JP5168014B2 - Speaking speed conversion device and program - Google Patents

Description

  The present invention relates to a technique for converting speech speed of speech (speech speed).

Techniques for converting speech speed have been proposed. For example, Patent Document 1 discloses a technique for displaying a time series of volume and pitch for each syllable in a character string with a broken line. As the user changes the spacing of characters (text boxes) placed near the broken line for each syllable, the speech speed changes, and each node of the broken line (the syllable boundary) changes according to the distance after the change. The shape of the broken line is changed so as to move to the new position on the time axis.
JP 2005-283788 A

  However, in the technique of Patent Document 1, only the time series of the volume and pitch after changing the speaking speed is displayed, so the degree of changing the speaking speed (difference in speaking speed before and after conversion) is used. It is difficult for a person to grasp intuitively. In view of the above circumstances, an object of the present invention is to solve the problem of enabling an intuitive grasp of the degree to which the speech speed has been changed.

In order to solve the above-described problems, a speech speed conversion device according to the first aspect of the present invention includes a speech speed conversion means for performing speech speed conversion on a target section specified by a speech signal, and speech speed conversion of the speech signal. A first area (for example, area A1) in which the previous waveform is arranged along the time axis in the first direction, and a second area (in which the waveform after speech speed conversion of the speech signal is arranged along the time axis in the first direction ( For example, the area A2) is juxtaposed in the second direction intersecting the first direction, and the target section of the speech signal before speech speed conversion and the conversion section corresponding to the target section of the speech signal after speech speed conversion The display device displays a waveform confirmation image in which a straight line connecting the start points (for example, the straight line LA) and a straight line connecting the end points (for example, the straight line LB) are arranged between the first region and the second region . Display control means. In the above configuration, since the waveform of the speech signal before the speech speed conversion is compared with the waveform of the speech signal after the speech speed conversion, the user can intuitively understand the degree to which the speech speed has been changed. There is an advantage that can be grasped. In addition, since a straight line connecting the start points and end points of both sections is displayed between the target section and the conversion section, use the front and rear on the time axis between the target section and the conversion section after speech speed conversion There is also an advantage that a person can grasp intuitively. As the waveform of the speech signal after the speech speed conversion, the speech signal waveform generated by the speech speed conversion means actually executing the speech speed conversion is suitable. For example, the speech signal before the speech speed conversion is used. The waveform may be a waveform obtained by expanding and contracting the above waveform by image processing.

  In a preferred aspect of the present invention, the speech speed converting means performs speech speed conversion on the target section specified in the speech signal, and the display control means includes the target section of the speech signal before speech speed conversion and the speech speed conversion. The conversion section corresponding to the target section in the subsequent audio signal is displayed on the display device. In the above aspect, there exists an advantage that a user can grasp | ascertain the front and back on the time axis between the object area and the conversion area after speech speed conversion intuitively. The display of the target section and the conversion section means displaying the section in a manner that can be visually identified from other sections. For example, a configuration in which the target section and the conversion section are displayed in a mode (color, brightness, and saturation) different from other sections is preferable.

  The speech speed conversion device according to the second aspect of the present invention includes a speech speed conversion means for performing speech speed conversion on a target section specified by a speech signal, and a waveform of the speech signal before speech speed conversion in a first direction time. The first region arranged along the axis and the second region arranged along the time axis in the first direction of the waveform after the speech speed conversion of the speech signal are juxtaposed in the second direction intersecting the first direction. Display control means for displaying the waveform confirmation image on the display device. The display control means variably sets the conversion interval in accordance with an instruction from the user, and converts the speech speed before determining the conversion interval. The waveform of the conversion section obtained by expanding and contracting the waveform of the previous audio signal in the direction of the time axis by image processing is arranged in the second area. After the conversion section is determined, the waveform of the conversion section after speech speed conversion for the audio signal is Place in the area. In the above configuration, since the waveform of the speech signal before the speech speed conversion is compared with the waveform of the speech signal after the speech speed conversion, the user can intuitively understand the degree to which the speech speed has been changed. There is an advantage that can be grasped. Moreover, since the conversion rate of the speech rate conversion is set according to the time length of the conversion section designated by the user, the user can easily set the conversion section to a desired time length. In addition, the processing load of the speech speed conversion means is reduced compared to the case where the waveform after the speech speed conversion by the speech speed conversion means is displayed before and after the conversion section is determined, and the image is displayed before and after the conversion section is determined. There is also an advantage that the waveform of the speech signal after the speech speed conversion can be accurately confirmed after the conversion section is determined as compared with the case where the waveform by the processing is displayed.

  In a preferred aspect of the present invention, the display control means arranges a conversion rate indicating line whose position in the second direction is variably set according to an instruction from the user for the target section, and the speech speed converting means The speech speed conversion is executed at a conversion rate corresponding to the position in the second direction of the point corresponding to the time point of the conversion rate indicating line with respect to the audio signal at each time point in the section. In the above aspect, since the conversion rate of the speech speed conversion is set according to the conversion rate indicating line in which the user indicates the position in the second direction, the user can change the degree of change of the speech speed to the desired level. There is an advantage that it can be set easily. In a further preferred aspect, the display control means variably sets the angle of the conversion rate instruction value in accordance with an instruction from the user. In the above aspect, there exists an advantage that a user can set the change of a conversion rate with time easily. A specific example of the above aspect will be described later as a second embodiment.

In addition, the speech speed conversion device according to each of the above aspects is realized by hardware (electronic circuit) such as a DSP (Digital Signal Processor) dedicated to speech speed conversion, as well as a CPU (Central Processing Unit) and the like. It is also realized by cooperation between a general-purpose arithmetic processing unit and a program. The program according to the first aspect arranges the speech speed conversion processing for executing the speech speed conversion for the target section specified in the audio signal and the waveform of the audio signal before the speech speed conversion along the time axis in the first direction. The first region and the second region in which the waveform of the speech signal after speech speed conversion is arranged along the time axis in the first direction are juxtaposed in the second direction intersecting the first direction, and before the speech speed conversion. For the target section of the speech signal and the conversion section corresponding to the target section of the speech signal after speech speed conversion, the straight line connecting the start points and the straight line connecting the end points are the first region and the second region. A computer is caused to execute display control processing for displaying a waveform confirmation image arranged therebetween on a display device.
In addition, the program according to the second aspect includes a speech speed conversion process for performing speech speed conversion on a target section specified in the speech signal, and a waveform of the speech signal before speech speed conversion along the time axis in the first direction. Waveform confirmation image in which the arranged first region and the second region in which the waveform after the speech speed conversion of the audio signal is arranged along the time axis in the first direction are juxtaposed in the second direction intersecting the first direction Is a program that causes a computer to execute display control processing to be displayed on the display device. In the display control processing, the conversion interval is variably set in accordance with an instruction from the user, and before the conversion interval is determined, The waveform of the conversion section obtained by expanding and contracting the waveform of the voice signal before speed conversion in the direction of the time axis by image processing is arranged in the second area, and after the conversion section is determined, the waveform of the conversion section after speech speed conversion for the voice signal is Arrange in the second region.
According to the program of the present invention, the same operation and effect as the speech speed conversion device according to each of the above aspects can be obtained. The program of the present invention is provided to a user in a form stored in a computer-readable recording medium and installed in the computer, or provided from a server device in a form of distribution via a communication network and installed in the computer. Is done.

<A: First Embodiment>
FIG. 1 is a block diagram of a speech speed converting apparatus according to the first embodiment of the present invention. As shown in FIG. 1, the speech speed conversion device 100 is realized by a computer system including an arithmetic processing device 10 and a storage device 12. The storage device 12 stores a program executed by the arithmetic processing device 10 and data used by the arithmetic processing device 10. For example, an audio signal S 1 representing a waveform on the time axis of audio is stored in the storage device 12. A known recording medium such as a semiconductor recording medium or a magnetic recording medium is arbitrarily employed as the storage device 12.

  The arithmetic processing device 10 functions as the display control unit 32 and the speech rate conversion unit 34 by executing a program stored in the storage device 12. The display control unit 32 controls image display. The speech speed conversion unit 34 generates the speech signal S2 by converting the speech speed of the speech signal S1. The degree of speech speed conversion by the speech speed conversion unit 34 (hereinafter referred to as “conversion rate”) is variably set. A known technique is arbitrarily employed for the speech speed conversion performed by the speech speed conversion unit 34. For example, the time axis companding technology (for example, PICOLA (Pointer Interval Controlled Overlap and Add)) that changes the speech speed while maintaining the pitch by inserting or deleting the waveform of the basic period detected from the audio signal S1 It is preferably used for speech speed conversion by the speed conversion unit 34.

  An input device 22, a display device 24, and a sound emitting device 26 are connected to the arithmetic processing device 10. The input device 22 is composed of an operator operated by a user for inputting an instruction to the speech speed conversion device 100. For example, a mouse is suitable as the input device 22. The display device 24 displays an image under the control of the display control unit 32. The sound emitting device 26 emits sound corresponding to the sound signal S (the sound signal S1 or the sound signal S2) supplied from the arithmetic processing device 10.

  FIG. 2 is a schematic diagram of a waveform confirmation image 40 that the display control unit 32 displays on the display device 24. As shown in FIG. 2, the waveform confirmation image 40 includes a waveform comparison area Aw. The waveform comparison area Aw is an area for comparatively displaying the waveform W1 of the speech signal S1 before speech speed conversion and the waveform W2 of the speech signal S2 after speech speed conversion.

  As shown in FIG. 2, the waveform contrast area Aw is divided into an area A1, an area A2, and an area A3. The region A1, the region A2, and the region A3 are rectangular regions that are long in the X direction. The display control unit 32 arranges the waveform W1 of the audio signal S1 in the region A1 with the X direction (horizontal direction) as a time axis. Similarly, the display control unit 32 arranges the waveform W2 of the audio signal S2 with the X direction as a time axis in the area A2. The region A1 and the region A2 are juxtaposed with an interval in the Y direction intersecting (orthogonal) in the X direction. The time axis of the area A1 and the time axis of the area A2 have a common starting point. When the user operates the scroll bar B, the display control unit 32 moves the section displayed in the waveform comparison area Aw of the waveform W1 and the waveform W2 along the time axis.

  When the user operates the operator Ua1 using the input device 22, the display control unit 32 changes the amplitude of the waveform W1 by increasing or decreasing the scale in the Y direction in the area A1. Similarly, when the operator Ua2 is operated, the display control unit 32 changes the amplitude of the waveform W2 by increasing or decreasing the scale in the Y direction in the area A2. When the operation element Ua3 is operated, the display control unit 32 reduces the X-direction scale of the area A1 and the area A2 (that is, the time length of the section displayed in the waveform comparison area Aw of the waveform W1 and the waveform W2). Increase or decrease. Note that only the waveform W1 and the waveform W2 on the display are changed by the operation of the operators Ua1 to Ua3, and the actual audio signal S1 and audio signal S2 are not changed by the operation of the operators Ua1 to Ua3. According to the above configuration, the waveform W1 and the waveform W2 can be changed to a mode that is easy for the user to visually recognize. For example, even when the original amplitude of the audio signal S1 or the audio signal S2 is small, the waveform W1 or the waveform W2 can be easily confirmed by increasing the amplitude on the display of the waveform W1 or the waveform W2.

  The operation element Ub1 and the operation element Ub2 are operation elements for the user to view the reproduced sound of the audio signal S1 and the audio signal S2. That is, when the user operates the operator Ub1, the sound signal S1 before the speech speed conversion stored in the storage device 12 is supplied to the sound emitting device 26. On the other hand, when the user operates the operator Ub2, the speech signal S2 after the speech speed conversion by the speech speed conversion unit 34 is supplied to the sound emitting device 26.

  As shown in FIG. 2, the region A3 is located between the region A1 and the region A2. The display control unit 32 arranges a straight line LA and a straight line LB indicating the relationship on the time axis between the waveform W1 in the region A1 and the waveform W2 in the region A2 in the region A3. The procedure for setting the straight line LA and the straight line LB will be described in detail below.

  By appropriately operating the input device 22, the user designates a part of the waveform W1 in the area A1 as the target section T1, as shown in FIG. For example, the user drags the mouse of the input device 22 in the X direction to specify the start point (for example, drag start point) and end point (for example, drag end point) of the target section T1. As shown in FIG. 3, the display control unit 32 displays the target section T1 designated by the user in the area A1. For example, the display control unit 32 changes the aspect (for example, color) of the target section T1. Further, as shown in FIG. 3, the display control unit 32 includes a straight line LA extending in the Y direction from the start point of the target section T1 and a straight line LB extending in the Y direction from the end point of the target section T1 in the area A3. indicate. By repeating the above operation, the user can designate a plurality of target sections T1 as shown in FIG.

  The user can arbitrarily select (activate) any target section T1 among the plurality of target sections T1 in the area A1 by appropriately operating the input device 22. The display control unit 32 changes (highlights) the display mode of the target section T1 selected by the user (hereinafter, particularly referred to as “selected section T1_S”). Further, the user can move the start point and the end point of the selected section T1_S in the X direction by operating the input device 22. The display control unit 32 updates the selection section T1_S displayed in the area A1 to the selection section T1_S corresponding to the start point and end point after the change by the user. Further, when the user instructs to delete the target section T1, the display control unit 32 cancels the designation of the target section T1 for the selected section T1_S and deletes the display of the target section T1 in the area A1.

  The user operates the input device 22 to designate a section (hereinafter referred to as “conversion section”) T2 after execution of speech speed conversion for the selected section T1_S. The conversion section T2 is a section obtained by extending or shortening the selection section T1_S. For example, when the user rotates the mouse wheel of the input device 22 downward, as shown in FIG. 4, the display control unit 32 sets the lower end portion pB of the straight line LB to X by a distance corresponding to the rotation angle of the wheel. Move to the positive side of the direction (the direction in which time passes). On the other hand, when the user rotates the wheel in the upward direction, the display control unit 32 moves the lower end portion pB by a distance corresponding to the rotation angle of the wheel to the negative side in the X direction (the direction in which the time goes back). As shown in FIG. 4, a section from the lower end portion pA of the straight line LA to the lower end portion pB of the straight line LB is designated as the conversion section T2. That is, the straight line LA is a straight line connecting the start point of the selection section T1_S and the conversion section T2 in the area A1, and the straight line LB is a straight line connecting the end point of the selection section T1_S and the end point of the conversion section T2. is there.

  The conversion section T2 is determined when the user operates the operation element (conversion) Uc1 in FIG. When the conversion section T2 is determined, the speech speed conversion unit 34 performs the speech speed conversion on the portion in the selected section T1_S of the audio signal S1. The conversion rate (magnification) of the speech speed conversion is set to the relative ratio (P1 / P2) of the time length P1 of the selected section T1_S to the time length P2 of the conversion section T2.

  As shown in FIG. 5, the display control unit 32 displays the determined conversion section T2 in the area A2. For example, the display mode (for example, color) of the conversion section T2 in the area A2 is changed. Then, as shown in FIG. 5, the display control unit 32 arranges the waveform after the speech speed conversion by the speech speed conversion unit 34 (a waveform W2 obtained by extending or shortening the selection section T1_S of the audio signal S1) in the conversion section T2. To do. Further, the display control unit 32 causes the waveform after the end point of the selection section T1_S to follow the conversion section T2 in the area A2, and among the plurality of target sections T1, straight lines corresponding to the target sections after the current selection section T1_S. The lower end pA of LA and the lower end pB of the straight line LB are moved in the X direction by the same movement amount as the straight line LB corresponding to the current selection section T1_S. On the other hand, when the user operates the operator Uc2, the display control unit 32 changes the waveform W2 in the conversion section T2 to the waveform before the speech speed conversion. That is, the contents of editing for the selected section T1_S are cancelled.

  By repeating the above processing for each target section T1, as illustrated in FIG. 2, the conversion section T2 after the speech speed conversion of each target section T1 is displayed in the region A2, and is converted into the target section T1. A straight line LA and a straight line LB connecting the section T2 are displayed in the area A3.

  In the embodiment described above, the waveform W1 of the speech signal S1 before the speech speed conversion and the waveform W2 of the speech signal S2 after the speech speed conversion are displayed in comparison, so the degree to which the speech speed of the speech has been changed. Can be grasped intuitively by the user. In addition, since the straight line LA and the straight line LB that connect the respective target sections T1 of the audio signal S1 and the respective conversion sections T2 of the audio signal S2 are arranged in the area A3, the target section T1 and the conversion section T2 are preceded and shortened. There is also an advantage that the user can recognize it intuitively.

<B: Second Embodiment>
Next, a second embodiment of the present invention will be described. In addition, about the element which an effect | action and function are the same as that of 1st Embodiment in each following form, the same code | symbol as the above is attached | subjected and each detailed description is abbreviate | omitted suitably.

  FIG. 6 is a schematic diagram of a waveform confirmation image 40 displayed on the display device 24 by the display control unit 32 according to the present embodiment. As shown in FIG. 6, in the area A3 of the waveform confirmation image 40, a conversion rate indicating line R is arranged for each target section T1 designated by the user in the waveform W1. The conversion rate indicating line R is a line segment that specifies a conversion rate applied to speech speed conversion of the audio signal S1 at each time point on the time axis. That is, the position in the Y direction of each point on the conversion rate indicating line R is designated as the conversion rate of the speech speed conversion for the audio signal S1.

  A reference line LR extending in the X direction is arranged in the center of the region A3 in the Y direction. The reference line LR means a reference value (that is, “1”) of a conversion rate at which the speech speed does not change before and after the speech speed conversion. As the conversion rate instruction line R is separated from the reference line LR to the negative side (upward) in the Y direction, the rate of change in speech speed increases (that is, the speech speed increases due to the speech speed conversion). The rate of change in speech rate conversion decreases as the distance from the reference line LR to the positive side (downward) in the Y direction decreases (that is, the speech rate decreases due to speech rate conversion).

  As in the first embodiment, the user designates one or more target sections T1 for the waveform W1 in the area A1 by appropriately operating the input device 22. As shown in FIG. 7, the display control unit 32 displays the target section T1 in the area A1 and displays the straight line L0A and the straight line L0B in the area A3. The straight line L0A is a line segment extending in the Y direction from the start point of the target section T1, and the straight line L0B is a line segment extending in the Y direction from the end point of the target section T1.

  The display control unit 32 displays the conversion rate instruction line R in the area A3 for the target section T1 (selected section T1_S) selected by the user. As shown in FIG. 8, the conversion rate indicating line R is a line segment extending over the end point eA on the straight line L0A and the end point eB on the straight line L0B. The user can change the position of the conversion rate indicating line R in the Y direction and the angle with respect to the X direction by appropriately operating the input device 22. For example, the user individually moves the end point eA and the end point eB of the conversion rate indicating line R in the Y direction along the straight line L0A and the straight line L0B (for example, drag the end point eA and the end point eB with the mouse of the input device 22). The angle of the conversion rate indicating line R can be adjusted. Further, the user adjusts the position of the entire conversion rate indicating line R in the Y direction while maintaining the angle, for example, by dragging the portion other than the end points (eA, eB) of the conversion rate indicating line R with the mouse. it can. The display control unit 32 updates the position and angle of the conversion rate instruction line R arranged in the area A3 as needed according to an instruction from the user.

  The position and angle of the conversion rate indicating line R are determined when the user operates the operation element Uc1 in FIG. When the conversion rate instruction line R is determined, the speech rate conversion unit 34 responds to the position in the Y direction of the point corresponding to the time point of the conversion rate instruction line R with respect to the audio signal S1 at each time point in the selected section T1_S. The speech rate conversion is executed at the conversion rate. For example, as shown in FIG. 10, the speech rate conversion for the portion of time t in the audio signal S1 is performed at the conversion rate rX corresponding to the position in the Y direction of the point eX corresponding to the time t on the conversion rate indicating line R. Applies.

  As understood from the above description, in the section where the conversion rate indicating line R is located on the region A1 side with respect to the reference line LR, the speech speed of the audio signal S2 is increased compared with the audio signal S1 (therefore, accordingly). The time length of the conversion section T2 is shorter than the selection section T1_S), and in the section where the conversion rate indicating line R is located on the region A2 side with respect to the reference line LR, the speech speed of the voice signal S2 is compared with the voice signal S1. (Therefore, the time length of the conversion section T2 is longer than the selection section T1_S). Further, in the section where the conversion rate indicating line R is inclined so that the end point eB is located on the region A1 side from the end point eA (for example, in the case of FIG. 10), the speech speed of the audio signal S2 gradually increases, and the end point eB In a section where the conversion rate indicating line R is inclined so as to be located on the region A2 side with respect to the end point eA, the speech speed of the voice signal S2 gradually decreases. In a section where the conversion rate instruction line R is parallel to the X direction, the speech speed of the voice signal S2 is constant.

When the conversion rate indicating line R is determined, the display control unit 32 displays the conversion section T2 specified from the conversion rate indicating line R in the area A2, as shown in FIG. 9, and similarly to the first embodiment. For the selected section T1_S and the conversion section T2, a straight line LA connecting the start points and a straight line LB connecting the end points are displayed in the area A3. Further, the display control unit 32 arranges the waveform W2 after the speech speed conversion by the speech speed conversion unit 34 in the conversion section T2 in the area A2. The time length P2 (FIG. 10) of the conversion interval T2 is, for example, the conversion rate r1 of the end point eA and the conversion rate r2 of the end point eB of the conversion rate indicating line R and the time length P1 of the selection interval T1_S: It is calculated by substituting for.
P2 = {2 / (r1 + r2)}. P1 (1)
That is, in the first embodiment, the conversion rate of the speech rate conversion is set from the conversion section T2 in which the user specifies the time length, whereas in this embodiment, the user specifies with the conversion rate instruction line R. The conversion section T2 is set so as to correspond to the conversion rate that has been obtained.

  As described above, in this embodiment, since the conversion rate instruction line R indicating the conversion rate applied to the speech speed conversion is displayed in the area A3, the user can intuitively understand the direction and degree of the conversion of the speech speed. There is an advantage that can be grasped. In particular, in the present embodiment, since the reference line LR is arranged in the area A3, the section in which the conversion rate indicating line R exists above the reference line LR increases the speech speed (or the section that exists below the reference line LR). The effect that the user can intuitively grasp the direction of the change in the speech speed by the speech speed conversion is particularly remarkable. Further, in this embodiment, since the conversion rate instruction line R is set so as to be inclined with respect to the X direction (Y direction), in addition to the effect that the speech speed of the audio signal S2 can be changed with time, the audio There is also an advantage that the degree of change in speech speed in the signal S2 can be intuitively grasped from the angle of the conversion rate indicating line R. For example, when the angle of the conversion rate instruction line R is large, the speech speed of the audio signal S2 changes abruptly.

<C: Third Embodiment>
FIG. 11 is a schematic diagram of a waveform confirmation image 40 displayed on the display device 24 by the display control unit 32 according to the present embodiment. As shown in FIG. 11, the waveform confirmation image 40 of this embodiment includes a default value application unit 50, a variable application unit 60, and a temporary storage unit 70 in addition to the elements illustrated in FIG. 6 (for example, the waveform comparison area Aw). Consists of including.

  The default value application unit 50 is an area operated by the user in order to apply a default (preset) conversion rate to speech speed conversion. As shown in FIG. 11, a plurality (three) of operators Ud1 to Ud3 are arranged in the default value application unit 50. When the user operates the operator Ud1 (slightly faster), the speech speed conversion unit 34 applies speech speed conversion to which the predetermined conversion rate (eg, “1.1”) indicating an increase in speech speed is applied to the entire audio signal S1. By executing this, an audio signal S2 is generated. When the operator Ud2 (slightly slow) is operated, the speech speed conversion unit 34 performs speech speed conversion on the entire speech signal S1 by applying a predetermined conversion rate (for example, “0.9”) indicating a decrease in the speech speed. As a result, an audio signal S2 is generated. When the operator Ud3 (slow only at the beginning) is operated, the speech speed conversion unit 34 performs speech speed conversion to which the predetermined conversion rate (eg, “0.9”) indicating a decrease in the speech speed is applied. Of these, the audio signal S2 is generated by executing it only in a section of a predetermined length from the starting point.

  The display control unit 32 displays the audio signal S2 generated by the speech speed conversion unit 34 in response to the operation of the operators Ud1 to Ud3 in the area A2. After adjusting the speech speed using the default value application unit 50, the user can adjust the speech speed individually for each target section T1 in the same manner as in the first embodiment or the second embodiment. As described above, since the speech speed of the audio signal S2 is adjusted to the default value by operating the default value application unit 50, there is an advantage that the burden on the user of adjusting the speech speed is reduced.

  The variable application unit 60 in FIG. 11 is an area operated by the user in order to use the existing conversion rate instruction line R. As illustrated in FIG. 11, the variable application unit 60 includes an operation element Ue1 and an operation element Ue2. For example, when the user operates the operator Ue1 (save) in a state where the conversion rate instruction line R is set for the selected section T1_S as shown in FIGS. 8 and 9, the arithmetic processing unit 10 displays the conversion rate instruction line R. Data (hereinafter referred to as “conversion rate data”) is stored in the storage device 12. The conversion rate data is, for example, data indicating the positions in the Y direction of the end points eA and eB of the conversion rate indicating line R. Conversion rate data is individually stored for each of a plurality of conversion rate indicating lines R having different positions and angles.

  On the other hand, when the user operates the operator Ue2 and selects one conversion rate data, the display control unit 32 corresponds the conversion rate indicating line R indicated by the conversion rate data to the current selection section T1_S. To place. Similar to the second embodiment, the user can arbitrarily adjust the position and angle of the conversion rate instruction line R set in the selection section T1_S. Since the existing conversion rate instruction line R is applied by operating the variable application unit 60 as described above, there is an advantage that the burden on the user of creating the conversion rate instruction line R is reduced.

  The temporary storage unit 70 in FIG. 11 is operated by the user in order to store a file indicating the contents of temporary settings in the waveform confirmation image 40 (hereinafter referred to as “setting file”) in the storage device 12 and use it at any time. It is an area. As illustrated in FIG. 11, the temporary storage unit 70 includes a plurality (three) of regions 72 corresponding to separate setting files. When the user operates the operation element Uf1 in any of the areas 72, a setting file corresponding to the area 72 is selected.

  When the user operates the operator Uf2 (memory) in any one of the areas 72, the arithmetic processing apparatus 10 stores the setting contents at the current time in the setting file corresponding to the area 72. The setting file includes, for example, an audio signal S1 before the speech speed conversion, information (for example, the position of the start point and the end point) specifying each target section T1 specified in the audio signal S1, and the audio signal S2 after the speech speed conversion. And information for specifying each conversion section T2 designated in the audio signal S2. When the conversion rate indicating line R is set, information for specifying the conversion rate indicating line R is also stored in the setting file.

  After the operation element Uf2 is operated (after the setting file is created or updated), the user can continue editing the audio signal S2 (setting the conversion section T2 and the conversion rate indicating line R). When the user operates the operation element Ug in the temporary storage unit 70, the arithmetic processing device 10 acquires the setting file selected by the operation of the operation element Uf1 from the storage device 12, and obtains the audio signal S2 in the setting file. The sound is output to the sound emitting device 26. Therefore, the reproduced sound of the audio signal S2 when the operation element Uf2 is operated is radiated from the sound emitting device 26.

  On the other hand, when the user operates the operator Uf3 (return) in any of the areas 72, the arithmetic processing device 10 acquires the setting file corresponding to the area 72 from the storage device 12, and the contents of the setting file are waveformd. Reflected in the contrast area Aw. That is, the audio signal S1, the audio signal S2, the target section T1, and the conversion section T2 are restored to the contents at the time of operation of the operator Uf2. When the operator Uf4 (clear) in any of the areas 72 is operated, the arithmetic processing device 10 initializes a setting file corresponding to the area 72. That is, the setting contents at the time of operation of the operator Uf2 (memory) are deleted.

  As described above, the setting contents when the operation element Uf2 is operated are held in the storage device 12 and are reflected in the waveform comparison area Aw at any time by the operation of the operation element Uf3. However, it is possible to reduce the work burden on the user who wants to generate the desired audio signal S2.

<D: Modification>
Various modifications can be made to each of the forms exemplified above. An example of a specific modification is as follows. Two or more aspects may be arbitrarily selected from the following examples and combined.

(1) Modification 1
In each of the above embodiments, the waveform W2 of the voice signal S2 actually generated by the speech speed conversion unit 34 is arranged in the area A2 (conversion section T2), but the waveform W1 in the target section T1 in the voice signal S1 is imaged. A configuration in which the waveform W2 in the conversion section T2 is calculated by expanding and contracting in the direction of the time axis by processing is also suitable. That is, the speech speed conversion by the speech speed conversion unit 34 is not essential for specifying the waveform W2 in the area A2. However, the waveform W2 calculated by image processing does not completely match the waveform W2 calculated by actual speech speed conversion. Therefore, from the viewpoint of allowing the user to accurately confirm the waveform W2 of the speech signal S2 after the speech speed conversion, the waveform W2 generated by the actual speech speed conversion is arranged from the first embodiment to the third embodiment. A configuration is preferred.

  A configuration in which the waveform W2 specified by the speech speed conversion and the waveform W2 specified by the image processing are used together is also suitable. For example, a configuration is adopted in which the waveform W2 by image processing is displayed before the conversion section T2 is determined, and the waveform W2 after the speech speed conversion is displayed after the conversion section T2 is determined. Further details are as follows.

  When the user designates the target section T1 of the audio signal S1 (before the conversion section T2 is determined), the display control unit 32 applies a waveform W2 obtained by expanding and contracting the waveform W1 in the target section T1 by image processing in the area A2. It arrange | positions to the conversion area T2 corresponding to the object area T1. The expansion rate of the waveform W1 by image processing is set according to the relative ratio of the time lengths of the target section T1 and the conversion section T2. The display control unit 32 performs image processing on the waveform W2 corresponding to the changed conversion section T2 every time the user changes the conversion section T2 (every time the conversion rate indicating line R is changed in the second embodiment). Calculated in step A2 and placed in area A2.

  On the other hand, when the user determines the conversion section T2 (conversion rate indicating line R in the second embodiment) by operating the operator Uc1 (conversion), the speech speed conversion unit 34 converts the speech speed into the waveform W1 of the selection section T1_S. To generate the waveform W2 in the conversion section T2. The display control unit 32 deletes the waveform W2 generated by the image processing from the area A2, and arranges the waveform W2 generated by the speech speed conversion unit 34 in the conversion section T2.

  According to the above configuration, since the waveform W2 (waveform generated by image processing) is displayed even during the adjustment of the conversion section T2, the user can intuitively grasp the change in the waveform of the audio signal S2. There is. In addition, the processing load by the speech speed conversion unit 34 is reduced compared to the case where the waveform W2 after the speech speed conversion is displayed before the conversion section T2 is determined (during adjustment), and the waveform W2 resulting from the image processing is converted into the conversion section T2. There is an advantage that the user can accurately confirm the voice signal S2 after the speech speed conversion, compared with the case where it is displayed after the confirmation. Note that after the conversion section T2 is determined, the waveform W2 obtained by image processing and the waveform W2 after the speech speed conversion may be overlapped and arranged in the region A2.

(2) Modification 2
In the second embodiment, the conversion rate indicating line R is a straight line (line segment), but a configuration in which the conversion rate indicating line R is a curved line is also employed. For example, a curve defined by a predetermined function or a free curve arbitrarily generated by the user is adopted as the conversion rate indicating line R. In the second embodiment, the user moves only the end point eA and the end point eB, but a configuration in which the user moves a point in the middle of the conversion rate instruction line R is also suitable.

(3) Modification 3
A method for displaying the target section T1 of the audio signal S1 and the conversion section T2 of the audio signal S2 is arbitrary. For example, in each of the above embodiments, the aspect of the target section T1 and the conversion section T2 is changed, but there is a configuration in which figures indicating the start and end points of the target section T1 and the conversion section T2 are arranged in the vicinity of the area A1 and the area A2. Adopted.

(4) Modification 4
The conversion rate indicating line R, the straight line LA, and the straight line LB in the second embodiment can be arranged in separate areas. For example, the straight line LA and the straight line LB are arranged in the region A3 between the region A1 and the region A2 as in the first embodiment, and converted into the region opposite to the region A3 with the region A1 (or region A2) interposed therebetween. A rate indicating line R, a straight line L0A, and a straight line L0B may be arranged.

(5) Modification 5
In each of the above forms, the target section T1 of the area A1 and the conversion section T2 of the area A2 are displayed and the straight line LA and the straight line LB are displayed in the area A3. However, the target section T1 and the conversion section T2 are displayed and displayed as a straight line. A configuration in which LA and straight line LB are not displayed, and a configuration in which straight line LA and straight line LB are displayed and target section T1 and conversion section T2 are not displayed are also employed.

1 is a block diagram of a speech speed conversion device according to a first embodiment of the present invention. It is a schematic diagram of a waveform confirmation image. It is a conceptual diagram for demonstrating selection of an object area. It is a conceptual diagram for demonstrating designation | designated of the conversion area. It is a conceptual diagram for demonstrating the determination of a conversion area. It is a schematic diagram of the waveform confirmation image in the second embodiment of the present invention. It is a conceptual diagram for demonstrating selection of an object area. It is a conceptual diagram for demonstrating the setting of a conversion rate instruction | indication line. It is a conceptual diagram for demonstrating the determination of a conversion area. It is a conceptual diagram which shows the relationship between a conversion rate instruction | indication line and a conversion rate. It is a schematic diagram of the waveform confirmation image in the third embodiment of the present invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 ... Speech rate conversion device, 10 ... Arithmetic processing device, 12 ... Memory | storage device, 22 ... Input device, 24 ... Display device, 26 ... Sound emission device, 32 ... Display control part, 34 ... Speaking speed conversion unit, 40 ... Waveform confirmation image.

Claims (4)

Speech rate conversion means for performing speech rate conversion for the target section specified in the audio signal;
A first region in which the waveform of the speech signal before speech speed conversion is arranged along the time axis in the first direction, and a waveform of the speech signal after speech speed conversion is arranged along the time axis in the first direction. The second area is juxtaposed in the second direction intersecting the first direction, and the target section of the speech signal before speech speed conversion and the conversion section corresponding to the target section of the speech signal after speech speed conversion A display control means for displaying, on a display device, a waveform confirmation image in which a straight line connecting the start points and a straight line connecting the end points are arranged between the first region and the second region. Speed converter. Speech rate conversion means for performing speech rate conversion for the target section specified in the audio signal;
A first region in which the waveform of the speech signal before speech speed conversion is arranged along the time axis in the first direction, and a waveform of the speech signal after speech speed conversion is arranged along the time axis in the first direction. The second region comprises display control means for displaying on the display device the waveform confirmation image juxtaposed in the second direction intersecting the first direction ,
The display control means variably sets a conversion interval according to an instruction from a user, and converts the waveform of the speech signal before speech speed conversion in the direction of the time axis by image processing before the conversion interval is determined. A speech speed conversion device that arranges a waveform of a section in a second area, and after determining the conversion section, arranges a waveform of the conversion section after speech speed conversion for the speech signal in the second area . Speech rate conversion processing for performing speech rate conversion for the target section specified in the audio signal;
A first region in which the waveform of the speech signal before speech speed conversion is arranged along the time axis in the first direction, and a waveform of the speech signal after speech speed conversion is arranged along the time axis in the first direction. The second area is juxtaposed in the second direction intersecting the first direction, and the target section of the speech signal before speech speed conversion and the conversion section corresponding to the target section of the speech signal after speech speed conversion A display control process for causing a display device to display a waveform confirmation image in which a straight line connecting start points and a straight line connecting end points are arranged between the first region and the second region. Program to make. Speech rate conversion processing for performing speech rate conversion for the target section specified in the audio signal;
A first region in which the waveform of the speech signal before speech speed conversion is arranged along the time axis in the first direction, and a waveform of the speech signal after speech speed conversion is arranged along the time axis in the first direction. The second area is a program for causing a computer to execute a display control process for causing a display device to display waveform confirmation images juxtaposed in a second direction intersecting the first direction ,
In the display control process, the conversion section is variably set according to an instruction from the user, and the conversion of the waveform of the speech signal before the speech speed conversion is expanded and contracted in the direction of the time axis by image processing before the conversion section is determined. A program that arranges the waveform of the section in the second area, and after the conversion section is determined, arranges the waveform of the conversion section after speech speed conversion for the voice signal in the second area .

Images