CN116312594A

CN116312594A - Method, apparatus and computer readable storage medium for dynamically adjusting speech quality

Info

Publication number: CN116312594A
Application number: CN202310186997.3A
Authority: CN
Inventors: 黄玉玉; 沈天豪; 高尚
Original assignee: Suzhou Huichuan Control Technology Co Ltd
Current assignee: Suzhou Huichuan Control Technology Co Ltd
Priority date: 2023-03-01
Filing date: 2023-03-01
Publication date: 2023-06-23

Abstract

The invention discloses a method, equipment and a computer readable storage medium for dynamically adjusting voice quality, wherein the method comprises the following steps: acquiring an initial sound signal in the surrounding environment; gradually performing volume gain on the initial sound signal according to a preset volume gain adjustment step length and the current volume gain intensity so as to obtain a volume gain sound signal; gradually performing echo cancellation on the volume gain sound signal according to a preset echo cancellation intensity adjustment step length and the current echo cancellation intensity to obtain an echo cancellation sound signal after echo cancellation; the method for dynamically adjusting the voice quality is applied to various voice intercom equipment, so that the occurrence of voice distortion and top elimination phenomena which are easily caused by adjusting voice by adopting fixed voice parameters is avoided, and the clear integrity of voice intercom is improved.

Description

Method, apparatus and computer readable storage medium for dynamically adjusting speech quality

Technical Field

The present invention relates to the field of sound processing technologies, and in particular, to a method and apparatus for dynamically adjusting speech quality, and a computer readable storage medium.

Background

One end of a voice processing module on various existing devices with voice intercom functions is connected with an intercom device, and the other end of the voice processing module is connected with a gateway to carry out voice communication through a communication network. In the process of transmitting voice, most of the existing product equipment adjusts voice call quality by solidifying some voice parameters in advance, and the mode of realizing voice adjustment comprises hardware adjustment and software adjustment, for example, some product equipment adjusts resistance and capacitance fixedly through hardware to carry out adjustment filtering, adjust the size of collected voice and adjust the suppression intensity of echo and noise; some product devices solidify sound parameters in advance through software to realize the adjustment of voice call quality.

In the current voice adjusting mode, whether hardware or software is adopted, the method is comparatively solidified, and various sounds doped in different external environments cannot be considered to have different influences on voice call quality, so that the voice adjusting mode adopting fixed voice parameters can cause unsatisfactory voice call quality effect after adjustment, and even normal voice call among users can be seriously influenced.

Disclosure of Invention

The invention mainly aims to provide a method, equipment and a computer readable storage medium for dynamically adjusting voice quality, and aims to solve the technical problem that the voice quality effect after adjustment is not ideal due to the fact that a fixed voice parameter is adopted to adjust voice at present.

To achieve the above object, the present invention provides a method for dynamically adjusting voice quality, the method comprising the steps of:

acquiring an initial sound signal in the surrounding environment;

gradually performing volume gain on the initial sound signal according to a preset volume gain adjustment step length and current volume gain intensity so as to obtain a volume gain sound signal;

gradually carrying out echo cancellation on the volume gain sound signal according to a preset echo cancellation intensity adjustment step length and the current echo cancellation intensity so as to obtain an echo cancellation sound signal after echo cancellation;

and gradually carrying out noise elimination on the echo elimination sound signal according to a preset noise elimination intensity adjustment step length and the current noise elimination intensity so as to obtain a voice signal after noise elimination.

Optionally, before the step of gradually performing volume gain on the initial sound signal according to the preset volume gain adjustment step size and the current volume gain intensity to obtain a volume gain sound signal, the method further includes:

Comparing the amplitude of the initial sound signal with a preset amplitude interval;

if the amplitude of the initial sound signal is not in the amplitude interval, executing the step of gradually carrying out volume gain on the initial sound signal according to the preset volume gain adjustment step length and the current volume gain intensity so as to obtain a volume gain sound signal; the amplitude of the volume gain sound signal is in the amplitude interval.

Optionally, before the step of performing echo cancellation on the volume gain sound signal step by step according to a preset echo cancellation intensity adjustment step size and a current echo cancellation intensity to obtain an echo cancellation sound signal after echo cancellation, the method includes:

determining an echo signal in the volume gain sound signal, and carrying out echo cancellation on the volume gain sound signal based on the current echo cancellation intensity so as to obtain an echo sound signal to be checked;

comparing the echo sound signal to be checked with the echo signal to obtain a comparison result, and determining a corresponding preset echo cancellation intensity adjustment step length according to the comparison result; the preset echo cancellation intensity adjustment step length is used for adjusting the current echo cancellation intensity;

And taking the sound signal to be checked of the echo as the volume gain sound signal, and executing the step of gradually carrying out echo cancellation on the volume gain sound signal according to a preset echo cancellation intensity adjustment step length and the current echo cancellation intensity so as to obtain an echo cancellation sound signal after echo cancellation.

Optionally, the step of comparing the echo sound signal to be verified with the echo signal to obtain a comparison result, and determining a corresponding preset echo cancellation intensity adjustment step according to the comparison result includes:

comparing the echo signal to be verified with the echo signal to judge whether an overlapping signal exists between the echo signal to be verified and the echo signal;

if the overlapping signals exist, determining that the comparison result is the comparison result of echo signal residues;

determining a corresponding first preset echo cancellation intensity adjustment step length according to the comparison result of the echo signal residues; the first preset echo cancellation strength adjustment step size is a positive value.

Optionally, after the step of determining whether there is an overlapping signal between the echo sound signal to be checked and the echo signal, the method further includes:

If no overlapping signal exists, determining the comparison result as a comparison result of no echo signal residue;

determining a corresponding second preset echo cancellation intensity adjustment step length according to a comparison result of no residue of the echo signal; the second preset echo cancellation strength adjustment step is negative.

Optionally, the step of performing echo cancellation on the volume gain sound signal step by step according to a preset echo cancellation intensity adjustment step length and a current echo cancellation intensity to obtain an echo cancellation sound signal after echo cancellation includes:

combining a preset echo cancellation intensity adjustment step length and a current echo cancellation intensity to adjust the current echo cancellation intensity, thereby obtaining an adjusted current echo cancellation intensity;

performing echo cancellation on the volume gain sound signal by using the adjusted current echo cancellation intensity;

and taking the adjusted current echo cancellation intensity as the current echo cancellation intensity, and circularly executing the step of combining a preset echo cancellation intensity adjustment step length and the current echo cancellation intensity to adjust the current echo cancellation intensity so as to obtain the adjusted current echo cancellation intensity, thereby obtaining an echo cancellation sound signal after echo cancellation.

determining a volume gain sound frequency band signal exceeding an echo threshold value in the volume gain sound signal;

and gradually carrying out echo cancellation on the volume gain sound frequency band signals in the volume gain sound signals according to a preset echo cancellation intensity adjustment step length and the current echo cancellation intensity so as to obtain echo cancellation sound signals after echo cancellation.

Optionally, the step of performing noise cancellation on the echo cancellation sound signal step by step according to a preset noise cancellation intensity adjustment step size and a current noise cancellation intensity to obtain a noise cancelled speech signal includes:

combining a preset noise elimination intensity adjustment step length and a current noise elimination intensity to adjust the current noise elimination intensity, so as to obtain the adjusted current noise elimination intensity;

performing noise cancellation on the echo cancellation sound signal using the adjusted current noise cancellation intensity;

and the step of circularly executing the step of combining the preset noise elimination intensity adjustment step length and the current noise elimination intensity to adjust the current noise elimination intensity to obtain the adjusted current noise elimination intensity so as to obtain a voice signal after noise elimination.

In addition, to achieve the above object, the present invention also provides a device for dynamically adjusting voice quality, the device comprising:

the sound acquisition module is used for acquiring initial sound signals in the surrounding environment;

the volume gain module is used for gradually carrying out volume gain on the initial sound signal according to a preset volume gain adjustment step length and the current volume gain intensity so as to obtain a volume gain sound signal;

the echo cancellation module is used for gradually performing echo cancellation on the volume gain sound signal according to a preset echo cancellation intensity adjustment step length and the current echo cancellation intensity so as to obtain an echo cancellation sound signal after echo cancellation;

and the noise elimination module is used for gradually eliminating the noise of the echo elimination sound signal according to the preset noise elimination intensity adjustment step length and the current noise elimination intensity so as to obtain a voice signal after noise elimination.

In addition, in order to achieve the above object, the present invention also provides a device for dynamically adjusting voice quality, which includes a processor, a memory, and a dynamically adjusting voice quality program stored on the memory and executable by the processor, wherein the dynamically adjusting voice quality program, when executed by the processor, implements the steps of the method for dynamically adjusting voice quality as described above.

The present invention also provides a computer readable storage medium having stored thereon a dynamically adjusted speech quality program, wherein the dynamically adjusted speech quality program, when executed by a processor, implements the steps of the dynamically adjusted speech quality method as described above.

According to the method for dynamically adjusting the voice quality, the initial voice signals in the surrounding environment are collected, the current volume gain intensity is dynamically adjusted through the preset volume gain adjustment step length based on the characteristics of the initial voice signals, and then the initial voice signals are gradually subjected to dynamic volume gain through the dynamically adjusted current volume gain intensity, so that the collected initial voice signals are more targeted in adjustment, the volume of the initial voice signals is stably increased in a dynamic balance mode under the condition that the characteristics of the initial voice signals are met, meanwhile, the negligence of the voice signals in the gain process is avoided, the volume effect of the volume gain voice signals is more ideal, and the hearing feeling is more met. Further, the current echo cancellation intensity is dynamically adjusted by presetting the echo cancellation intensity adjustment step length, and then the echo signals in the volume gain sound signals are gently and gradually cancelled by the dynamically adjusted current echo cancellation intensity, so that the echo cancellation of the volume gain sound signals in a dynamic balance mode is realized, the influence of the echo on the voice quality is avoided, and the obtained echo cancellation sound signals enable the voice sent by the user in the initial sound signals to be clearer. Finally, the same principle, through the dynamic adjustment of the preset noise elimination intensity adjustment step length to the current noise elimination intensity, the noise signal of the echo elimination sound signal is gently and gradually eliminated in a dynamic balance mode, the influence of noise on voice quality is avoided, the voice output corresponding to the voice signal after noise elimination is clear, the voice quality effect felt at one end of the received voice signal is more excellent, the voice conversation effect is more ideal and accords with the user expectation, and the voice conversation experience of the user is greatly improved.

The method for dynamically adjusting the voice quality fully considers the scheme by taking different sound characteristics of different surrounding environments into consideration, thereby realizing dynamic adjustment of each sound signal starting from the initial sound signal in a mode of gradually adjusting each voice adjusting intensity (current volume gain intensity, current echo eliminating intensity and current noise eliminating intensity) on the acquired initial sound signal, being capable of carrying out targeted gentle adjustment on each acquired initial sound signal based on the characteristics of surrounding environment sound compared with a mode of adjusting the voice by adopting fixed sound parameters, avoiding the occurrence of voice distortion and top eliminating phenomena easily caused by adjusting the voice by adopting fixed sound parameters, and greatly improving the definition and the complete stability of voice intercom.

Drawings

FIG. 1 is a schematic diagram of a hardware operating environment of a dynamically adjusted voice quality device according to an embodiment of the present invention;

FIG. 2 is a flowchart of a method for dynamically adjusting speech quality according to a first embodiment of the present invention;

FIG. 3 is a detailed flowchart of step S30 of a method for dynamically adjusting speech quality according to an embodiment of the present invention;

FIG. 4 is a detailed flowchart of step S40 of a method for dynamically adjusting speech quality according to an embodiment of the present invention;

FIG. 5 is a flowchart illustrating a method for dynamically adjusting voice quality according to an embodiment of the present invention before step S30;

FIG. 6 is a detailed flowchart of step S310 of a method for dynamically adjusting speech quality according to an embodiment of the present invention;

fig. 7 is a schematic diagram of a voice intercom application flow involved in the method for dynamically adjusting voice quality according to the present invention;

FIG. 8 is a schematic diagram of an application flow of voice signal conditioning related to a method for dynamically adjusting voice quality according to the present invention;

fig. 9 is a schematic diagram of a frame structure of a device for dynamically adjusting voice quality according to the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The embodiment of the invention provides a dynamic voice quality adjusting device which can be an adapter plate, can be applied to various voice intercom devices, such as intelligent terminals of mobile phones, tablet computers, personal computers and the like, and can also be applied to equipment facilities of elevators, mines and the like needing voice intercom. By taking the adapter plate as an example, the sound collecting device comprising the microphone of various voice intercom equipment can be electrically connected with the adapter plate, so that the collected sound signals of the surrounding environment are adjusted and optimized through the adapter plate, and therefore clearer and complete voice is obtained.

As shown in fig. 1, fig. 1 is a schematic structural diagram of a hardware operating environment of a dynamically adjusting voice quality device according to an embodiment of the present invention.

As shown in fig. 1, the dynamically adjusting voice quality device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display (Display), an input unit such as a dashboard, and the optional user interface 1003 may also include a standard wired interface, a wireless interface. Network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a WIFI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above. A dynamic voice quality adjustment program may be included in the memory 1005, which is a computer storage medium.

Those skilled in the art will appreciate that the hardware configuration shown in fig. 1 does not constitute a limitation of the apparatus, and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components.

With continued reference to fig. 1, the memory 1005 in fig. 1, which is a computer readable storage medium, may include an operating system, a user interface module, a network communication module, and a program for dynamically adjusting voice quality.

In fig. 1, the network communication module is mainly used for connecting with a server and performing data communication with the server; and the processor 1001 may call a dynamically adjusted voice quality program stored in the memory 1005 and perform the following operations:

acquiring an initial sound signal in the surrounding environment;

Further, the processor 1001 may call a dynamically adjusted voice quality program stored in the memory 1005, and further perform the following operations:

Based on the above hardware structure of the dynamic voice quality adjusting device, various embodiments of the method for dynamically adjusting voice quality according to the present invention are presented.

The embodiment of the invention provides a method for dynamically adjusting voice quality.

Referring to fig. 2, fig. 2 is a flow chart of a method for dynamically adjusting voice quality according to a first embodiment of the present invention; in a first embodiment of the present invention, the method for dynamically adjusting voice quality comprises the steps of:

Step S10, acquiring an initial sound signal in the surrounding environment;

in this embodiment, the initial sound signal may be continuous, including the current time node and the subsequent time node continuously collecting the acquired sound signals.

The initial sound signal in the surrounding environment at least comprises a voice signal sent by a user in the surrounding environment, a noise signal in the surrounding environment and an echo signal sent by a loudspeaker of a voice intercom (communication) device in the surrounding environment (namely, a voice signal sent by a far-end user). It should be noted that the voice intercom device herein includes various devices and terminals having voice intercom function, such as a mobile phone, a tablet computer, an elevator, and the like, and is not limited herein.

Step S20, gradually performing volume gain on the initial sound signal according to a preset volume gain adjustment step length and current volume gain intensity to obtain a volume gain sound signal;

before understanding the preset volume gain adjustment step size, the concept of the step size can be understood: in the programming language, a numerical value is added with a certain number (namely step length) in each operation to repeatedly execute the operation; in simplex optimization, the simplex distance is shifted forward each time.

The preset volume gain adjustment step length is the step length for adjusting the current volume gain intensity each time so as to change the current volume gain intensity. The preset volume gain adjustment step length can be set according to actual needs, and is not limited herein. For example, the setting may be performed according to a rule of dividing the volume gain intensity, the volume gain intensity is set to be 20 levels, the preset volume gain adjustment step length may be increased or decreased by 1 level, that is, the preset volume gain adjustment step length may be represented as +1 or-1. When the current volume gain intensity is 10 and the preset volume gain adjustment step length is +1, the adjusted current volume gain intensity is 11.

The current volume gain intensity may be a default volume gain intensity when the initial sound signal adjustment is performed by the sound collected just before the initial sound signal adjustment, for example, the default volume gain intensity is 10 th level, and then the volume gain intensity after the current volume gain intensity is adjusted by the preset volume gain adjustment step length is used as the current volume gain intensity, that is, the current volume gain intensity is a dynamically changing process from the default volume gain intensity since the initial sound signal adjustment is performed.

The volume gain of the initial sound signal can be performed through a default volume gain intensity serving as the current volume gain intensity and a preset volume gain algorithm (the current volume gain intensity belongs to the calculation parameters of the volume gain algorithm, the algorithm is not improved, and details are omitted herein), if the initial sound signal after gain fails to reach the expectation, the default volume gain intensity needs to be adjusted through a preset volume gain adjustment step length, so that the adjusted current volume gain intensity serves as the current volume gain intensity, the initial sound signal is subjected to gain by combining the preset volume gain algorithm, and the current volume gain intensity is continuously adjusted until the volume corresponding to the initial sound signal reaches the user expectation by utilizing the current volume gain intensity, so that the volume gain sound signal is obtained.

In an embodiment, before the step S20, the method further includes:

step a, comparing the amplitude of the initial sound signal with a preset amplitude interval;

the amplitude of the sound signal represents the volume of the sound, namely, the larger the amplitude is, the larger the corresponding volume is, and conversely, the smaller the volume is. An amplitude interval (also referred to as a volume interval) [15db,60db ] may be preset, and the amplitude interval is the volume corresponding to normal speech of a person, or other interval sizes may be set as needed, which is not limited herein.

The amplitude of the initial sound signal is compared with the amplitude interval, that is, the sound volume corresponding to the initial sound signal is compared with the volume interval. And the amplitude of the initial sound signal may be the amplitude after the default volume gain intensity adjustment.

Step b, if the amplitude of the initial sound signal is not within the amplitude interval, executing the step of gradually performing volume gain on the initial sound signal according to a preset volume gain adjustment step length and the current volume gain intensity so as to obtain a volume gain sound signal; the amplitude of the volume gain sound signal is in the amplitude interval.

If the amplitude of the initial sound signal is not within the amplitude interval, the current volume gain strength is unsuitable for the initial sound signal, so that the sound is too loud to cause the sound distortion to be topped off or too small to cause the other party of the voice call to be inaudible. Therefore, the step S20 needs to be executed, the current volume gain intensity is adjusted by presetting a volume gain adjustment step, so that the current volume gain intensity is increased or decreased, and the volume gain of the initial sound signal is continuously performed by the adjusted current volume gain intensity, that is, the amplitude of the initial sound signal is changed until the amplitude of the obtained volume gain sound signal is located in the amplitude interval, so that the adjustment of the current volume gain intensity is suspended.

The current volume gain intensity when the volume gain sound signal is obtained can be stored, and the initial sound signal collected later is subjected to volume adjustment by utilizing the stored current volume gain intensity, so that the volume adjustment of the sound signal is realized more efficiently and the voice quality is improved under the condition of conforming to the surrounding environment.

By the embodiment of the invention, the volume of the sound is regulated in a progressive dynamic mode, the regulated volume of the sound is not suddenly reduced or increased in the process of increasing or decreasing the volume, the heard sound is prevented from being negligibly small, which is equivalent to a transition process of slowly pulling up or down in a moderating curve form, and the quality and the actual auditory sensation of a user during voice communication are greatly improved.

In an embodiment, the amplitude of the voice signal of the voice of the person in the initial sound signal may be compared with a preset amplitude interval; if the amplitude of the voice signal is not in the amplitude interval, gradually performing volume gain on the voice signal in the initial sound signal according to a preset volume gain adjustment step length and the current volume gain intensity so as to obtain a volume gain sound signal; the amplitude of the voice signal of the voice of the man in the volume gain voice signal is located in the amplitude range. By the embodiment, the most important voice signal in the voice call can be adjusted in a targeted manner without volume gain on noise and echo, so that the voice is more prominent, clear and bright.

Step S30, according to the preset echo cancellation intensity adjustment step length and the current echo cancellation intensity, the echo cancellation is gradually carried out on the volume gain sound signal so as to obtain an echo cancellation sound signal after echo cancellation;

similarly, the preset echo cancellation strength adjustment step length is a step length for adjusting the current echo cancellation strength each time so as to change the current echo cancellation strength. The preset echo cancellation strength adjustment step length may also be set according to actual needs, which is not limited herein, for example, may be set according to a division rule of the echo cancellation strength, for example, the echo cancellation strength may be set to 30 levels, which is not described herein.

The current echo cancellation strength may be a default echo cancellation strength when the volume gain sound signal is initially adjusted, for example, the default echo cancellation strength is a level 15, and then the echo cancellation strength after the current echo cancellation strength is adjusted by the preset echo cancellation strength adjustment step length is used as the current echo cancellation strength, that is, the current echo cancellation strength is a dynamically changing process from the default echo cancellation strength since the volume gain sound signal is adjusted.

The echo cancellation operation may be performed on the volume gain sound signal by using the default echo cancellation strength as the current echo cancellation strength and a preset echo cancellation algorithm (the current echo cancellation strength belongs to the calculation parameters of the echo cancellation algorithm), which is not improved in the present invention, and if the volume gain sound signal after the echo cancellation operation fails to reach the expected value, that is, there is an echo, the default echo cancellation strength needs to be adjusted by using the preset echo cancellation strength adjustment step length, so that the adjusted current echo cancellation strength is used as the current echo cancellation strength, the echo cancellation is performed on the volume gain sound signal in combination with the preset echo cancellation algorithm, and the current echo cancellation strength is continuously adjusted until the echo in the volume gain sound signal is completely cancelled by using the current echo cancellation strength, so as to obtain an echo cancellation sound signal after the echo cancellation, that is, an echo cancellation sound signal without the echo signal.

Referring to fig. 3, in an embodiment, the step S30 includes:

step S31, combining a preset echo cancellation intensity adjustment step length and a current echo cancellation intensity to adjust the current echo cancellation intensity, thereby obtaining an adjusted current echo cancellation intensity;

the preset echo cancellation intensity adjustment step length is combined with the current echo cancellation intensity, namely the preset echo cancellation intensity adjustment step length and the current echo cancellation intensity are added, when the preset echo cancellation intensity adjustment step length is positive, the adjusted current echo cancellation intensity is increased, otherwise, the adjusted current echo cancellation intensity is reduced. The larger the preset echo cancellation strength adjustment step size is, the larger the amplitude of the current echo cancellation strength after each adjustment is increased or reduced, and the smaller the amplitude of the current echo cancellation strength after each adjustment is increased or reduced is otherwise.

Step S32, echo cancellation is carried out on the volume gain sound signal by utilizing the adjusted current echo cancellation intensity;

after the current echo cancellation intensity after each time is obtained, the intensity parameter change in the echo cancellation algorithm is preset, and then the echo cancellation is carried out on the volume gain sound signal at the moment based on the preset echo cancellation algorithm after the intensity parameter change.

Step S33, taking the adjusted current echo cancellation intensity as the current echo cancellation intensity, and circularly executing the step of combining the preset echo cancellation intensity adjustment step length and the current echo cancellation intensity to adjust the current echo cancellation intensity, thereby obtaining the adjusted current echo cancellation intensity so as to obtain an echo cancellation sound signal after echo cancellation.

Taking the adjusted current echo cancellation strength as the current echo cancellation strength, if the current echo cancellation strength does not obtain an echo cancellation sound signal without an echo signal, or the current echo cancellation strength and the echo cancellation strength before adjustment can both enable the adjusted volume gain sound signal to be free of an echo signal, the situation also indicates that the current echo cancellation strength is likely to be further reduced and the adjusted volume gain sound signal can also be enabled to be free of an echo signal after the reduction. Thereby circularly executing step S31: combining a preset echo cancellation intensity adjustment step length and a current echo cancellation intensity to adjust the current echo cancellation intensity, thereby obtaining an adjusted current echo cancellation intensity until an echo cancellation sound signal after echo cancellation is obtained, that is, an echo cancellation sound signal without echo exactly, where the echo cancellation sound signal without echo exactly means: if the current echo cancellation intensity is gradually increased, the sound signal of the volume gain has no echo signal when the current echo cancellation intensity is increased to a certain intensity, and the corresponding sound signal of the echo cancellation is the sound signal of the echo cancellation; if the current echo cancellation strength is gradually reduced, the volume gain sound signal is just re-presented with the echo signal when reduced to a certain strength (the original echo cancellation strength is such that the echo signal has been cancelled), the previous echo cancellation strength when the echo signal is re-presented is the best current echo cancellation strength, with which the echo cancellation sound signal just without the echo signal is obtained.

For the above steps S31 to S33, the volume gain sound signal may be initially echo-adjusted by using the default echo cancellation strength as the current echo cancellation strength and the preset echo cancellation algorithm, and if there is still or no echo signal after the initial echo cancellation algorithm, the current echo cancellation strength may be adjusted according to the preset echo cancellation algorithm.

Under the condition that no echo signal exists after the primary echo is adjusted, the current echo intensity needs to be gradually reduced, namely the preset echo cancellation intensity adjustment step length is negative, the preset echo cancellation intensity and the current echo cancellation intensity are combined each time, namely the current echo cancellation intensity after adjustment is gradually reduced, the capacity of echo cancellation is gradually reduced, the current echo cancellation intensity is stopped being reduced when the reappearance echo signal is obtained, the echo cancellation is carried out on the volume gain sound signal according to the current echo cancellation intensity before reappearance echo signal, and the purpose of doing so is that: although the echo signal is eliminated by the default echo eliminating intensity or the current echo eliminating intensity obtained after each step-by-step adjustment, the echo eliminating intensity is likely to be too high, so that the voice signal of the user is also eliminated by mistake, and further the voice of the user is distorted, so that the echo eliminating intensity is also required to be gradually reduced until the more reliable current echo eliminating intensity is found, the current echo eliminating intensity just can eliminate the echo, and if the current echo eliminating intensity is reduced, the echo can start to appear, so that the dynamic balance point of the echo eliminating is achieved, namely, a critical value is found, the interference on the voice of the user is minimized, and further the voice of the user is clearer and more complete.

It should be noted that when the echo cancellation sound signal without the echo signal is obtained, the corresponding current echo cancellation intensity is saved, and then the echo cancellation intensity is utilized to cancel the subsequent sound signal, so that the clear voice conforming to the surrounding environment can be obtained more directly and efficiently.

Step S40, according to the preset noise elimination intensity adjustment step length and the current noise elimination intensity, the noise elimination is gradually carried out on the echo elimination sound signal so as to obtain a voice signal after noise elimination.

Similarly, the preset noise elimination intensity adjustment step length is a step length for adjusting the current noise elimination intensity to change the current noise elimination intensity every time, and the preset noise elimination intensity adjustment step length can also be set according to actual needs, so that the preset noise elimination intensity adjustment step length is not limited herein, for example, can be set according to a division rule of the noise elimination intensity, for example, the noise elimination intensity can be set to 30 levels, and is not described herein.

The current noise level may be a default noise cancellation level when the echo cancellation sound signal is initially adjusted, for example, the default noise cancellation level is 20 th level, and then the noise cancellation level after the current noise cancellation level is adjusted by the preset noise cancellation level adjustment step is used as the current noise cancellation level, that is, the current noise cancellation level is a dynamic process from the default noise cancellation level since the echo cancellation sound signal is adjusted.

In addition, the noise is a piece of sound data with a constant frequency and amplitude, and the default noise elimination intensity may be a preset noise reduction intensity, or may be a noise reduction intensity determined according to the amplitude and the frequency of the noise in the sound signal.

The present invention does not improve the algorithm itself, but does not add more details here), and if the echo cancellation sound signal after the noise cancellation operation fails to reach the expected level, i.e. there is still noise, the default noise cancellation intensity needs to be adjusted by the preset noise cancellation intensity adjustment step length, so that the adjusted current noise cancellation intensity is used as the current noise cancellation intensity, the echo cancellation sound signal is subjected to noise cancellation by combining with the preset noise cancellation algorithm, and the current noise cancellation intensity is continuously adjusted until the noise in the echo cancellation sound signal is completely cancelled by the current noise cancellation intensity, so as to obtain a voice signal after the noise cancellation, i.e. the opposite party only hears the voice of the user in the voice call process, without noise and echo interference, so that the voice is more prominent and clear, and the call quality is improved.

Referring to fig. 4, in an embodiment, the step S40 includes:

step S41, combining a preset noise elimination intensity adjustment step length and a current noise elimination intensity to adjust the current noise elimination intensity, so as to obtain the adjusted current noise elimination intensity;

the preset noise elimination intensity adjustment step length is combined with the current noise elimination intensity, namely, the preset noise elimination intensity adjustment step length and the current noise elimination intensity are added, when the preset noise elimination intensity adjustment step length is a positive number, the adjusted current noise elimination intensity is increased, and otherwise, the adjusted current noise elimination intensity is reduced. The larger the preset noise elimination intensity adjustment step length is, the larger the current noise elimination intensity after each adjustment is increased or reduced, and the smaller the current noise elimination intensity after each adjustment is increased or reduced.

Step S42, noise cancellation is carried out on the echo cancellation sound signal by utilizing the adjusted current noise cancellation intensity;

after the current noise elimination intensity after each time is obtained, the intensity parameter in the preset noise elimination algorithm is changed, and then the echo elimination sound signal at the moment is subjected to noise elimination based on the preset noise elimination algorithm after the intensity parameter is changed.

And step S43, taking the adjusted current noise elimination intensity as the current noise elimination intensity, and circularly executing the step of combining the preset noise elimination intensity adjustment step length and the current noise elimination intensity to adjust the current noise elimination intensity so as to obtain the adjusted current noise elimination intensity, thereby obtaining the voice signal after noise elimination.

The same procedure as the echo cancellation procedure, the adjusted current noise cancellation strength is taken as the current noise cancellation strength, if the current noise cancellation strength does not obtain a human voice signal of a noiseless signal, or the current noise cancellation strength and the noise cancellation strength before adjustment can both make the echo cancellation sound signal noiseless signal after adjustment, but this also indicates that the current noise cancellation strength is likely to be able to continue to be reduced, and in case of reduction, the echo cancellation sound signal noiseless signal after adjustment can also be made. Thereby cyclically executing step S41: the step length of the preset noise elimination intensity adjustment step length and the current noise elimination intensity are combined to adjust the current noise elimination intensity, the adjusted current noise elimination intensity is obtained until the noise eliminated voice signal is obtained, namely the voice signal which is just noiseless is obtained, and the voice signal which is just noiseless is referred to as: if the current noise elimination intensity is gradually increased, the noise-free signal of the echo elimination sound signal is just when the current noise elimination intensity is increased to a certain intensity, and the corresponding noise-free signal is the voice signal; if the current noise cancellation strength is gradually reduced, the echo cancellation sound signal is just reduced to a certain strength and the noise signal reappears again (the original noise cancellation strength causes the noise signal to be cancelled), then the previous noise cancellation strength when the noise signal reappears is the best current noise cancellation strength, and the human voice signal just without the noise signal is obtained by using the previous noise cancellation strength.

Other relevant descriptions are the same as the echo cancellation process, and will not be repeated here.

By adopting the embodiment of the invention about noise elimination, the optimal noise elimination intensity can be determined in a mode of dynamically adjusting the noise elimination intensity (noise reduction intensity), namely, the noise elimination critical point between noise and no noise is determined, so that the noise of sound signals in the surrounding environment is reduced pertinently, the phenomena of human voice distortion, top elimination and the like caused by adopting parameters such as fixed noise elimination intensity and the like for sound adjustment are avoided, the interference of noise on human voice is eliminated, the clear integrity of human voice is greatly ensured, and the voice call quality is further improved.

In addition, it should be noted that the whole sound adjusting process of the volume gain, the echo cancellation and the noise cancellation does not limit the sequence of sound adjustment, that is, the three links of the volume gain, the echo cancellation and the noise cancellation may not have a fixed sequence in the whole sound adjusting process, that is, it is possible to perform any link first.

It should be noted that, no matter the volume gain intensity, the echo cancellation intensity or the noise cancellation intensity is larger and better, the larger the echo cancellation intensity or the noise cancellation intensity is, the original voice is affected, and the distortion or the top cancellation are caused.

It should be noted that, in the above embodiment, the user may be a person or a robot, that is, the voice signal after echo cancellation and noise cancellation may be a voice signal of a person or a voice signal of a robot, or may be other voice signals sent by talkback using an elevator.

According to the method for dynamically adjusting the voice quality, the initial voice signals in the surrounding environment are collected, the current volume gain intensity is dynamically adjusted through the preset volume gain adjustment step length based on the characteristics of the initial voice signals, and then the initial voice signals are gradually subjected to dynamic volume gain through the dynamically adjusted current volume gain intensity, so that the collected initial voice signals are more targeted in adjustment, the volume of the initial voice signals is stably increased in a dynamic balance mode under the condition that the characteristics of the initial voice signals are met, the negligence of the voice signals in the gain process is avoided, the volume effect of the volume gain voice signals is more ideal, and the hearing feeling is better met. Further, the current echo cancellation intensity is dynamically adjusted by presetting the echo cancellation intensity adjustment step length, and then the echo signals in the volume gain sound signals are gently and gradually cancelled by the dynamically adjusted current echo cancellation intensity, so that the echo cancellation of the volume gain sound signals in a dynamic balance mode is realized, the influence of the echo on the voice quality is avoided, and the obtained echo cancellation sound signals enable the voice sent by the user in the initial sound signals to be clearer. Finally, the same principle, through the dynamic adjustment of the preset noise elimination intensity adjustment step length to the current noise elimination intensity, the noise signal of the echo elimination sound signal is gently and gradually eliminated in a dynamic balance mode, the influence of noise on voice quality is avoided, the voice output corresponding to the voice signal after noise elimination is clear, the voice quality effect felt at one end of the received voice signal is more excellent, the voice conversation effect is more ideal and accords with the user expectation, and the voice conversation experience of the user is greatly improved.

Referring to fig. 5, in an embodiment, before the step S30, the method further includes:

step S300, determining an echo signal in the volume gain sound signal, and performing echo cancellation on the volume gain sound signal based on the current echo cancellation intensity to obtain an echo sound signal to be checked;

When a party uses the voice intercom device, the voice signal transmitted by the other party is received and played, and the voice signal transmitted by the other party is the echo signal in the embodiment.

The current echo cancellation strength may be a default echo cancellation strength or an echo cancellation strength after each adjustment based on the default echo cancellation strength.

In the process of echo adjustment, echo cancellation is carried out on the volume gain sound signal each time based on the current echo cancellation intensity and a preset echo cancellation algorithm, so that the sound signal obtained after each echo cancellation is used as an echo sound signal to be checked, namely the echo sound signal to be checked needs to be further checked to judge whether the echo signal exists.

Step S310, comparing the echo signal to be verified and the echo signal to obtain a comparison result, and determining a corresponding preset echo cancellation intensity adjustment step length according to the comparison result; the preset echo cancellation intensity adjustment step length is used for adjusting the current echo cancellation intensity;

comparing the echo to-be-checked sound signal with the echo signal can obtain at least two comparison results: and comparing the comparison result of the echo signal residues with the comparison result of no echo signal residues, namely judging whether the echo signal exists in the sound signal to be checked or not through comparison.

Under the comparison result of echo signal residues, the corresponding preset echo cancellation intensity adjustment step length can be a positive number; under the comparison result that the echo signal has no residue, the corresponding preset echo cancellation intensity adjustment step length can be a negative number. The specific preset echo cancellation strength adjustment step value may be set according to actual needs, and is not limited herein.

In addition, the overlapping proportion between the sound signal to be verified and the echo signal can be determined as a comparison result, correspondingly, the higher the overlapping proportion is, the larger the preset echo cancellation intensity adjustment step length (absolute value) can be, otherwise, the smaller the preset echo cancellation intensity adjustment step length (absolute value) can be, so that different preset echo cancellation intensity adjustment step lengths are determined according to the comparison result of different overlapping proportions, the current echo cancellation intensity is adjusted pertinently, under the condition that the overlapping proportion is higher, the echo cancellation intensity can be adjusted quickly through the preset echo cancellation intensity adjustment step length, so that clear voice is obtained in time, under the condition that the overlapping proportion is lower, the phenomena of voice distortion, voice cancellation and the like caused by the fact that the echo cancellation intensity is adjusted excessively instantaneously are prevented, and accordingly, according to different overlapping proportions, the balance between the efficient echo adjustment and the voice distortion cancellation prevention is realized, and the sound signal can be adjusted quickly and well.

Step S320, taking the sound signal to be verified as the volume gain sound signal, and executing the step of performing echo cancellation on the volume gain sound signal step by step according to a preset echo cancellation intensity adjustment step size and a current echo cancellation intensity to obtain an echo cancelled sound signal after echo cancellation.

After determining the preset echo cancellation intensity adjustment step length, in order to realize dynamic adjustment of the sound signals, the sound signals to be checked in the echo are used as the volume gain sound signals, the step of gradually performing echo cancellation on the volume gain sound signals according to the preset echo cancellation intensity adjustment step length and the current echo cancellation intensity is circularly executed until the echo cancellation sound signals after echo cancellation are obtained, and the corresponding current echo cancellation intensity is stored for subsequent use.

According to the embodiment of the invention, the current echo cancellation intensity can be adaptively adjusted based on different comparison results, so that the echo in the sound signal can be accurately, quickly and well adjusted, and the conversation voice quality and the conversation experience of a user are improved.

Referring to fig. 6, in an embodiment, the step S310 includes:

Step S311, comparing the echo signal to be verified with the echo signal to determine whether there is an overlapping signal between the echo signal to be verified and the echo signal;

step S312, if there is an overlapping signal, determining that the comparison result is the comparison result of echo signal residues;

step S313, determining a corresponding first preset echo cancellation intensity adjustment step according to the comparison result of the echo signal residues; the first preset echo cancellation strength adjustment step size is a positive value.

When the echo to be verified sound signal is compared with the echo signal, the echo to be verified sound signal can be compared through a signal spectrum level, and can also be compared through a signal data level, the comparison is not limited, as long as a comparison result of whether the echo to be verified and the echo signal are overlapped can be obtained, after the comparison, if an overlapped signal exists between the echo to be verified and the echo signal, the echo is not eliminated completely, and the comparison result of echo signal residues is obtained. This also means that the current echo cancellation strength is insufficient to completely cancel the echo signal in the sound signal, and the echo cancellation strength needs to be increased to completely cancel the echo, so that the corresponding first preset echo cancellation strength adjustment step length is a positive value, and when the echo cancellation strength is adjusted each time, the first preset echo cancellation strength adjustment step length is combined with the current echo cancellation strength to increase the adjusted current echo cancellation strength, thereby gradually increasing the echo cancellation strength, realizing complete cancellation of the echo under the condition that the user is not easy to perceive, obtaining clearer voice, and improving the use experience of the user during voice intercom.

In addition, based on the same principle, the method for determining the preset echo cancellation intensity adjustment step length in the embodiment may also be applied to determining the preset noise cancellation intensity adjustment step length, that is, comparing the sound signal to be checked of the noise with the noise signal, so as to obtain the preset noise cancellation intensity adjustment step length, which is not described in detail herein.

Based on the foregoing embodiments, in an embodiment, after the step S311, the method further includes:

step c, if no overlapping signal exists, determining that the comparison result is a comparison result of no echo signal residue;

step d, determining a corresponding second preset echo cancellation intensity adjustment step length according to the comparison result of no residue of the echo signal; the second preset echo cancellation strength adjustment step is negative.

Under the condition that no overlapping signal exists between the sound signal to be verified of the echo and the echo signal, namely, the comparison result is determined to be the comparison result of no echo signal residue, the current echo cancellation strength is indicated to be capable of completely canceling the echo signal, and since the current echo cancellation strength is likely to be that the echo cancellation is complete due to overlarge strength, but the overlarge strength influences the voice signal of a person, a second preset echo cancellation strength adjustment step length is required to be a negative value to reduce the current echo cancellation strength until the adjusted current echo cancellation strength again enables the echo to reappear in the sound signal, and the former echo cancellation strength is used as the most suitable current echo cancellation strength to adjust the subsequent sound signal.

Through the embodiment of the invention, in order to reasonably adjust the echo signal in the sound signal, even if the original echo cancellation intensity can completely cancel the echo signal, the original echo cancellation intensity can be adjusted to determine the optimal current echo cancellation intensity, so that the sound signal is adjusted without echo interference, negative influence on the voice signal of the person caused by overlarge echo cancellation intensity is avoided, and the voice quality during conversation is ensured to the greatest extent in dynamic balance.

Based on the foregoing embodiments, in one embodiment, the step S30 includes:

step e, determining volume gain sound frequency band signals exceeding an echo threshold value in the volume gain sound signals;

and f, performing echo cancellation on the volume gain sound frequency band signal in the volume gain sound signal step by step according to a preset echo cancellation intensity adjustment step length and the current echo cancellation intensity so as to obtain an echo cancellation sound signal after echo cancellation.

In this embodiment of the present invention, a volume gain sound frequency band signal exceeding an echo threshold value may be found and determined from the volume gain sound signals, and then only one or more sections of the volume gain sound frequency band signal exceeding the echo threshold value may be subjected to the echo adjustment in each of the above embodiments, so as to obtain an echo cancellation sound signal after echo cancellation, where the echo threshold value may be set according to actual needs.

According to the embodiment of the invention, the sound signal can be adjusted in a segmented way, so that the pertinence is higher, the adjusting accuracy is higher, and finally, the obtained voice can be clearer.

In order to facilitate understanding of the foregoing embodiments, the technical solutions of the present invention will be described in connection with an interposer as a device for dynamically adjusting voice quality:

fig. 7 is a schematic diagram of an application flow of voice intercom related to the method for dynamically adjusting voice quality of the present invention. The interphone is electrically connected with the adapter plate, one user (called a near-end user) carries out conversation and talkback with the other user (called a far-end user) through the interphone, when an initial sound signal of the environment where the near-end user is located is collected by the interphone and then is transmitted to the adapter plate, and then the adapter plate adjusts the sound signal through an echo cancellation algorithm and a noise cancellation algorithm after gain or no gain to obtain clear voice, and the voice is transmitted to a mobile phone of the far-end user or other voice intercom equipment through a gateway.

Referring to fig. 7, as further shown in fig. 8, fig. 8 is a schematic diagram of an application flow of adjusting a sound signal according to the method for dynamically adjusting voice quality of the present invention.

Firstly, collecting sound by an interphone in the environment where a near-end user is located;

judging the amplitude of sound: if the amplitude is too low, increasing the sound amplitude; or if the amplitude is too high, the sound amplitude is reduced, and the mode of increasing the amplitude or reducing the amplitude can be realized by adjusting the volume gain intensity;

echo cancellation and noise cancellation are performed on the sound signal;

judging whether the echo and noise reduction strength is proper: if the echo cancellation strength is low, the echo cancellation strength is increased; if the echo cancellation strength is high, the echo cancellation strength is reduced; if the noise reduction strength is low, the noise reduction strength is increased; if the noise reduction strength is high, the noise reduction strength is reduced.

In addition, referring to fig. 9, the present invention also proposes a device for dynamically adjusting voice quality, the device for dynamically adjusting voice quality comprising:

the sound collection module A10 is used for obtaining initial sound signals in the surrounding environment;

the volume gain module A20 is used for gradually carrying out volume gain on the initial sound signal according to a preset volume gain adjustment step length and the current volume gain intensity so as to obtain a volume gain sound signal;

the echo cancellation module a30 is configured to perform echo cancellation on the volume gain sound signal step by step according to a preset echo cancellation intensity adjustment step length and a current echo cancellation intensity, so as to obtain an echo cancellation sound signal after echo cancellation;

The noise cancellation module a40 is configured to perform noise cancellation on the echo cancellation sound signal step by step according to a preset noise cancellation intensity adjustment step size and a current noise cancellation intensity, so as to obtain a noise cancelled speech signal.

Optionally, the volume gain module a20 is further configured to:

Optionally, the echo cancellation module a30 is further configured to:

Optionally, the noise cancellation module a40 is further configured to:

The specific implementation manner of the device for dynamically adjusting voice quality of the present invention is basically the same as the above embodiments of the method for dynamically adjusting voice quality, and will not be described herein.

Furthermore, the invention also provides a computer readable storage medium. The computer readable storage medium of the present invention stores a dynamic voice quality adjustment program, wherein the dynamic voice quality adjustment program, when executed by a processor, implements the steps of the dynamic voice quality adjustment method as described above.

The method implemented when the dynamic voice quality adjustment program is executed may refer to various embodiments of the method for dynamically adjusting voice quality according to the present invention, which will not be described herein.

It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structural changes made by the description of the present invention and the accompanying drawings or direct/indirect application in other related technical fields are included in the scope of the invention.

Claims

1. A method for dynamically adjusting voice quality, the method comprising the steps of:

acquiring an initial sound signal in the surrounding environment;

2. The method of dynamically adjusting voice quality according to claim 1, wherein prior to said step of gradually applying a volume gain to said initial sound signal based on a preset volume gain adjustment step size and a current volume gain intensity to obtain a volume gain sound signal, said method further comprises:

3. The method for dynamically adjusting voice quality as recited in claim 1, wherein before the step of performing echo cancellation on the volume gain sound signal step by step according to a preset echo cancellation intensity adjustment step size and a current echo cancellation intensity to obtain an echo cancelled sound signal, comprising:

4. The method for dynamically adjusting voice quality as recited in claim 3, wherein said step of comparing said echo to-be-verified voice signal with said echo signal to obtain a comparison result, and determining a corresponding preset echo cancellation intensity adjustment step according to said comparison result comprises:

5. The method of dynamically adjusting voice quality as recited in claim 4, wherein after said step of determining whether there is an overlapping signal between the echo to be verified voice signal and the echo signal, the method further comprises:

6. The method for dynamically adjusting voice quality as recited in claim 1, wherein said step of gradually echo-canceling said volume gain acoustic signal according to a preset echo cancellation intensity adjustment step size and a current echo cancellation intensity to obtain an echo cancelled acoustic signal comprises:

7. The method for dynamically adjusting voice quality as recited in claim 1, wherein said step of gradually echo-canceling said volume gain acoustic signal according to a preset echo cancellation intensity adjustment step size and a current echo cancellation intensity to obtain an echo cancelled acoustic signal comprises:

8. The method for dynamically adjusting voice quality according to claim 1, wherein said step of gradually noise-canceling said echo-cancelled sound signal according to a preset noise-canceling intensity adjustment step size and a current noise-canceling intensity to obtain a noise-cancelled sound signal comprises:

9. A dynamically adjusted speech quality device comprising a processor, a memory, and a dynamically adjusted speech quality program stored on the memory that is executable by the processor, wherein the dynamically adjusted speech quality program, when executed by the processor, implements the steps of the dynamically adjusted speech quality method of any of claims 1 to 8.

10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a dynamically adjusting speech quality program, wherein the dynamically adjusting speech quality program, when executed by a processor, implements the steps of the dynamically adjusting speech quality method according to any of claims 1 to 8.