Smart phone device based on adaptive voice intensity adjustment

Abstract

The present invention discloses an intelligent telephone device based on adaptive voice intensity adjustment, comprising a voice module and a power module, wherein the voice module is connected to the power module, and a processor provided with a voice intensity comfort zone learning module and an intelligent adaptive voice intensity module, wherein the processor is connected to the voice module; the present invention solves the problem of unstable voice intensity caused by distance change and other reasons during telephone calls, forms a voice comfort zone through continuous learning, accumulates and learns voices using an intelligent adaptive voice intensity adjustment method, intelligently adjusts voice intensity, and improves telephone user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of telephone voice communication, and more specifically, to an intelligent telephone device based on adaptive voice intensity adjustment. Background Art

[0002] Telephone voice communication has always been an important means of communication. In current telephone situations, the distance between the speaker and the microphone is inconsistent, or the voice is loud or soft for various reasons. The voice intensity received by the receiver will be loud or soft, affecting the call experience. The current device does not have the function of adaptive voice intensity adjustment. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art and provide an intelligent telephone device based on adaptive voice intensity adjustment, which solves the problem of unstable voice intensity caused by distance changes during telephone calls, continuously learns to form a voice comfort zone, uses an intelligent adaptive voice intensity adjustment method to accumulate and learn voice, and intelligently adjusts the voice intensity to improve the telephone user experience.

[0004] The object of the present invention is achieved through the following solutions:

[0005] A smart phone device based on adaptive voice intensity adjustment comprises a voice module and a power module, wherein the voice module is connected to the power module; and a processor provided with a voice intensity comfort zone learning module and an intelligent adaptive voice intensity module, wherein the processor is connected to the voice module.

[0006] Furthermore, the speech intensity comfort zone learning module is used for constructing a speech intensity comfort zone and updating related parameters; the intelligent adaptive speech intensity module is used for optimizing and adjusting the speech intensity of the sampling points within the sampling period according to the speech intensity comfort zone to achieve the effect of comfortable speech intensity output.

[0007] Furthermore, the voice module is used for voice collection, input and output.

[0008] Furthermore, the speech intensity comfort zone learning module identifies the speech intensity comfort zone through data accumulation and machine learning; there are n speech sampling points in each speech sampling period T, and the speech intensity comfort zone learning module performs speech intensity comfort zone learning adjustment for the n speech sampling points in each speech sampling period T of the receiver, adjusts the speech intensity of the speech that is not in the speech intensity comfort zone, and finally adjusts it to within the speech intensity comfort zone.

[0009] Further, the intelligent adaptive speech intensity module adjusts the n speech sampling points of the receiver within each speech sampling period T to the speech intensity comfort zone. After each period completes the processing of the speech intensity comfort zone learning module, the intelligent adaptive speech intensity module is used to adjust the speech intensity of the current sampling point.

[0010] Further, the speech intensity comfort zone learning module includes:

[0011] The first learning and adjustment module is used to execute the first learning and adjustment process: when Vb <= Vmin, then Vmin is decreased by 10 unit speech intensities V_Unit, that is, Vmin_new = Vmin – 10 * V_Unit; Vmax is decreased by 5 unit speech intensity adjustment amounts V_Unit, that is, Vmax_new = Vmax – 5 * V_Unit. Finally, the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to complete the update of the upper and lower boundaries of the speech intensity comfort zone.

[0012] The second learning and adjustment module is used to execute the second learning and adjustment process: when Va < Vmin and Vmin < Vb < Vmax, then Vmin remains unchanged, that is, Vmin_new = Vmin; Vmax is decreased by 2 unit speech intensities V_Unit, that is, Vmax_new = Vmax – 2 * V_Unit. If the adjusted V_Span_new in this scenario is less than V_MinSpan, then the values of Vmax and Vmin and the upper and lower boundaries of the speech intensity comfort zone remain unchanged in this adjustment period. If the adjusted V_Span_new in this scenario is greater than or equal to V_MinSpan, then the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to the value of V_Span_new to complete the update of the upper and lower boundaries of the speech intensity comfort zone.

[0013] The third learning adjustment module is used to execute the third learning adjustment process: when Va > Vmin and Vb < Vmax, then Vmin is increased by 1 unit of voice intensity V_Unit, that is, Vmin_new = Vmin + V_Unit; Vmax is decreased by 1 unit of voice intensity adjustment amount V_Unit, that is, Vmax_new = Vmax – V_Unit; if the adjusted V_Span_new in this scenario is less than V_MinSpan, then the values of Vmax and Vmin are not updated in this adjustment cycle, and the upper and lower boundaries of the voice intensity comfort zone remain unchanged. If the adjusted V_Span_new in this scenario is greater than or equal to V_MinSpan, then the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to the value of V_Span_new, completing the update of the upper and lower boundaries of the voice intensity comfort zone;

[0014] The fourth learning adjustment module is used to execute the fourth learning adjustment process: when Vmin < Va < Vmax and Vb > Vmax, then Vmin is increased by 2 units of voice intensity V_Unit, that is, Vmin_new = Vmin + 2 * V_Unit; Vmax remains unchanged, that is, Vmax_new = Vmax; if the adjusted V_Span_new in this scenario is less than V_MinSpan, then the values of Vmax and Vmin are not updated in this adjustment cycle, and the upper and lower boundaries of the voice intensity comfort zone remain unchanged. If the adjusted V_Span_new in this scenario is greater than or equal to V_MinSpan, then the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to the value of V_Span_new, completing the update of the upper and lower boundaries of the voice intensity comfort zone;

[0015] The fifth learning adjustment module is used to execute the fifth learning adjustment process: when Va >= Vmax, then Vmax is increased by 10 units of voice intensity V_Unit, that is, Vmax_new = Vmax + 10 * V_Unit; Vmin is increased by 5 units of voice intensity adjustment amount V_Unit, that is, Vmin_new = Vmin + 5 * V_Unit. Finally, the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated, completing the update of the upper and lower boundaries of the voice intensity comfort zone;

[0016] The sixth learning adjustment module is used to execute the sixth learning adjustment process: when Va<=Vmin and Vb>=Vmax, Vmin is reduced by 1 unit of speech intensity V_Unit, that is, Vmin_new=Vmin-V_Unit; Vmax is increased by 1 unit of speech intensity adjustment V_Unit, that is, Vmax_new=Vmax+V_Unit, and finally the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, the value of V_Span is updated, and the upper and lower boundaries of the speech intensity comfort zone are updated;

[0017] The seventh learning adjustment module is used to execute the seventh learning adjustment process: if the speech intensity of 80% of the samples in this sampling period is less than 2% of V_SysMax (V_SysMax=1000V_Unit), that is, more than 80% of the samples are within 20V_Unit, it is regarded as a silent scene. The upper and lower boundaries of the comfort zone will not be adjusted in this period, and the speech intensity will not be adjusted.

[0018] Further, when V_CurSpan<=V_Span_new, the intelligent adaptive speech intensity module includes:

[0019] The first adjustment module, when Va<=Vmin_new, increases the speech intensity of all samples in this period by (Vmin_new-Va);

[0020] The second adjustment module, when Va>=Vmin_new and Vb<=Vmax_new, the overall speech intensity of all samples in this period is adjusted to 0, that is, no adjustment is performed;

[0021] The third adjustment module, when Vb>=Vmax_new, reduces the speech intensity of all samples in this period by (Vb-Vmax_new).

[0022] Further, when V_CurSpan>V_Span_new, the intelligent adaptive speech intensity module includes:

[0023] A fourth adjustment module, used to execute a fourth adjustment process: used to execute the first adjustment process: when Va>=Vmin_new, all sample points in this period are reduced as a whole by the speech intensity of (Va-Vmin_new);

[0024] A fifth adjustment module, used to execute the fifth adjustment process: used to execute the second adjustment process: when Va<=Vmin_new and Vb>=Vmax_new, the overall speech intensity of all sample points in this period is adjusted to 0, that is, no adjustment is performed;

[0025] The sixth adjustment module is used to execute the sixth adjustment process: used to execute the third adjustment process: when Vb<=Vmax_new, the speech intensity of all samples in this period is increased as a whole by (Vmax_new-Vb).

[0026] The beneficial effects of the present invention include:

[0027] The present invention solves the problem of unstable voice intensity caused by distance changes and other reasons during telephone calls, continuously learns to form a voice comfort zone, uses an intelligent adaptive voice intensity adjustment method to accumulate and learn the voice, intelligently adjusts the voice intensity to the voice intensity comfort zone, and improves the telephone user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0029] Figure 1 A schematic diagram of the functional structure of a device according to an embodiment of the present invention;

[0030] Figure 2 A flowchart of a speech intensity comfort zone learning module according to an embodiment of the present invention;

[0031] Figure 3 A schematic diagram of scenario 1 of a speech intensity comfort zone learning module according to an embodiment of the present invention;

[0032] Figure 4 A schematic diagram of scenario 2 of a speech intensity comfort zone learning module according to an embodiment of the present invention;

[0033] Figure 5 This is a schematic diagram of scenario 3 of the speech intensity comfort zone learning module of an embodiment of the present invention;

[0034] Figure 6 A schematic diagram of scenario 4 of a speech intensity comfort zone learning module according to an embodiment of the present invention;

[0035] Figure 7 A schematic diagram of scenario 5 of a speech intensity comfort zone learning module according to an embodiment of the present invention;

[0036] Figure 8 A schematic diagram of scenario 6 of a speech intensity comfort zone learning module according to an embodiment of the present invention;

[0037] Fig. 9 It is a flow chart of an intelligent adaptive speech intensity module according to an embodiment of the present invention;

[0038] Fig.10 This is a schematic diagram of the sampling point before adjustment when Va<=Vmin_new in the intelligent adaptive speech intensity module of an embodiment of the present invention;

[0039] Fig.11 This is a schematic diagram of the sampling point after adjustment when Va<=Vmin_new in the intelligent adaptive speech intensity module of an embodiment of the present invention;

[0040] Fig.12 This is a schematic diagram of a sampling point adjustment scheme in an intelligent adaptive speech intensity module according to an embodiment of the present invention when Va>=Vmin_new and Vb<=Vmax_new;

[0041] Fig.13 This is a schematic diagram of the sampling point before adjustment when Vb>=Vmax_new in the intelligent adaptive speech intensity module of an embodiment of the present invention;

[0042] Fig.14 This is a schematic diagram of the sampling point after adjustment when Vb>=Vmax_new in the intelligent adaptive speech intensity module of an embodiment of the present invention;

[0043] Fig.15 This is a schematic diagram of the sampling point before adjustment when Va>=Vmin_new in the intelligent adaptive speech intensity module of an embodiment of the present invention;

[0044] Fig.16 This is a schematic diagram of the sampling point after adjustment when Va>=Vmin_new in the intelligent adaptive speech intensity module of an embodiment of the present invention;

[0045] Fig.17 It is a schematic diagram of a sampling point adjustment scheme in the intelligent adaptive speech intensity module of an embodiment of the present invention when Va<=Vmin_new and Vb>=Vmax_new;

[0046] Fig.18 This is a schematic diagram of the sampling point before adjustment when Vb<=Vmax_new in the intelligent adaptive speech intensity module of an embodiment of the present invention;

[0047] Fig.19 This is a schematic diagram of the sampling point after adjustment when Vb<=Vmax_new in the intelligent adaptive speech intensity module of an embodiment of the present invention;

[0048] Explanation of terms

[0049] There are n speech sampling points in each speech sampling period T;

[0050] "V" is used to represent the speech intensity at the speech sampling point;

[0051] "V_Unit" represents the unit speech intensity, 0 is the minimum measurable value of the speech intensity system, represented by "V_SysMin", and the speech intensity value of 1000 times the unit speech intensity is the maximum measurable value of the speech intensity system, represented by "V_SysMax", that is, "V_SysMax" = 1000*V_Unit, and the overall sampling range of the system is 0 to 1000V_Unit;

[0052] "Vmin" is used to represent the lower boundary value of the speech intensity comfort zone, "Vmax" is used to represent the upper boundary value of the speech intensity comfort zone, the initial value of Vmin is set to the speech intensity with the smallest speech intensity in the first speech sampling point, the initial value of Vmax is set to the speech intensity with the largest speech intensity in the first speech sampling point, "Vmin_new" is the value of Vmin after adjustment and update in this adjustment cycle, and "Vmax_new" is the value of Vmax after adjustment and update in this adjustment cycle.

[0053] "V_Span" indicates the span of the current speech intensity comfort zone, that is, the difference between Vmax and Vmin: Vmax-Vmin;

[0054] "V_Span_new" represents the span range of the intensity comfort zone of the updated speech, that is, the difference between Vmax_new and Vmin_new: Vmax_new-Vmin_new;

[0055] “V_MinSpan” represents the minimum span of the comfort zone of speech intensity, and its value is 20% of the maximum measurable value V_SysMax of the speech intensity system, that is, 200*V_Unit.

[0056] According to the speech intensity, the n sampling points in the Ts period are sorted according to the speech intensity. The A sampling point represents the sampling point with the lowest speech intensity value Va in the Tc period, and the B sampling point represents the sampling point with the highest speech intensity value Vb in the Tc period. The speech intensity of the sampling points from point B to point A decreases. Point H is the middle sampling point between the n sampling points of point A and point B, that is, there are n / 2 sampling points between point H and point B, and the speech intensity corresponding to point H is Vh. The Min point is the sampling point corresponding to the lower boundary value Vmin of the speech intensity comfort zone, and the Max point is the sampling point corresponding to the lower boundary value Vmax of the speech intensity comfort zone. "V_CurSpan" represents the span range of the speech sampling points in this period, that is, Vb–Va after the difference between Vb and Va is updated. DETAILED DESCRIPTION

[0057] All features disclosed in all embodiments in this specification, or steps in all methods or processes implicitly disclosed, except for mutually exclusive features and / or steps, can be combined and / or extended, replaced in any way.

[0058] As Figure 1 shown, the intelligent telephone device based on adaptive speech intensity adjustment includes a processor, a speech module, and a power module; the processor includes a speech intensity comfort zone learning module and an intelligent adaptive speech intensity module. The speech intensity comfort zone learning module is mainly responsible for constructing the speech intensity comfort zone and updating related parameters. The intelligent adaptive speech intensity module is mainly responsible for optimizing and adjusting the speech intensity of the sampling points in the current sampling period according to the speech intensity comfort zone to achieve the effect of comfortable speech intensity output. The speech module mainly completes the acquisition, input, and output of speech.

[0059] (1) Speech intensity comfort zone learning module

[0060] Through data accumulation, machine learning can continuously identify the size range of daily comfortable speech intensity, that is, the speech intensity comfort zone. According to the speech outside the speech intensity comfort zone, weighted adjustment of speech intensity is performed, and finally it is adjusted into the speech intensity comfort zone.

[0061] There are n speech sampling points in each speech sampling period T. The speech intensity comfort zone learning module is to perform speech intensity comfort zone learning and adjustment for the n speech sampling points of the receiver in each speech sampling period T. The flowchart of the speech intensity comfort zone learning module is as Figure 2 shown. In a specific embodiment, the adjustment process is described as follows:

[0062] Scenario 1:

[0063] When Vb <= Vmin, then Vmin is decreased by 10 units of speech intensity V_Unit, that is, Vmin_new = Vmin - 10 * V_Unit; Vmax is decreased by 5 units of speech intensity adjustment V_Unit, that is, Vmax_new = Vmax - 5 * V_Unit. Finally, the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to complete the update of the upper and lower boundaries of the speech intensity comfort zone. The adjustment details are as Figure 3 shown.

[0064] Scenario 2:

[0065] When Va < Vmin and Vmin < Vb < Vmax, then Vmin remains unchanged, that is, Vmin_new = Vmin; Vmax is decreased by 2 units of speech intensity V_Unit, that is, Vmax_new = Vmax - 2 * V_Unit.

[0066] If the adjusted V_Span_new in this scenario is less than V_MinSpan, then the values of Vmax and Vmin are not updated in this adjustment cycle, and the upper and lower boundaries of the voice intensity comfort zone remain unchanged. If the adjusted V_Span_new in this scenario is greater than or equal to V_MinSpan, then the value of Vmin is updated to Vmin_new, the value of Vmax is updated to Vmax_new, and the value of V_Span is updated to V_Span_new, completing the update of the upper and lower boundaries of the voice intensity comfort zone. The adjustment details are as Figure 4 shown.

[0067] Scenario Three:

[0068] When Va > Vmin and Vb < Vmax, then Vmin is increased by 1 unit of voice intensity V_Unit, i.e., Vmin_new = Vmin + V_Unit; Vmax is decreased by 1 unit of voice intensity adjustment V_Unit, i.e., Vmax_new = Vmax – V_Unit.

[0069] If the adjusted V_Span_new in this scenario is less than V_MinSpan, then the values of Vmax and Vmin are not updated in this adjustment cycle, and the upper and lower boundaries of the voice intensity comfort zone remain unchanged. If the adjusted V_Span_new in this scenario is greater than or equal to V_MinSpan, then the value of Vmin is updated to Vmin_new, the value of Vmax is updated to Vmax_new, and the value of V_Span is updated to V_Span_new, completing the update of the upper and lower boundaries of the voice intensity comfort zone. The adjustment details are as Figure 5 shown.

[0070] Scenario Four:

[0071] When Vmin < Va < Vmax and Vb > Vmax, then Vmin is increased by 2 units of voice intensity V_Unit, i.e., Vmin_new = Vmin + 2 * V_Unit; Vmax remains unchanged, i.e., Vmax_new = Vmax.

[0072] If the adjusted V_Span_new in this scenario is less than V_MinSpan, then the values of Vmax and Vmin are not updated in this adjustment cycle, and the upper and lower boundaries of the voice intensity comfort zone remain unchanged. If the adjusted V_Span_new in this scenario is greater than or equal to V_MinSpan, then the value of Vmin is updated to Vmin_new, the value of Vmax is updated to Vmax_new, and the value of V_Span is updated to V_Span_new, completing the update of the upper and lower boundaries of the voice intensity comfort zone. The adjustment details are as Figure 6 shown.

[0073] Scene 5:

[0074] When Va>=Vmax, Vmax increases by 10 units of speech intensity V_Unit, that is, Vmax_new=Vmax+10*V_Unit; Vmin increases by 5 units of speech intensity adjustment V_Unit, that is, Vmin_new=Vmin+5*V_Unit. Finally, the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to complete the update of the upper and lower boundaries of the speech intensity comfort zone. The adjustment details are as follows: Figure 7 shown.

[0075] Scene 6:

[0076] When Va<=Vmin and Vb>=Vmax, Vmin is reduced by 1 unit of speech intensity V_Unit, that is, Vmin_new=Vmin-V_Unit; Vmax is increased by 1 unit of speech intensity adjustment V_Unit, that is, Vmax_new=Vmax+V_Unit. Finally, the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to complete the update of the upper and lower boundaries of the speech intensity comfort zone. The adjustment details are as follows: Figure 8 shown.

[0077] Scene 7:

[0078] If the speech intensity of 80% of the samples in this sampling period is less than 2% of V_SysMax (V_SysMax=1000V_Unit), that is, more than 80% of the samples are within 20V_Unit, it is regarded as a silent scene. The upper and lower boundaries of the comfort zone are not adjusted in this period, and the speech intensity is not adjusted.

[0079] (2) Intelligent adaptive speech intensity module

[0080] Intelligent adaptive speech intensity module: The receiver adjusts the n speech sampling points in each speech sampling cycle T to the speech intensity comfort zone. After the speech intensity comfort zone learning module is processed in each cycle, the speech intensity of the current sampling point needs to be adjusted.

[0081] Intelligent adaptive speech intensity module flow chart, such as Fig. 9 In a specific embodiment, the specific adjustment process is as follows:

[0082] When V_CurSpan<=V_Span_new, make adjustments according to the following three situations:

[0083] <1> When Va<=Vmin_new, the speech intensity of all samples in this cycle is increased by (Vmin_new-Va) as a whole; the schematic diagram before adjustment is as follows Fig.10 As shown, the schematic diagram after adjustment is as follows Fig.11 shown.

[0084] <2> When Va>=Vmin_new and Vb<=Vmax_new, the overall speech intensity of all samples in this cycle is not adjusted; the adjustment scheme diagram is as follows Fig.12 shown.

[0085] <3> When Vb>=Vmax_new, the speech intensity of all samples in this cycle is reduced by (Vb-Vmax_new); the schematic diagram before adjustment is as follows Fig.13 As shown, the schematic diagram after adjustment is as follows Fig.14 shown.

[0086] When V_CurSpan>V_Span_new, make adjustments according to the following three situations:

[0087] <1> When Va>=Vmin_new, the speech intensity of all samples in this cycle is reduced by (Va-Vmin_new) as a whole; the schematic diagram before adjustment is as follows Fig.15 As shown, the schematic diagram after adjustment is as follows Fig.16 shown.

[0088] <2> When Va<=Vmin_new and Vb>=Vmax_new, the overall speech intensity of all samples in this cycle is not adjusted; the adjustment scheme diagram is as follows Fig.17 shown.

[0089] <3> When Vb<=Vmax_new, the speech intensity of all samples in this cycle is increased by (Vmax_new-Vb) as a whole; the schematic diagram before adjustment is as follows Fig.18 As shown, the schematic diagram after adjustment is as follows Fig.19 shown.

[0090] The parts not involved in the present invention are the same as the prior art or can be implemented by using the prior art.

[0091] The above technical solution is only one implementation mode of the present invention. For those skilled in the art, it is easy to make various types of improvements or modifications based on the application methods and principles disclosed in the present invention, and it is not limited to the method described in the above specific implementation mode of the present invention. Therefore, the method described above is only preferred and does not have a restrictive meaning.

[0092] In addition to the above examples, those skilled in the art may obtain other embodiments based on the above disclosure or by using the knowledge or technology in the relevant field to make changes. The features of each embodiment may be interchangeable or replaced. The changes and modifications made by those skilled in the art do not depart from the spirit and scope of the present invention and should be within the scope of protection of the claims attached to the present invention.

Claims

1. A smart phone device based on adaptive voice intensity adjustment, comprising a voice module and a power module, wherein the voice module is connected to the power module; characterized in that: It includes a processor provided with a speech intensity comfort zone learning module and an intelligent adaptive speech intensity module, and the processor is connected to the speech module; The speech intensity comfort zone learning module is used for constructing the speech intensity comfort zone and updating related parameters; the intelligent adaptive speech intensity module is used for optimizing and adjusting the speech intensity of the sampling points within the sampling period according to the speech intensity comfort zone to achieve the effect of comfortable speech intensity output; The speech intensity comfort zone learning module identifies the speech intensity comfort zone through data accumulation and machine learning; each speech sampling period T has n speech sampling points, and the speech intensity comfort zone learning module performs speech intensity comfort zone learning adjustment for the n speech sampling points in each speech sampling period T of the receiver, and adjusts the speech intensity of the speech that is not in the speech intensity comfort zone, and finally adjusts it to the speech intensity comfort zone; The speech intensity comfort zone learning module includes: The first learning adjustment module is used to execute the first learning adjustment process: when Vb <= Vmin, Vmin is reduced by 10 units of speech intensity V_Unit, that is, Vmin_new = Vmin – 10*V_Unit; Vmax is reduced by 5 units of speech intensity adjustment V_Unit, that is, Vmax_new = Vmax – 5*V_Unit, and finally the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, the value of V_Span is updated, and the upper and lower boundaries of the speech intensity comfort zone are updated; The second learning adjustment module is used to execute the second learning adjustment process: when Va < Vmin and Vmin < Vb < Vmax, Vmin remains unchanged, that is, Vmin_new = Vmin; Vmax is reduced by 2 units of speech intensity V_Unit, that is, Vmax_new= Vmax – 2*V_Unit; if the adjusted V_Span_new in this scene is less than V_MinSpan, the values ​​of Vmax and Vmin are not updated in this adjustment cycle, and the upper and lower boundaries of the speech intensity comfort zone remain unchanged; if the adjusted V_Span_new in this scene is greater than or equal to V_MinSpan, the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to the value of V_Span_new, and the update of the upper and lower boundaries of the speech intensity comfort zone is completed; The third learning adjustment module is used to execute the third learning adjustment process: when Va>Vmin and Vb<Vmax, Vmin increases by 1 unit of speech intensity V_Unit, that is, Vmin_new = Vmin + V_Unit; Vmax decreases by 1 unit of speech intensity adjustment V_Unit, that is, Vmax_new = Vmax – V_Unit; if the adjusted V_Span_new in this scenario is less than V_MinSpan, the values ​​of Vmax and Vmin are not updated in this adjustment cycle, and the upper and lower boundaries of the speech intensity comfort zone remain unchanged; if the adjusted V_Span_new in this scenario is greater than or equal to V_MinSpan, the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to the value of V_Span_new, and the update of the upper and lower boundaries of the speech intensity comfort zone is completed; The fourth learning adjustment module is used to execute the fourth learning adjustment process: when Vmin < Va < Vmax and Vb > Vmax, Vmin increases by 2 units of speech intensity V_Unit, that is, Vmin_new = Vmin + 2*V_Unit; Vmax remains unchanged, that is, Vmax_new = Vmax; if the adjusted V_Span_new in this scene is less than V_MinSpan, the values ​​of Vmax and Vmin are not updated in this adjustment cycle, and the upper and lower boundaries of the speech intensity comfort zone remain unchanged; if the adjusted V_Span_new in this scene is greater than or equal to V_MinSpan, the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, and the value of V_Span is updated to the value of V_Span_new, and the update of the upper and lower boundaries of the speech intensity comfort zone is completed; The fifth learning adjustment module is used to execute the fifth learning adjustment process: when Va>=Vmax, Vmax increases by 10 units of speech intensity V_Unit, that is, Vmax_new = Vmax + 10*V_Unit; Vmin increases by 5 units of speech intensity adjustment V_Unit, that is, Vmin_new = Vmin + 5*V_Unit, and finally the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, the value of V_Span is updated, and the upper and lower boundaries of the speech intensity comfort zone are updated; The sixth learning adjustment module is used to execute the sixth learning adjustment process: when Va <= Vmin and Vb >= Vmax, Vmin is reduced by 1 unit of speech intensity V_Unit, that is, Vmin_new = Vmin - V_Unit; Vmax is increased by 1 unit of speech intensity adjustment V_Unit, that is, Vmax_new = Vmax + V_Unit, and finally the value of Vmin is updated to the value of Vmin_new, the value of Vmax is updated to the value of Vmax_new, the value of V_Span is updated, and the upper and lower boundaries of the speech intensity comfort zone are updated; The seventh learning adjustment module is used to execute the seventh learning adjustment process: if the speech intensity of 80% of the samples in this sampling period is less than 2% of V_SysMax, V_SysMax = 1000V_Unit, that is, more than 80% of the samples are within 20V_Unit, it is regarded as a silent scene. The upper and lower boundaries of the comfort zone will not be adjusted in this period, and the speech intensity will not be adjusted.

2. The smart phone device based on adaptive speech intensity adjustment according to claim 1, characterized in that: The voice module is used for voice collection, input and output.

3. The smart phone device based on adaptive speech intensity adjustment according to any one of claims 1 or 2, characterized in that: The intelligent adaptive speech intensity module adjusts the n speech sampling points of the receiver in each speech sampling period T to the speech intensity comfort zone. After the speech intensity comfort zone learning module is processed in each period, the intelligent adaptive speech intensity module is used to adjust the speech intensity of the current sampling point.

4. The smart phone device based on adaptive speech intensity adjustment according to claim 3, characterized in that: When V_CurSpan <= V_Span_new, the intelligent adaptive speech intensity module includes: The first adjustment module, when Va <= Vmin_new, increases the speech intensity of all samples in this period by (Vmin_new - Va); The second adjustment module, when Va>=Vmin_new and Vb<=Vmax_new, the overall speech intensity of all samples in this period is adjusted to 0, that is, no adjustment is performed; The third adjustment module, when Vb>=Vmax_new, reduces the speech intensity of all samples in this cycle by (Vb-Vmax_new).

5. The smart phone device based on adaptive speech intensity adjustment according to claim 3, characterized in that: When V_CurSpan>V_Span_new, the intelligent adaptive speech intensity module includes: The fourth adjustment module is used to execute the fourth adjustment process: used to execute the first adjustment process: when Va>=Vmin_new, the speech intensity of all samples in this period is reduced by (Va-Vmin_new); A fifth adjustment module, used to execute the fifth adjustment process: used to execute the second adjustment process: when Va <= Vmin_new and Vb >= Vmax_new, the overall speech intensity of all sample points in this period is adjusted to 0, that is, no adjustment is performed; The sixth adjustment module is used to execute the sixth adjustment process: used to execute the third adjustment process: when Vb <= Vmax_new, all sample points in this period are overall increased by the speech intensity of (Vmax_new - Vb).

Images