that including：Obtain the voice signal during network telephone call；Determine the gap periods and voice amplitudes of the voice signal；According to the gap periods and the voice amplitudes, the speech quality of the network telephone call process is determined.
- 2. according to the method for claim 1, it is characterised in that the gap periods and voice for determining the voice signal Amplitude, including：Amplitude detection is carried out to the voice signal, and the interval of the voice signal is determined according to the result of the amplitude detection Cycle；The amplitude of the voice signal is counted according to the gap periods, determines the voice amplitudes of the voice signal.
- 3. according to the method for claim 1, it is characterised in that it is described according to the gap periods and the voice amplitudes, The speech quality of the network telephone call process is determined, including：Determine occur the bad word frequency of voice quality in the voice signal；According to the gap periods, the voice amplitudes and the bad word frequency of institute's Voice Quality, the networking telephone is determined The speech quality of communication process.
- 4. according to the method for claim 3, it is characterised in that described to determine voice quality occur not in the voice signal The good word frequency, including：The voice signal is converted into by text signal using speech recognition technology；Determine whether occur indicating the bad word of voice quality in the text signal by semantic matches, if occurring, calculate There is the frequency of the mark bad word of voice quality in the text signal.
- 5. according to the method for claim 3, it is characterised in that it is described according to the gap periods, the voice amplitudes and The frequency of the bad word of institute's Voice Quality, the speech quality of the network telephone call process is determined, including：Determine the white noise probability of the voice signal；According to the gap periods, the voice amplitudes, the bad word frequency of institute's Voice Quality and the white noise probability, really The speech quality of the fixed network telephone call process.
- 6. according to the method for claim 5, it is characterised in that described according to the gap periods, the voice amplitudes, institute The bad word frequency of Voice Quality and the white noise probability, the speech quality of the network telephone call process is determined, wrapped Include：According to formula Q=- α * N- β * J+ γ * A- δ * S, the speech quality of the network telephone call process is obtained；Wherein, Q is the speech quality of the network telephone call process, and N is the white noise probability of the voice signal, and J is institute The gap periods of predicate sound signal, A are the voice amplitudes of the voice signal, and S is voice quality occur in the voice signal The bad word frequency, α are the weight factor of the white noise probability, and β is the weight factor of the gap periods, and γ is institute's predicate The weight factor of sound amplitude, δ are the weight factor of the bad word frequency of the quality.
- A kind of 7. networking telephone quality determining device, it is characterised in that including：Voice acquisition module, for obtaining the voice signal during network telephone call；Parameter determination module, for determining the gap periods and voice amplitudes of the voice signal；Quality determination module, for according to the gap periods and the voice amplitudes, determining the network telephone call process Speech quality.
- 8. device according to claim 7, it is characterised in that the parameter determination module includes：Amplitude detection and cycle determining unit, for carrying out amplitude detection to the voice signal, and according to the amplitude detection Result determine the gap periods of the voice signal；Voice amplitudes determining unit, for being counted according to the gap periods to the amplitude of the voice signal, determine institute The voice amplitudes of predicate sound signal.
- 9. device according to claim 7, it is characterised in that the quality determination module includes：Word frequency detection unit, for determining occur the bad word frequency of voice quality in the voice signal；Speech quality determining unit, for according to the gap periods, the voice amplitudes and the bad word of institute's Voice Quality The frequency, determine the speech quality of the network telephone call process.
- 10. device according to claim 9, it is characterised in that the word frequency detection unit includes：Voice transforming subunit, for the voice signal to be converted into text signal using speech recognition technology；Word frequency detection sub-unit, for determining whether occur mark voice quality in the text signal by semantic matches Bad word, if occurring, calculate the frequency that the mark bad word of voice quality occurs in the text signal.
- 11. device according to claim 9, it is characterised in that the speech quality determining unit includes：Noise probability computation subunit, for determining the white noise probability of the voice signal；Speech quality determination subelement, for according to the gap periods, the voice amplitudes, the bad word of institute's Voice Quality The frequency and the white noise probability, determine the speech quality of the network telephone call process.
- 12. device according to claim 11, it is characterised in that the speech quality determination subelement specifically includes：According to formula Q=- α * N- β * J+ γ * A- δ * S, the speech quality of the network telephone call process is obtained；Wherein, Q is the speech quality of the network telephone call process, and N is the white noise probability of the voice signal, and J is institute The gap periods of predicate sound signal, A are the voice amplitudes of the voice signal, and S is voice quality occur in the voice signal The bad word frequency, α are the weight factor of the white noise probability, and β is the weight factor of the gap periods, and γ is institute's predicate The weight factor of sound amplitude, δ are the weight factor of the bad word frequency of the quality.
- 13. a kind of computer equipment, it is characterised in that the computer equipment includes：One or more processors；Storage device, for storing one or more programs,When one or more of programs are by one or more of computing devices so that one or more of processors are real The now networking telephone quality determination method as described in any in claim 1-6.
- 14. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The networking telephone quality determination method as described in any in claim 1-6 is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710773750.6A CN107580155B (en) | 2017-08-31 | 2017-08-31 | Network telephone quality determination method, network telephone quality determination device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710773750.6A CN107580155B (en) | 2017-08-31 | 2017-08-31 | Network telephone quality determination method, network telephone quality determination device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107580155A true CN107580155A (en) | 2018-01-12 |
| CN107580155B CN107580155B (en) | 2020-09-11 |
Family
ID=61030691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710773750.6A Active CN107580155B (en) | 2017-08-31 | 2017-08-31 | Network telephone quality determination method, network telephone quality determination device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107580155B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108881182A (en) * | 2018-05-30 | 2018-11-23 | 上海携程商务有限公司 | The networking telephone realization method and system of mobile terminal based on IOS |
| CN110289014A (en) * | 2019-05-21 | 2019-09-27 | 华为技术有限公司 | A kind of speech quality detection method and electronic equipment |
| CN113393863A (en) * | 2021-06-10 | 2021-09-14 | 北京字跳网络技术有限公司 | Voice evaluation method, device and equipment |
| CN113676599A (en) * | 2021-08-20 | 2021-11-19 | 上海明略人工智能(集团)有限公司 | Network call quality detection method, system, computer device and storage medium |
| CN113824843A (en) * | 2020-06-19 | 2021-12-21 | 大众问问(北京)信息科技有限公司 | Voice call quality detection method, device, equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030142813A1 (en) * | 2002-01-25 | 2003-07-31 | Acoustic Technologies, Inc. | Telephone having four VAD circuits |
| US20070104185A1 (en) * | 2005-11-10 | 2007-05-10 | Edward Walter | Voice over internet protocol codec adjustment |
| CN102438266A (en) * | 2011-01-12 | 2012-05-02 | 北京炎强通信技术有限公司 | Method and device for optimizing voice quality of mobile communication network |
| CN103348730A (en) * | 2011-02-10 | 2013-10-09 | 英派尔科技开发有限公司 | Quality-of-experience measurement for voice services |
| CN103632680A (en) * | 2012-08-24 | 2014-03-12 | 华为技术有限公司 | Speech quality assessment method, network element and system |
| CN103648120A (en) * | 2013-12-25 | 2014-03-19 | 北京炎强通信技术有限公司 | Method for optimizing voice over wireless local area network of mobile communication network |
| CN104485114A (en) * | 2014-11-27 | 2015-04-01 | 湖南省计量检测研究院 | Auditory perception characteristic-based speech quality objective evaluating method |
| CN104506387A (en) * | 2014-12-26 | 2015-04-08 | 大连理工大学 | LTE (long-term evolution) communication system speech quality evaluation method |
| CN105261362A (en) * | 2015-09-07 | 2016-01-20 | 科大讯飞股份有限公司 | Conversation voice monitoring method and system |
-
2017
- 2017-08-31 CN CN201710773750.6A patent/CN107580155B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030142813A1 (en) * | 2002-01-25 | 2003-07-31 | Acoustic Technologies, Inc. | Telephone having four VAD circuits |
| US20070104185A1 (en) * | 2005-11-10 | 2007-05-10 | Edward Walter | Voice over internet protocol codec adjustment |
| CN102438266A (en) * | 2011-01-12 | 2012-05-02 | 北京炎强通信技术有限公司 | Method and device for optimizing voice quality of mobile communication network |
| CN103348730A (en) * | 2011-02-10 | 2013-10-09 | 英派尔科技开发有限公司 | Quality-of-experience measurement for voice services |
| CN103632680A (en) * | 2012-08-24 | 2014-03-12 | 华为技术有限公司 | Speech quality assessment method, network element and system |
| CN103648120A (en) * | 2013-12-25 | 2014-03-19 | 北京炎强通信技术有限公司 | Method for optimizing voice over wireless local area network of mobile communication network |
| CN104485114A (en) * | 2014-11-27 | 2015-04-01 | 湖南省计量检测研究院 | Auditory perception characteristic-based speech quality objective evaluating method |
| CN104506387A (en) * | 2014-12-26 | 2015-04-08 | 大连理工大学 | LTE (long-term evolution) communication system speech quality evaluation method |
| CN105261362A (en) * | 2015-09-07 | 2016-01-20 | 科大讯飞股份有限公司 | Conversation voice monitoring method and system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108881182A (en) * | 2018-05-30 | 2018-11-23 | 上海携程商务有限公司 | The networking telephone realization method and system of mobile terminal based on IOS |
| CN108881182B (en) * | 2018-05-30 | 2020-08-25 | 上海华客信息科技有限公司 | IOS-based mobile terminal network telephone realization method and system |
| CN110289014A (en) * | 2019-05-21 | 2019-09-27 | 华为技术有限公司 | A kind of speech quality detection method and electronic equipment |
| CN110289014B (en) * | 2019-05-21 | 2021-11-19 | 华为技术有限公司 | Voice quality detection method and electronic equipment |
| CN113824843A (en) * | 2020-06-19 | 2021-12-21 | 大众问问(北京)信息科技有限公司 | Voice call quality detection method, device, equipment and storage medium |
| CN113824843B (en) * | 2020-06-19 | 2023-11-21 | 大众问问(北京)信息科技有限公司 | Voice call quality detection method, device, equipment and storage medium |
| CN113393863A (en) * | 2021-06-10 | 2021-09-14 | 北京字跳网络技术有限公司 | Voice evaluation method, device and equipment |
| CN113393863B (en) * | 2021-06-10 | 2023-11-03 | 北京字跳网络技术有限公司 | Voice evaluation method, device and equipment |
| CN113676599A (en) * | 2021-08-20 | 2021-11-19 | 上海明略人工智能(集团)有限公司 | Network call quality detection method, system, computer device and storage medium |
| CN113676599B (en) * | 2021-08-20 | 2024-03-22 | 上海明略人工智能(集团)有限公司 | Network call quality detection method, system, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107580155B (en) | 2020-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107580155A (en) | Networking telephone quality determination method, device, computer equipment and storage medium | |
| Rix et al. | Objective assessment of speech and audio quality—technology and applications | |
| CN109961792B (en) | Method and apparatus for recognizing speech | |
| US11688515B2 (en) | Mobile device based techniques for detection and prevention of hearing loss | |
| CN112863547A (en) | Virtual resource transfer processing method, device, storage medium and computer equipment | |
| CN106887241A (en) | A kind of voice signal detection method and device | |
| US9524733B2 (en) | Objective speech quality metric | |
| CN107799126A (en) | Sound end detecting method and device based on Supervised machine learning | |
| CN104067341A (en) | Voice activity detection in presence of background noise | |
| Rix | Perceptual speech quality assessment-a review | |
| CN108833722A (en) | Audio recognition method, device, computer equipment and storage medium | |
| WO2015034633A1 (en) | Method for non-intrusive acoustic parameter estimation | |
| MX2008016354A (en) | Detecting an answering machine using speech recognition. | |
| CN110335593A (en) | Sound end detecting method, device, equipment and storage medium | |
| CN108428175A (en) | A kind of big data analysis method and system based on consumer record | |
| CN105825869A (en) | Voice processing device and voice processing method | |
| Ding et al. | Non-intrusive single-ended speech quality assessment in VoIP | |
| CN107846520A (en) | single-pass detection method and device | |
| CN109065017B (en) | Voice data generation method and related device | |
| CN107403629A (en) | Far field pickup method of evaluating performance and system, electronic equipment | |
| CN111326159B (en) | Voice recognition method, device and system | |
| CN109637540B (en) | Bluetooth evaluation method, device, equipment and medium for intelligent voice equipment | |
| CN117061378A (en) | Voice call quality detection method | |
| US8244538B2 (en) | Measuring double talk performance | |
| US20230245668A1 (en) | Neural network-based audio packet loss restoration method and apparatus, and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |