CN107580155B - Network telephone quality determination method, network telephone quality determination device, computer equipment and storage medium - Google Patents
Network telephone quality determination method, network telephone quality determination device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN107580155B CN107580155B CN201710773750.6A CN201710773750A CN107580155B CN 107580155 B CN107580155 B CN 107580155B CN 201710773750 A CN201710773750 A CN 201710773750A CN 107580155 B CN107580155 B CN 107580155B
- Authority
- CN
- China
- Prior art keywords
- voice
- quality
- determining
- amplitude
- interval period
- 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.)
- Active
Links
Images
Abstract
The embodiment of the invention discloses a method, a device, computer equipment and a storage medium for determining the quality of a network telephone, wherein the method comprises the following steps: acquiring a voice signal in the communication process of the network telephone; determining interval period and voice amplitude of the voice signal; and determining the call quality of the network telephone call process according to the interval period and the voice amplitude. The embodiment of the invention solves the problem that the traditional telephone quality evaluation mode cannot evaluate the call quality of the IP telephone, and realizes the effect of timely detecting the call quality under the condition of poor call quality of the IP telephone.
Description
Technical Field
The embodiment of the invention relates to voice recognition and voice quality evaluation technologies, in particular to a method and a device for determining network telephone quality, computer equipment and a storage medium.
Background
With the rapid development of the communication industry, the realization of network communication through mobile devices such as smart phones and tablet computers becomes an indispensable communication mode, wherein an IP phone (Voice Over Internet Protocol) is more popular among the communication modes, and the communication quality of the network phone is more important.
Currently, voice quality evaluation for telephone service is mainly detected by three models, including: MOS model, PSQM model and E model. The MOS model and the PSQM model are subjective models, namely scores of call quality are obtained through manual evaluation. The idea of the E model is to integrate the negative impact of several factors on the speech quality during the transmission of voice signals into R for evaluating the subjective quality of the voice call, wherein the specific formula of R is: r ═ Ro-Is-Id-Ie+ a, Ro Is the interference of background noise and current noise, Is the quality-affecting factor generated simultaneously with the speech signal, such as interference due to quantization, connection noise and side tone, Id Is the quality-affecting factor caused by delay, including interference due to talk echo and loss of interactivity, Ie Is the quality loss introduced by using special equipment, such as the effect of low bit rate codec and the effect of packet loss.
However, in the above prior art, both the MOS model and the PSQM model obtain the call quality score through manual evaluation, the influence of the artificial subjective factors in the call quality score is large, while the parameters in the E model formula R are related to the transmission of the traditional telephone, and the IP telephone is transmitted through the network, which is different from the traditional telephone transmitted through the circuit switching mode, and obviously, the E model is not suitable for evaluating the voice call quality in the IP telephone.
Disclosure of Invention
The invention provides a method and a device for determining the quality of a network telephone, computer equipment and a storage medium, which are used for realizing the timely detection of the call quality in IP telephone calls.
In a first aspect, an embodiment of the present invention provides a method for determining quality of a network telephone, where the method includes:
acquiring a voice signal in the communication process of the network telephone;
determining interval period and voice amplitude of the voice signal;
and determining the call quality of the network telephone call process according to the interval period and the voice amplitude.
In a second aspect, an embodiment of the present invention further provides an apparatus for determining a quality of a network telephone, where the apparatus includes:
the voice acquisition module is used for acquiring a voice signal in the conversation process of the network telephone;
the parameter determination module is used for determining the interval period and the voice amplitude of the voice signal;
and the quality determining module is used for determining the call quality of the network telephone in the call process according to the interval period and the voice amplitude.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement any of the above-described voice over internet protocol quality determination methods.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements any of the foregoing network telephone quality determination methods.
According to the embodiment of the invention, the voice signal in the call process of the IP phone is obtained, the interval period and the voice amplitude of the voice signal are determined, and the call quality in the call process of the IP phone is determined according to the interval period and the voice amplitude, so that the problem that the traditional call quality evaluation mode cannot evaluate the call quality of the IP phone is solved, and the effect of timely detecting the call quality under the condition of poor call quality of the IP phone is realized.
Drawings
Fig. 1 is a flowchart of a method for determining the quality of a network telephone according to a first embodiment of the present invention;
fig. 2 is a flowchart of a method for determining the quality of a network telephone according to a second embodiment of the present invention;
fig. 3 is a flowchart of a method for determining the quality of a network telephone according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a network telephone quality determination apparatus in a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computer device of the network telephone quality determination apparatus in the fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a method for determining quality of a network telephone according to an embodiment of the present invention, where the embodiment is applicable to a situation of determining call quality in a network telephone process, and the method may be executed by a device for determining quality of a network telephone, and the device may be implemented in a software and/or hardware manner. As shown in fig. 1, the method for determining the quality of the internet phone includes:
and step 110, acquiring a voice signal in the conversation process of the network telephone.
Specifically, whether an intelligent terminal such as a smart phone and a tablet personal computer is in the call process of an IP phone or not is detected, and when the intelligent terminal is in the call process of the IP phone, the call data of the IP phone is lost due to the call network line problem of an operator and the call ticket conversion format of the operator, so that the call quality of the IP phone is good and bad in the call process, and therefore the intelligent terminal can extract a voice signal in the call process in real time in the call process of the IP phone to detect the call quality. It should be noted that, when acquiring a voice signal in the IP telephone process, the voice signal may be a voice signal extracted in real time when the intelligent terminal is in a call, or may be a voice signal of a call recording type pulled from a call list of the intelligent terminal corresponding to the call after the IP telephone call. When the voice signal of the call process of the IP telephone is acquired, the voice signal may be continuously acquired or may be acquired according to a preset time interval.
And step 120, determining the interval period and the voice amplitude of the voice signal.
Because the nature of the internet used in an IP telephony session is a packet-switched network, packets from the same source may be transmitted to a receiving end via different routes, and therefore, the time delay for the packets to reach the receiving end is also different. The difference of the packet transmission delay is called delay jitter, and the existence of the delay jitter may cause the interruption of the voice signal decoded by the receiving end, which causes the jitter of the voice signal in the process of acquiring the IP phone call. The detection of the voice jitter can be judged by the discontinuous periodicity of the acquired voice signal frequency, and if the interval period of the acquired voice signal in the IP telephone conversation process is short and repeated, the probability of poor conversation quality caused by poor network signals is higher. In this embodiment, after acquiring a voice signal during an IP telephone call, the inter-period of the voice signal may be detected and used as a factor for determining the call quality.
Specifically, since the speech signal is a signal having an amplitude on the time axis, the discontinuous frequency of the acquired speech signal can be detected according to the variation of the amplitude of the speech signal, and the interval period of the speech signal can be obtained according to the inverse relationship between the interval period and the frequency of the speech signal. For example, since the acquired voice signal in the IP telephone call process is an amplitude signal, the minimum detection may be performed on the voice signal, and the discontinuous frequency of the voice signal may be determined according to the result of detecting the amplitude change of the voice signal based on the minimum value. The minimum value detection has various detection methods, for example, methods such as derivation of an amplitude curve can detect the minimum value on the curve of the voice signal, and which minimum value detection method is specifically adopted in the embodiment is not limited here.
Correspondingly, when the network is not smooth, in order to guarantee the transmission of the voice signal packets, the voice signal packets are compressed, and the compression process can lead to the amplitude of the voice signal being compressed, so that the listener feels that the voice is small. In this embodiment, after acquiring the voice signal during the IP telephone call, the voice amplitude of the voice signal may be detected, and the voice amplitude of the voice signal may be used as a factor for determining the call quality.
Specifically, since the obtained voice signal during the call of the IP phone is a signal having an amplitude on the time axis, the strength of the voice signal can be directly measured to obtain the voice amplitude of the voice signal. For example, in order to reduce the detection time of the voice amplitude, considering that the voice signal is a continuous signal in the time domain during the call of the IP phone, it is preferable to select a voice signal of one period as a sample, and then calculate the average value of the amplitudes of the voice signal obtained by the sample in one period as the output result of the voice amplitude detection, wherein the period is the interval period of the detected voice signal, and the value of the voice amplitude is proportional to the average value of the voice signal.
And step 130, determining the call quality of the network telephone call process according to the interval period and the voice amplitude.
In this embodiment, after the interval period and the voice amplitude of the voice signal in the IP phone call process are obtained in the step 120, the call quality in the P phone call process can be detected according to the interval period and the voice amplitude, so that when the call quality of the IP phone is detected to be poor, the call quality can be detected in time, and the call quality can be fed back. For example, when the call quality is determined by using the interval period and the voice amplitude, the influence degree of the interval period and the voice amplitude on the call quality of the IP phone may be analyzed, and a weight ratio may be set according to the influence degree of the interval period and the voice amplitude on the call quality, so as to calculate the call quality of the current IP phone. After the call quality in the IP telephone call process is determined, a value determined by the call quality may be displayed, for example, after the call quality result is calculated and determined to be a, the call quality status may be determined by comparing the calculated a value with a preset correspondence between the call quality result value and the call quality status; the quality condition of the call quality can also be directly displayed, for example, the representation modes such as good call quality, better call quality, poorer call quality, poor call quality and the like are displayed, and the specific representation mode is set according to the actual condition.
The embodiment of the invention provides a method for determining the quality of a network telephone, which determines the interval period and the voice amplitude of a voice signal by acquiring the voice signal in the call process of the network telephone and determines the call quality in the call process of the network telephone according to the interval period and the voice amplitude, solves the problem that the traditional telephone quality evaluation mode cannot evaluate the call quality of an IP telephone, and achieves the effect of timely detecting the call quality under the condition of poor call quality of the IP telephone.
On the basis of the foregoing embodiment, an embodiment of the present invention further provides a preferred implementation manner, and the determining the interval period and the speech amplitude of the speech signal is further embodied as: carrying out amplitude detection on the voice signal, and determining an interval period of the voice signal according to the result of the amplitude detection; and counting the amplitude of the voice signal according to the interval period, and determining the voice amplitude of the voice signal. Specifically, the amplitude detection is performed on the voice signal according to the amplitude variation condition in the voice signal, so as to obtain the discontinuous frequency of the voice signal, and then the interval period of the voice signal is calculated according to the relationship between the interval period of the voice signal and the discontinuous frequency of the voice signal. Further, selecting a voice signal of any voice signal interval period as a sample, counting the amplitude mean value of the voice signal in the sample, and determining the voice amplitude of the voice signal according to the statistical result of the amplitude mean value.
Example two
Fig. 2 is a flowchart of a method for determining the quality of the internet phone according to a second embodiment of the present invention, where the embodiment of the present invention further optimizes the determination of the call quality of the internet phone during the call process according to the interval period and the voice amplitude on the basis of the first embodiment of the present invention as follows: determining the frequency of words with poor voice quality in the voice signal; and determining the conversation quality of the network telephone in the conversation process according to the interval period, the voice amplitude and the frequency of the words with poor voice quality. As shown in fig. 2, the method for determining the quality of the internet phone includes:
and step 210, acquiring a voice signal in the conversation process of the network telephone.
In a preferred implementation manner of this embodiment, the determining the interval period and the voice amplitude of the voice signal specifically includes: carrying out amplitude detection on the voice signal, and determining an interval period of the voice signal according to the result of the amplitude detection; and counting the amplitude of the voice signal according to the interval period, and determining the voice amplitude of the voice signal.
And step 230, determining the frequency of the words with poor voice quality in the voice signal.
In this embodiment, the quality of the voice call may be poor due to the problem of the call network line or the format conversion of the operator's call bill during the IP telephone call, and when the call parties encounter the situation of poor call quality, most people can speak the voice call with semantic information, such as "cannot hear", "cannot hear" and "speak again" during the call process, and these voice calls with semantic information can reflect the quality of the voice call to some extent, and when such words or sentences representing poor voice quality appear, the quality of the voice call may have the situation of poor call quality.
In a preferred implementation manner of this embodiment, the determining the frequency of the occurrence of words with poor speech quality in the speech signal includes:
converting the voice signal into a text signal by adopting a voice recognition technology;
and determining whether the words marked with poor voice quality appear in the text signal or not through semantic matching, and if so, calculating the frequency of the words marked with poor voice quality appearing in the text signal.
Specifically, a specific semantic database is established according to voice calls with semantic information, such as "cannot be heard clearly", "cannot be heard clearly" and "can be spoken again" in the call process, the acquired voice signals in the call process of the IP telephone are converted into text texts through a voice recognition technology, then whether the voice calls or words with the semantic information, such as "cannot be heard clearly", "cannot be heard clearly" and "can be spoken again", in the semantic database appear in the text texts is judged through a semantic matching mode, and preferably, the synonym matching technology is adopted to judge whether the voice calls or words with the semantic information, which represent that the voice quality is poor, appear in the text texts. When the word text corresponding to the voice signal in the IP telephone conversation process appears similar voice conversation or words with semantic information, such as 'inaudible', 'not clearly heard', and're-speaking', in the semantic database, the frequency and/or times of appearance of the voice conversation or words of the type in the IP telephone conversation process are/is calculated, and the voice conversation or words of the type are used as judgment factors for judging the conversation quality. The speech recognition and the synonym matching are prior art, and are not limited herein, for example, LSTM may be used as the speech recognition method.
And step 240, determining the conversation quality of the network telephone in the conversation process according to the interval period, the voice amplitude and the frequency of the words with poor voice quality.
In this embodiment, after the interval period, the voice amplitude, and the frequency of the words with poor voice quality of the voice signal in the IP phone call process obtained in step 220 and step 230 are determined, the obtained parameter information may be used as an influence factor that affects the voice call quality, and since the influence degrees of the several influence factors on the voice call quality in the IP phone call process are different, the influence degrees of the interval period, the voice amplitude, and the frequency of the words with poor voice quality on the call quality of the IP phone may be analyzed, the weight ratios of the interval period, the voice amplitude, and the frequency of the words with poor voice quality are determined according to the respective influence degrees, and finally the call quality of the IP phone is determined by calculation according to the interval period, the voice amplitude, the frequency of the words with poor voice quality, and the respective corresponding weight ratios.
The embodiment of the invention provides a method for determining the quality of a network telephone, which is used for detecting the call quality in the call process of an IP telephone by further combining the frequency of words with poor voice quality in the call process of the IP telephone after determining the interval period and the voice amplitude of a voice signal, solving the problem of determining the call quality in the call process of the IP telephone and realizing the effect of quickly determining the call quality according to the frequency of words with poor voice quality in the call process under the condition of poor call quality of the IP telephone.
EXAMPLE III
Fig. 3 is a flowchart of a method for determining the quality of the internet phone according to a third embodiment of the present invention, and the embodiment of the present invention further optimizes the step of determining the call quality of the internet phone during the call process according to the interval period, the speech amplitude, and the frequency of the word with poor speech quality based on the first embodiment and the second embodiment. As shown in fig. 3, the method for determining the quality of the internet phone includes:
and step 310, acquiring a voice signal in the conversation process of the network telephone.
And step 320, determining the interval period and the voice amplitude of the voice signal.
In a preferred implementation manner of this embodiment, the determining the interval period and the voice amplitude of the voice signal includes: carrying out amplitude detection on the voice signal, and determining an interval period of the voice signal according to the result of the amplitude detection; and counting the amplitude of the voice signal according to the interval period, and determining the voice amplitude of the voice signal.
And step 330, determining the frequency of the words with poor voice quality in the voice signal.
In a preferred implementation manner of this embodiment, the determining the frequency of the occurrence of words with poor speech quality in the speech signal includes: converting the voice signal into a text signal by adopting a voice recognition technology; and determining whether the words marked with poor voice quality appear in the text signal or not through semantic matching, and if so, calculating the frequency of the words marked with poor voice quality appearing in the text signal.
And step 340, determining the white noise probability of the voice signal.
In this embodiment, when the poor call quality occurs during the IP phone call, a white noise signal is generated outside the voice signal, so that the white noise detection is performed on the acquired voice signal during the IP phone call, and the white noise detection result is used as an evaluation factor for determining the voice call quality. Where white noise detection of a speech signal is a known method, the white noise detection may use any known white noise detection method. Illustratively, the target detection RCNN network is used to perform classification training on calibrated white noise-containing speech and white noise-free speech samples, and the obtained output probability of the target detection RCNN network is the output probability of the white noise model. The white noise is in direct proportion to the output probability of the white noise model.
And step 350, determining the call quality of the network telephone call process according to the interval period, the voice amplitude, the frequency of words with poor voice quality and the white noise probability.
In this embodiment, after determining the interval period, the voice amplitude, the frequency of words with poor voice quality and the white noise probability of the acquired voice signal in the IP telephone call process through steps 320, 330 and 340, the obtained parameter information can be used as an influencing factor influencing the voice call quality, since the influence factors have different degrees on the voice call quality in the IP telephone call process, therefore, the influence degree of the interval period, the voice amplitude, the frequency of words with poor voice quality and the white noise probability on the call quality of the IP telephone can be respectively analyzed, and determining the weight proportion of the interval period, the voice amplitude, the frequency of the words with poor voice quality and the white noise probability according to the influence degree result, and finally performing comprehensive calculation according to the interval period, the voice amplitude, the frequency of the words with poor voice quality, the white noise probability and the respective corresponding weight proportion to determine the call quality of the IP phone.
In a preferred implementation manner of this embodiment, the determining, according to the interval period, the voice amplitude, the frequency of words with poor voice quality, and the white noise probability, the call quality of the internet phone call process includes:
acquiring the call quality of the network telephone call process according to a formula Q-alpha N-beta J + gamma A-S;
q is the call quality of the network telephone call process, N is the white noise probability of the voice signal, J is the interval period of the voice signal, A is the voice amplitude of the voice signal, S is the frequency of words with poor voice quality appearing in the voice signal, alpha is the weight factor of the white noise probability, beta is the weight factor of the interval period, gamma is the weight factor of the voice amplitude, and is the weight factor of the frequency of words with poor quality.
Specifically, α, β, and γ are determinations of weighting factors, which are theoretically obtained through experiments, and the initial value is a real number greater than zero, for example, α is 2.0, β is 2.0, and γ is 1.0 and 1.0. Through the telephone call quality evaluation model Q, whether the call quality is poor in the IP telephone call process can be judged, wherein the call quality is in direct proportion to the value of Q. It should be noted that the setting of the weighting factors α, β, γ can be adaptively adjusted according to the actual situation, and is not limited herein.
The embodiment of the invention provides a method for determining the quality of a network telephone, which comprehensively considers the call quality in the IP telephone call process through the interval period of a voice signal, the voice amplitude, the frequency of words with poor voice quality and the white noise probability, particularly adopts a call quality determination ground model, well solves the problem of call quality determination in the IP telephone call process, and realizes the effect of quickly determining the call quality under the condition of poor call quality of the IP telephone.
Example four
Fig. 4 is a schematic structural diagram of a network telephone quality determination apparatus according to a fourth embodiment of the present invention; the device executes the method for determining the quality of the network telephone provided by any one of the above embodiments, and the device can be implemented in a software and/or hardware manner. As shown in fig. 4, the network telephone quality determination apparatus includes:
the voice acquiring module 410 is configured to acquire a voice signal during a voice over internet protocol call.
A parameter determining module 420, configured to determine an interval period and a voice amplitude of the voice signal.
In a preferred implementation manner of this embodiment, the parameter determining module includes:
the amplitude detection and period determination unit is used for carrying out amplitude detection on the voice signal and determining the interval period of the voice signal according to the result of the amplitude detection;
and the voice amplitude determining unit is used for counting the amplitude of the voice signal according to the interval period and determining the voice amplitude of the voice signal.
And the quality determining module 430 is configured to determine the call quality of the internet phone call process according to the interval period and the voice amplitude.
In a preferred implementation manner of this embodiment, the quality determining module includes:
the word frequency detection unit is used for determining the word frequency with poor voice quality in the voice signal;
and the call quality determining unit is used for determining the call quality of the network telephone call process according to the interval period, the voice amplitude and the frequency of the words with poor voice quality.
Wherein, the word frequency detection unit specifically comprises:
the voice conversion unit is used for converting the voice signal into a text signal by adopting a voice recognition technology; and the word frequency detection subunit is used for determining whether words with poor speech quality are marked in the text signal through semantic matching, and if the words with poor speech quality are marked in the text signal, calculating the frequency of the words with poor speech quality marked in the text signal.
The call quality determination unit includes
The noise probability calculating subunit is used for determining the white noise probability of the voice signal; and the conversation quality determining subunit is used for determining the conversation quality of the network telephone in the conversation process according to the interval period, the voice amplitude, the frequency of the words with poor voice quality and the white noise probability.
The sub-unit for determining call quality specifically comprises:
acquiring the call quality of the network telephone call process according to a formula Q-alpha N-beta J + gamma A-S;
q is the call quality of the network telephone call process, N is the white noise probability of the voice signal, J is the interval period of the voice signal, A is the voice amplitude of the voice signal, S is the frequency of words with poor voice quality appearing in the voice signal, alpha is the weight factor of the white noise probability, beta is the weight factor of the interval period, gamma is the weight factor of the voice amplitude, and is the weight factor of the frequency of words with poor quality.
The network telephone quality determination device provided by the embodiment of the invention can execute the network telephone quality determination method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects for executing the method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of a computer device according to a fifth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary computer device 512 suitable for use in implementing embodiments of the present invention. The computer device 512 shown in FIG. 5 is only an example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 5, computer device 512 is in the form of a general purpose computing device. Components of computer device 512 may include, but are not limited to: one or more processors 516, a system memory 528, and a bus 518 that couples the various system components including the system memory 528 and the processors 516.
The system memory 528 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)530 and/or cache memory 532. The computer device 512 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 534 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, and commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 518 through one or more data media interfaces. Memory 528 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 540 having a set (at least one) of program modules 542, including but not limited to an operating system, one or more application programs, other program modules, and program data, may be stored in, for example, the memory 528, each of which examples or some combination may include an implementation of a network environment. The program modules 542 generally perform the functions and/or methods of the described embodiments of the invention.
The computer device 512 may also communicate with one or more external devices 514 (e.g., keyboard, pointing device, display 524, etc.), with one or more devices that enable a user to interact with the computer device 512, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 512 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 522. Also, computer device 512 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via network adapter 520. As shown, the network adapter 520 communicates with the other modules of the computer device 512 via the bus 518. It should be appreciated that although not shown in FIG. 5, other hardware and/or software modules may be used in conjunction with computer device 512, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processor 516 executes various functional applications and data processing by running programs stored in the system memory 528, for example, implementing the method for determining the quality of the network telephone provided by the embodiment of the present invention includes:
acquiring a voice signal in the communication process of the network telephone;
determining interval period and voice amplitude of the voice signal;
and determining the call quality of the network telephone call process according to the interval period and the voice amplitude.
EXAMPLE six
The sixth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for determining the quality of a network telephone, which includes:
acquiring a voice signal in the communication process of the network telephone;
determining interval period and voice amplitude of the voice signal;
and determining the call quality of the network telephone call process according to the interval period and the voice amplitude.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (12)
1. A method for determining the quality of a network telephone, comprising:
acquiring a voice signal in the communication process of the network telephone;
carrying out amplitude detection on the voice signal, and determining an interval period of the voice signal according to the result of the amplitude detection; counting the amplitude of the voice signal according to the interval period, and determining the voice amplitude of the voice signal; the interval period can represent the discontinuous frequency of the voice signal, and an inverse relation exists between the interval period and the frequency;
determining the call quality of the network telephone call process according to the interval period and the voice amplitude; when the interval period of the voice signal is short and repeated, the probability of poor call quality is high.
2. The method of claim 1, wherein said determining the speech quality of the voice over internet protocol call process based on the interval period and the speech amplitude comprises:
determining the frequency of words with poor voice quality in the voice signal;
and determining the conversation quality of the network telephone in the conversation process according to the interval period, the voice amplitude and the frequency of the words with poor voice quality.
3. The method of claim 2, wherein determining the frequency of poor speech quality words in the speech signal comprises:
converting the voice signal into a text signal by adopting a voice recognition technology;
and determining whether the words marked with poor voice quality appear in the text signal or not through semantic matching, and if so, calculating the frequency of the words marked with poor voice quality appearing in the text signal.
4. The method of claim 2, wherein the determining the speech quality of the voice over internet protocol call process according to the interval period, the speech amplitude and the frequency of the speech quality-poor word comprises:
determining a white noise probability of the speech signal;
and determining the call quality of the network telephone call process according to the interval period, the voice amplitude, the frequency of words with poor voice quality and the white noise probability.
5. The method of claim 4, wherein the determining the call quality of the voice over internet protocol call process according to the interval period, the voice amplitude, the voice quality poor word frequency and the white noise probability comprises:
acquiring the call quality of the network telephone call process according to a formula Q-alpha N-beta J + gamma A-S;
q is the call quality of the network telephone call process, N is the white noise probability of the voice signal, J is the interval period of the voice signal, A is the voice amplitude of the voice signal, S is the frequency of words with poor voice quality appearing in the voice signal, alpha is the weight factor of the white noise probability, beta is the weight factor of the interval period, gamma is the weight factor of the voice amplitude, and is the weight factor of the frequency of words with poor quality.
6. An internet phone quality determination apparatus, comprising:
the voice acquisition module is used for acquiring a voice signal in the conversation process of the network telephone;
the parameter determination module is used for determining the interval period and the voice amplitude of the voice signal; the interval period can represent the discontinuous frequency of the voice signal, and an inverse relation exists between the interval period and the frequency; the parameter determination module comprises: the amplitude detection and period determination unit is used for carrying out amplitude detection on the voice signal and determining the interval period of the voice signal according to the result of the amplitude detection; the voice amplitude determining unit is used for counting the amplitude of the voice signal according to the interval period and determining the voice amplitude of the voice signal;
the quality determining module is used for determining the conversation quality of the network telephone in the conversation process according to the interval period and the voice amplitude; when the interval period of the voice signal is short and repeated, the probability of poor call quality is high.
7. The apparatus of claim 6, wherein the quality determination module comprises:
the word frequency detection unit is used for determining the word frequency with poor voice quality in the voice signal;
and the call quality determining unit is used for determining the call quality of the network telephone call process according to the interval period, the voice amplitude and the frequency of the words with poor voice quality.
8. The apparatus of claim 7, wherein the word frequency detection unit comprises:
the voice conversion unit is used for converting the voice signal into a text signal by adopting a voice recognition technology;
and the word frequency detection subunit is used for determining whether words with poor speech quality are marked in the text signal through semantic matching, and if the words with poor speech quality are marked in the text signal, calculating the frequency of the words with poor speech quality marked in the text signal.
9. The apparatus of claim 7, wherein the call quality determination unit comprises:
the noise probability calculating subunit is used for determining the white noise probability of the voice signal;
and the conversation quality determining subunit is used for determining the conversation quality of the network telephone in the conversation process according to the interval period, the voice amplitude, the frequency of the words with poor voice quality and the white noise probability.
10. The apparatus according to claim 9, wherein the sub-unit for determining call quality specifically comprises:
acquiring the call quality of the network telephone call process according to a formula Q-alpha N-beta J + gamma A-S;
q is the call quality of the network telephone call process, N is the white noise probability of the voice signal, J is the interval period of the voice signal, A is the voice amplitude of the voice signal, S is the frequency of words with poor voice quality appearing in the voice signal, alpha is the weight factor of the white noise probability, beta is the weight factor of the interval period, gamma is the weight factor of the voice amplitude, and is the weight factor of the frequency of words with poor quality.
11. A computer device, characterized in that the computer device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method for determining quality of internet telephony as claimed in any one of claims 1 to 5.
12. A computer-readable storage medium on which a computer program is stored, which, when being executed by a processor, carries out the method for determining the quality of a network telephone according to any one of claims 1 to 5.
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 CN107580155A (en) | 2018-01-12 |
| CN107580155B true 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) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN110289014B (en) * | 2019-05-21 | 2021-11-19 | 华为技术有限公司 | Voice quality detection method and electronic equipment |
| 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 |
| 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 |
| 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 |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6754337B2 (en) * | 2002-01-25 | 2004-06-22 | Acoustic Technologies, Inc. | Telephone having four VAD circuits |
| US7738368B2 (en) * | 2005-11-10 | 2010-06-15 | At&T Intellectual Property I, L.P. | Voice over internet protocol codec adjustment |
-
2017
- 2017-08-31 CN CN201710773750.6A patent/CN107580155B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107580155A (en) | 2018-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107580155B (en) | Network telephone quality determination method, network telephone quality determination device, computer equipment and storage medium | |
| CN107910014B (en) | Echo cancellation test method, device and test equipment | |
| JP5053285B2 (en) | Determining audio device quality | |
| US9412371B2 (en) | Visualization interface of continuous waveform multi-speaker identification | |
| US10237412B2 (en) | System and method for audio conferencing | |
| US9979769B2 (en) | System and method for audio conferencing | |
| CN112071328B (en) | Audio noise reduction | |
| US20140214426A1 (en) | System and method for improving voice communication over a network | |
| US9583108B2 (en) | Voice detection for automated communication system | |
| MX2008016354A (en) | Detecting an answering machine using speech recognition. | |
| US7162421B1 (en) | Dynamic barge-in in a speech-responsive system | |
| CN107578770A (en) | Networking telephone audio recognition method, device, computer equipment and storage medium | |
| WO2015034633A1 (en) | Method for non-intrusive acoustic parameter estimation | |
| KR102307355B1 (en) | Method and apparatus for improving call quality in noisy environment | |
| CN108010539A (en) | A kind of speech quality assessment method and device based on voice activation detection | |
| WO2023040523A1 (en) | Audio signal processing method and apparatus, electronic device, and storage medium | |
| US10204634B2 (en) | Distributed suppression or enhancement of audio features | |
| US20120053937A1 (en) | Generalizing text content summary from speech content | |
| US11146607B1 (en) | Smart noise cancellation | |
| CN111326159B (en) | Voice recognition method, device and system | |
| US20180082703A1 (en) | Suitability score based on attribute scores | |
| CN112133324A (en) | Call state detection method, device, computer system and medium | |
| KR102583434B1 (en) | Method and system for evaluating quality of voice counseling | |
| US8244538B2 (en) | Measuring double talk performance | |
| CN112216285B (en) | Multi-user session detection method, system, mobile terminal and storage medium |
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 |