Audio output control device, audio output control method, and program

Abstract

The present invention provides a voice output control device, a voice output control method, and a program that can easily and appropriately control the output of alarm sounds that have sufficient perceptibility and functionality. [Solution] In an audio output control device 1 that outputs a predetermined alarm sound to alert a user riding in a vehicle, the device has a volume determination unit 24 that determines the volume of the alarm sound that satisfies predetermined perceptibility and predetermined functionality. The volume determination unit 24 can determine the volume of the alarm sound based on a multiple regression equation (equation (2)) obtained with at least the type of alarm sound (x1, x2), the volume of the running sound (x3), whether the running section is a tunnel section or an open section (x5), whether or not the vehicle is running on a railway bridge (x7), and the user's age (x9) as explanatory variables and the volume of the alarm sound as the dependent variable.

Description

Technical Field

[0001] The present invention relates to an audio output control device, an audio output control method, and a program.

Background Art

[0002] Regarding the warning sound in a railway vehicle, it is necessary to output it at a volume that not only satisfies the perceptibility of being clearly audible but also has sufficient functionality such as strongly attracting attention and promoting arousal. On the other hand, if it is output at a large volume randomly, there is a risk of burdening the ears.

[0003] In Patent Document 1, regarding the warning sound related to railways, a method of determining the volume of a warning sound having perceptibility and functionality by performing frequency analysis of the background noise and the warning sound presented in the cab has been proposed.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] <00000​​​​​​​​​​One aspect of the present invention is an audio output control device that outputs a predetermined alarm sound to alert a user riding in a vehicle, and includes a volume determination unit that determines the volume of the alarm sound to satisfy predetermined perceptibility and predetermined functionality, wherein the volume determination unit determines the volume of the alarm sound based on a multiple regression equation obtained with at least the type of alarm sound, the volume of the running sound, whether the running section is a tunnel section or an open section, whether or not the vehicle is crossing a railway bridge, and the user's age as explanatory variables, and the volume of the alarm sound as the dependent variable.

[0008] One aspect of the present invention is an audio output control method for outputting a predetermined alarm sound to alert a user riding in a vehicle, and includes a volume determination step for determining the volume of the alarm sound that satisfies predetermined perceptibility and predetermined functionality, wherein the volume determination step determines the volume of the alarm sound based on a multiple regression equation obtained with at least the type of alarm sound, the volume of the running sound, whether the running section is a tunnel section or an open section, whether or not the vehicle is crossing a railway bridge, and the user's age as explanatory variables, and the volume of the alarm sound as the dependent variable.

[0009] One aspect of the present invention is a program that can be executed by a computer capable of exchanging information with an input / output device, which outputs a predetermined alarm sound to alert a user riding in a vehicle, and includes a volume determination step of determining the volume of the alarm sound that satisfies predetermined perceptibility and predetermined functionality, wherein the volume determination step determines the volume of the alarm sound based on a multiple regression equation obtained with at least the type of alarm sound, the volume of the running sound, whether the running section is a tunnel section or an open section, whether or not the vehicle is crossing a railway bridge, and the user's age as explanatory variables, and the volume of the alarm sound as the dependent variable. [Effects of the Invention]

[0010] According to the present invention, the output of an alarm sound that is sufficiently perceptible and functional can be controlled simply and appropriately. [Brief explanation of the drawing]

[0011] [Figure 1] Figure 1 is a block diagram showing an example configuration of the audio output control device 1. [Figure 2] Figure 2 is a table showing the acoustic parameters of alarm sounds A to C. [Figure 3] Figure 3 is a table showing the explanatory variables of the running sound. [Figure 4] Figure 4 is a graph showing the volume of the alarm sound that satisfies the perceivedness adjusted by the participants, by age group. [Figure 5] Figure 5 is a graph showing the volume of the alarm sound that satisfies the functionality adjusted by the participants, by age group. [Figure 6] Figure 6 is a table showing the results of the multiple regression analysis. [Figure 7] Figure 7 is a table showing the explanatory variables of the running sound and the adjusted volume calculated by formula (2). [Figure 8] Figure 8 is a table showing the results of the subjective evaluation. [Figure 9] Figure 9 is a flowchart showing the flow of the alarm sound output process.

Mode for Carrying Out the Invention

[0012] [First Embodiment] Hereinafter, the voice output control device and the voice output control method will be described with reference to the drawings. <反映

[0013] <反映 (Configuration of Voice Output Control Device 1) Figure 1 is a block diagram showing a configuration example of the voice output control device 1. Here, a case where an alarm sound for alerting a crew member such as a driver (hereinafter, appropriately referred to as a user) riding on a railway vehicle is output will be described as an example.

[0014] The voice output control device 1 is configured to have the functions of an operation input unit 11, an external state acquisition unit 12, a user state acquisition unit 13, a running information acquisition unit 14, a storage unit 15, a control unit 16, and a voice output unit 17. Here, the voice output control device 1 will be described as having all of the above-described functions, but these functions may be configured by a plurality of devices and may be capable of exchanging information with each other, or the voice output control device 1 may include other functions.

[0015] The operation input unit 11 receives the user's operation input, the information stored in the storage unit 15, or the input of the information necessary for the processing of the control unit 16, and supplies it to the control unit 16. The operation input unit 11 is configured to include input devices such as, for example, a keyboard, a mouse, a touch panel, a microphone, and a reading device for an external storage device or an image input device.

[0016] The external state acquisition unit 12 acquires an external state for determining whether an alarm or a warning necessary for railway operation is required, and supplies it to the control unit 16. The external state acquisition unit 12 may be configured to include an imaging device, a sensor, etc. for detecting a dangerous state or the like, or may be configured to acquire information for detecting a dangerous state or the like acquired by another device.

[0017] The user state acquisition unit 13 acquires information necessary for detecting the state of the user, and supplies it to the control unit 16. The user state acquisition unit 13 is configured by, for example, an imaging device such as a camera or an input device that acquires image data captured by an external imaging device. In this case, the user state acquisition unit 13 acquires an image including the imaged state of the user and supplies it to the control unit 16. Further, the user state acquisition unit 13 is, for example, a wearable device that measures the biological information of the user. In this case, the user state acquisition unit 13 acquires biological information such as the user's pulse, blood pressure, and respiration rate, and supplies it to the control unit 16. The information necessary for detecting the state of the user acquired by the user state acquisition unit 13 may be multiple types of information.

[0018] The running information acquisition unit 14 acquires information indicating the running status of the vehicle and supplies it to the control unit. Information indicating the running status of the vehicle includes, for example, the volume of running noise in the driver's cab, information on whether the vehicle is a passenger vehicle or a freight vehicle, information on whether the running section is a tunnel section or an open section, information on whether the track condition is slab or ballast, information on whether or not the vehicle is crossing a railway bridge, and information on whether or not the windows are open. The running information acquisition unit 14 has a function to acquire running status information, for example, by consisting of an imaging device such as a camera and a microphone, or by acquiring running status information acquired by an external device.

[0019] The memory unit 15 is configured, for example, with ROM (Read Only Memory), RAM (Random Access Memory), and non-volatile memory. The memory unit 15 stores information related to alarm sounds. Multiple alarm sounds may be stored to be output, and the operation input unit 11 can be configured to set which alarm sound is used based on, for example, the railway line on which the train is running, the content of the alarm or warning, or selection or setting by the crew member receiving the alarm.

[0020] The control unit 16 consists of a CPU (Central Processing Unit), memory units (ROM (Read Only Memory), RAM (Random Access Memory), non-volatile memory, etc.), hardware, and other elements. The control unit 16 controls the entire voice output control device 1 by executing a control application program (not shown) stored in the memory unit 15, and also functions as a user state determination unit 21 to voice output control unit 25.

[0021] The user state determination unit 21 determines whether or not an alarm is necessary based on the user state information supplied from the user state acquisition unit 13, and supplies the determination result to the voice output execution determination unit 23. Here, the user state determination unit 21 is described as determining the degree of the user's drowsiness (level of alertness) based on the user state information supplied from the user state acquisition unit 13. Specifically, the user state determination unit 21 can, for example, detect the size of the user's pupils from the user's facial image data supplied from the user state acquisition unit 13, or determine the degree of the user's drowsiness from biometric information such as the user's pulse, blood pressure, and respiratory rate supplied from the user state acquisition unit 13. The method by which the user state determination unit 21 determines the degree of the user's drowsiness is not limited to this method.

[0022] The external state determination unit 22 determines, based on the external state information supplied from the external state acquisition unit 12, whether or not a state requiring the output of some kind of alarm sound, and supplies the determination result to the voice output execution determination unit 23. For example, the external state determination unit 22 acquires video information of the front of the vehicle and detection results from various sensors from the external state acquisition unit 12 to detect abnormal or dangerous conditions, or it determines whether or not there is an input signal from an external device indicating that an abnormal or dangerous condition has been detected.

[0023] The audio output execution determination unit 23 determines whether or not to execute alarm sound output based on various setting information input by the operation input unit 11, the user status determination result by the user status determination unit 21, and the external status determination result by the external status determination unit 22. If it determines that alarm sound output should be executed, the audio output execution determination unit 23 supplies the determination result to the volume determination unit 24.

[0024] When the volume determination unit 24 receives a determination result from the voice output execution determination unit 23 that an alarm sound output should be executed, it determines the volume of the alarm sound that satisfies predetermined perceptibility and predetermined functionality.

[0025] A warning sound that satisfies perceptual requirements is one that the user can easily hear. A warning sound that satisfies functional requirements is one that can awaken the user, such as making them feel awake when they hear it. In the same driving conditions, the volume of a functional warning sound is louder than the volume of a perceptual warning sound; therefore, a functional warning sound satisfies perceptual requirements.

[0026] Specifically, the volume determination unit 24 determines the volume of the alarm sound based on a multiple regression equation obtained with at least the type of alarm sound, the volume of the running sound, whether the running section is a tunnel section or an open section, whether or not it is running on a railway bridge, and the user's age as explanatory variables, and the volume of the alarm sound as the dependent variable. Details of the volume determination method by the volume determination unit 24 will be described later.

[0027] The audio output control unit 25 outputs an alarm sound to the outside via the audio output unit 17 at a volume determined by the volume determination unit 24. The audio output unit 17 is configured as an audio output device such as a speaker, or as having a function to output audio data to an external audio output device.

[0028] (Method for determining the volume of the alarm sound) The volume determination method by the volume determination unit 24 will now be explained.

[0029] The following equation is a multiple regression equation used to determine the volume of the alarm sound. Dependent variable = b + a1x1 + a2x2 + a3x3 + a4x4 + a5x5 + a5x6 + a7x7 + a8x8 + a9x9

[0030] The dependent variable is the volume of the alarm sound (dB). x1 to x9 are the independent variables. a1 to a9 are the partial regression coefficients, and b is the intercept.

[0031] Explanatory variables x1 and x2 are values ​​corresponding to the type of alarm sound, and x3 is the volume (dB) of the running sound. x4 is a value indicating whether the vehicle is a passenger or freight vehicle, x5 is a value indicating whether the section of travel is a tunnel or an open section, x6 is a value indicating whether the track condition is a slab track or a ballast track, x7 is a value indicating whether or not the vehicle is traveling on a bridge, and x8 is a value indicating whether or not the window is open. And x9 is a value corresponding to the user's age. Details of each explanatory variable will be described later.

[0032] The partial regression coefficients a1 to a9 and the intercept b are values ​​obtained through experiments described later.

[0033] The volume determination unit 24 determines explanatory variables based on driving information acquired via the driving information acquisition unit 14, and calculates a volume of an alarm sound that satisfies predetermined perceptibility and predetermined functionality by performing a multiple regression equation based on the determined explanatory variables.

[0034] ((explanatory variable)) This section explains the explanatory variables in multiple regression equations.

[0035] (((Type of alarm sound: x1, x2))) It is generally known that the volume of the alarm sound that should be set differs depending on the type of sound to be heard. Therefore, in this embodiment, the type of alarm sound is used as an explanatory variable in a multiple regression equation with the volume of the alarm sound as the dependent variable. The type of alarm sound is represented using dummy variables x1 and x2. For example, there are three types of alarm sounds A to C, which are represented by the acoustic parameters shown in Figure 2. If the alarm sound used is alarm sound A, then x1=1, x2=0; if it is alarm sound B, then x1=0, x2=0; and if it is alarm sound C, then x1=0, x2=1.

[0036] Sounds using a musical scale below 1000Hz are greatly affected by masking under loud vehicle noise; therefore, it is preferable that the alarm sound has a primary frequency of 1000Hz or higher.

[0037] (((Road noise volume: x3))) It is generally known that the louder the running noise, the louder the alarm sound that should be set. Therefore, in this embodiment, the running noise volume (hereinafter referred to as "noise level" as appropriate) is used as an explanatory variable in a multiple regression equation with the alarm sound volume as the dependent variable. x3 is the value of the running noise volume. The running noise volume is, for example, the equivalent noise level, and its unit is decibels (dB).

[0038] (((Is the vehicle a passenger car or a freight car?: x4))) When the type of vehicle is different, even if the volume of the running sound is the same, the volume of the alarm sound that should be set will differ. Freight trains contain a variety of sound sources and have a higher sound pressure than passenger trains, so the volume of the alarm sound that should be set will be higher. Therefore, in this embodiment, whether the vehicle is a passenger train or a freight train (hereinafter referred to as "vehicle type" as appropriate) is used as an explanatory variable in a multiple regression equation with the volume of the alarm sound as the dependent variable. Whether the vehicle is a passenger train or a freight train is represented by a dummy variable x4. If the vehicle type is a freight train, x4 = 1, and if it is a passenger train, x4 = 0.

[0039] (((Is the route a tunnel section or an open-air section?: x5))) When the travel section differs, even if the volume of the running sound is the same, the volume of the alarm sound that should be set will differ. The relationship between the travel section and the setting of the alarm sound volume was unknown. However, the inventors have found that in tunnel sections, sound reverberates more than in open sections, resulting in a higher noise level, and therefore the volume of the alarm sound that should be set will be higher. Therefore, in this embodiment, whether the travel section is a tunnel section or an open section (hereinafter referred to as section type as appropriate) is used as an explanatory variable in a multiple regression equation with the volume of the alarm sound as the dependent variable. Whether the travel section is a tunnel section or an open section is represented by a dummy variable x5. If the travel section is a tunnel section, x5=1, and if it is an open section, x5=0.

[0040] (((Orbital condition: slab or ballast orbit: x6))) When track conditions differ, even if the volume of running noise is the same, the volume of the alarm sound that should be set will differ. Slab tracks made of concrete material are composed of softer rail fastening devices than ballast tracks, and the frequency of running noise is higher, so the volume of the alarm sound that should be set will be higher. Therefore, in this embodiment, whether the track condition is a slab track or a ballast track (hereinafter referred to as slab as appropriate) is used as an explanatory variable in a multiple regression equation with the volume of the alarm sound as the dependent variable. Whether the track condition is a slab track or a ballast track is represented by a dummy variable x6. If the track condition is a slab track, x6 = 1, and if it is a ballast track, x6 = 0.

[0041] (((Whether or not we are crossing a railway bridge: x7))) When traveling on a railway bridge, even if the volume of the running sound is the same, the volume of the alarm sound that should be set differs. When traveling on a railway bridge, vibrations are transmitted from the track to the bridge and radiated as noise, resulting in a higher noise level and an increase in sound pressure level across a wide frequency band. Therefore, the volume of the alarm sound that should be set is higher when traveling on a railway bridge. Accordingly, in this embodiment, whether or not the train is traveling on a railway bridge (hereinafter referred to as "bridge" as appropriate) is used as an explanatory variable in a multiple regression equation with the volume of the alarm sound as the dependent variable. Whether or not the train is traveling on a railway bridge is represented by a dummy variable x7. If the train is traveling on a railway bridge, x7=1, and if it is not traveling on a railway bridge, x7=0.

[0042] (((Whether the window is open or not: x8))) When the train windows are open, the required alarm volume differs even if the overall noise level is the same. When the windows are open, the noise transmitted through the air is greater than when they are closed, resulting in a wider range of frequencies being included overall, thus requiring a higher alarm volume. Therefore, in this embodiment, whether or not the windows are open (hereinafter referred to as "window" as appropriate) is used as an explanatory variable in a multiple regression equation with the alarm volume as the dependent variable. Whether or not the windows are open is represented by a dummy variable x8. If the windows are open, x8=1, and if the windows are closed, x8=0.

[0043] (((User's age: x9))) The appropriate alarm volume may differ depending on the user's age, even if the running noise volume is the same. Users in their 30s or younger may experience higher levels of drowsiness in monotonous situations and require greater stimulation to wake up compared to users in their 40s or older. Therefore, in this embodiment, the user's age is used as an explanatory variable in a multiple regression equation with the alarm volume as the dependent variable. The user's age is represented using a dummy variable x9. If the user is in their 30s or younger, x9=1, and if the user is 40 or older, x9=0.

[0044] ((Partial regression coefficient, intercept)) I will explain partial regression coefficients and intercepts.

[0045] (1) Investigation of alarm sound volume settings under various driving noises The inventor prepared three types of alarm sounds (Sound) as shown in Figure 2 in order to obtain a multiple regression equation for the volume of the alarm sound. Specifically, alarm sound A, alarm sound B which is alarm sound A octave higher, and alarm sound C which has a faster tempo than alarm sound A were prepared. The duration of alarm sounds A to C is approximately 4.8 seconds.

[0046] Furthermore, the inventors prepared eight types of running sounds, noises a to h, as shown in Figure 3. The volume levels of the running sounds were set to five levels: 65, 70, 75, 80, and 85 dB. Each running sound was recorded in the driver's cab of an actual commercial train, and a sound source was synthesized by repeatedly playing 10-second audio clips during constant-speed operation, excluding announcements, warnings, and signals from the driver's cab, the driver's verbal cueing, communication with the control center, and sounds such as passing, overtaking, or being overtaken by other trains. The recording was performed using recording software (Nx42-xR RION) at a sampling frequency of 48 kHz and 24 bits.

[0047] Sixty participants (ages 19-65, male) listened to eight different driving sounds prepared by the inventor, and then played alarm sounds in a randomly specified order, adjusting the volume using a volume control device. The inventor used these volume levels as data.

[0048] Regarding functionality, participants adjusted the volume to the minimum level necessary to wake up. For perceptual adjustments, the criteria were to set the volume to a level that was "somewhat easy to hear" to "easy to hear," adjusting it to a level that could be heard comfortably even while concentrating on driving.

[0049] The equipment used in the survey is as follows: • Powered speakers (MSR100, DZR15, YAMAHA) • Audio interface (Roland Rubix44) • Fader (Alps Alpine) ·DC power supply (DC power supplier AND) • Data recorder (DA-21 RION) • Driving simulator stand and monitor (train driving simulator system, Mitsubishi Precision) • Notebook computers (LIFEBOOK WU2 / F3 Fujitsu, Let's note CF-QV Panasonic) • Video camera (HandyCam Panasonic)

[0050] This study yielded the results shown in Figures 4 and 5 regarding the volume of alarm sounds adjusted by participants. Figure 4 is a graph showing the volume of alarm sounds that satisfied perceptual needs, adjusted by participants, broken down by age group. Figure 5 is a graph showing the volume of alarm sounds that satisfied functional needs, adjusted by participants, broken down by age group.

[0051] (2) Calculation of partial regression coefficients and intercept Multiple regression analysis was performed using the following variables as explanatory variables: the type of alarm sound (x1, x2), the volume of the running sound (x3), whether the vehicle is a passenger or freight vehicle (x4), whether the section of travel is a tunnel or an open section (x5), whether the track condition is a slab track or a ballast track (x6), whether or not the vehicle is traveling on a railway bridge (x7), whether or not the windows are open (x8), and the user's age (x9). The volume of the alarm sound adjusted by the participants (Figures 4, 5) was used as the dependent variable, and the partial regression coefficients, standardized partial regression coefficients, and intercept shown in Figure 6 were obtained.

[0052] As a result, the volume of the alarm sound that satisfies perceptual requirements (y aud Equation (1) is used as the multiple regression equation to calculate the volume of the alarm sound (y) that satisfies the functionality. aro Equation (2) was obtained as the multiple regression equation for calculating ).

[0053] y aud =55.214+0.874x1+1.160x2+0.204x3+0.028x4+1.022x5+0.129x6+0.299x7+0.227x8+0.382x9...(1)

[0054] y aro =63.997+0.766x1+1.282x2+0.177x3-0.003x4+0.703x5+0.160x6+0.204x7+0.078x8+1.481x9...(2)

[0055] As shown in Figure 6, the P-values ​​of the partial regression coefficients in the multiple regression equations for the explanatory variables—type of alarm sound (x1, x2), volume of running sound (x3), whether the running section is a tunnel or an open section (x5), whether or not the train is running on a railway bridge (x7), and the user's age (x9)—were less than 0.05, indicating statistical significance.

[0056] As shown in Figure 6, the magnitude of the standardized partial regression coefficients in the multiple regression equation for perceptuality increased in the following order: volume of running noise (x3: 0.878), type of warning sound (x2: 0.331), whether the running section was a tunnel or an open section (x5: ​​0.310), type of warning sound (x1: 0.250), age (x9: 0.116), and whether or not the train was running on a railway bridge (x7: 0.079).

[0057] As shown in Figure 6, the magnitude of the standardized partial regression coefficients in the multiple regression equation for functionality increased in the following order: volume of running noise (x3: 0.761), age (x9: 0.450), type of warning sound (x2: 0.366), type of warning sound (x1: 0.219), whether the running section is a tunnel section or an open section (x5: ​​0.213), and whether or not the train is running on a railway bridge (x7: 0.054).

[0058] ((Evaluation of volume determination method using equations (1) and (2))) Next, we will explain the evaluation results of the volume determination method using equations (1) and (2).

[0059] The degrees-of-freedom adjusted multiple correlation coefficients of equations (1) and (2) are given by R with respect to the multiple regression equation of perceptuality (equation (1)). *2 =0.887, regarding the functional multiple regression equation (Equation (2)) R *2 The result was 0.926. The multiple correlation coefficient is an evaluation index that indicates prediction accuracy, and is expressed as the square of the correlation coefficient R. The closer it is to "1", the higher the accuracy. This shows that equations (1) and (2) have high accuracy.

[0060] Furthermore, the inventors conducted a subjective evaluation of the volume determined using formula (2).

[0061] The inventors prepared alarm sounds A and B from the alarm sounds shown in Figure 2, and driving sounds a and f from the driving sounds shown in Figure 3. The volume of the alarm sounds was set to two types: the conventional value of 75 dB used in the past, and an adjusted volume calculated by equation (2). Figure 7 is a table showing the explanatory variables and the adjusted volume calculated by equation (2).

[0062] Under the above conditions, the inventors obtained the average value of the functional evaluation shown in Figure 8 based on the subjective evaluations of 33 participants (ages 40-69).

[0063] As shown in Figure 8, when the alarm volume was the adjusted volume calculated by equation (2), more than 80% of participants rated it as functional. From the above, it can be seen that the volume determination method using equation (2) in this embodiment is highly regarded.

[0064] The volume determination unit 24 determines the volume of the alarm sound based on the multiple regression equation shown in equation (2), which is obtained by using the type of alarm sound, the volume of the running sound, whether the vehicle is a passenger vehicle or a freight vehicle, whether the running section is a tunnel section or an open section, whether the track condition is a slab track or a ballast track, whether or not the vehicle is running on a railway bridge, whether or not the windows are open, and the user's age as explanatory variables, and the volume of the alarm sound as the dependent variable.

[0065] [Other examples] As described above, in Figure 6, the P-values ​​of the partial regression coefficients in the multiple regression equations for the explanatory variables—type of alarm sound (x1, x2), volume of running sound (x3), whether the running section is a tunnel or an open section (x5), whether or not the train is running on a railway bridge (x7), and the user's age (x9)—were less than 0.05, indicating statistical significance.

[0066] Therefore, the volume determination unit 24 may determine the volume based on a multiple regression equation in which only the explanatory variables that showed significance are used as explanatory variables.

[0067] Specifically, the volume determination unit 24 determines the volume of the alarm sound based on a multiple regression equation obtained using the type of alarm sound (x1, x2), the volume of the running sound (x3), whether the running section is a tunnel section or an open section (x5), whether or not it is running on a railway bridge (x7), and the user's age (x9) as explanatory variables, and the volume of the alarm sound as the dependent variable.

[0068] In this case, the volume determination unit 24 does not need to acquire information such as whether the vehicle is a passenger vehicle or a freight vehicle (x4), whether the track condition is a slab track or a ballast track (x6), or whether the windows are open or not (x8). Therefore, it can determine the volume of the alarm sound more simply while maintaining significance.

[0069] [Alarm sound output processing] Referring to the flowchart in Figure 9, the alarm sound output process performed by the voice output control device 1 will be explained.

[0070] In step S11, the user state acquisition unit 13 starts acquiring the user state. When the user state acquisition unit 13 starts acquiring the user state, the user state determination unit 21 of the control unit 16 determines the user's state based on the user state information supplied from the user state acquisition unit 13 and supplies the determination result to the voice output execution determination unit 23.

[0071] In step S12, the external state acquisition unit 12 starts acquiring external states to determine whether or not there is a state requiring warnings or alerts necessary for railway operation. Once the external state acquisition unit 12 starts acquiring external states, the external state determination unit 22 determines, based on the external state information supplied from the external state acquisition unit 12, whether or not there is a state requiring the output of some kind of warning sound, and supplies the determination result to the voice output execution determination unit 23.

[0072] In step S13, the audio output execution determination unit 23 determines whether or not an alarm sound needs to be output based on the various setting information input by the operation input unit 11, the user status determination result by the user status determination unit 21, and the external status determination result determined by the external status determination unit 22.

[0073] If it is determined in step S13 that an alarm sound output is necessary, in step S14 the voice output execution determination unit 23 supplies the determination result to the volume determination unit 24. The volume determination unit 24 causes the driving information acquisition unit 14 to start acquiring driving information and acquires driving information from the driving information acquisition unit 14. Then, based on the acquired driving information and the type of alarm sound, the volume determination unit 24 uses a multiple regression equation to determine the volume of the alarm sound that satisfies predetermined perceptibility and predetermined functionality.

[0074] For example, the volume determination unit 24 determines the volume of the alarm sound based on the multiple regression equation shown in equation (2) above, which uses the type of alarm sound, the volume of the running sound, whether the vehicle is a passenger vehicle or a freight vehicle, whether the running section is a tunnel section or an open section, whether the track condition is a slab track or a ballast track, whether or not the vehicle is running on a railway bridge, whether or not the windows are open, and the user's age as explanatory variables, and the volume of the alarm sound as the dependent variable.

[0075] In step S15, the audio output control unit 25 outputs an alarm sound to the outside via the audio output unit 17 at the volume determined in step S16. After that, the process ends.

[0076] [Supplementary explanation of the embodiment] The embodiments described above are all preferred examples of the present invention. The numerical values, components, arrangement positions and connection configurations of the components, and processing order in the flowcharts shown in the embodiments are examples only and are not intended to limit the present invention. Furthermore, the figures are not necessarily strictly illustrative.

[0077] The series of processes described above can be executed by hardware or by software. When the series of processes are executed by software, the programs that make up the software are installed from a program storage medium onto a computer that is built into dedicated hardware, or onto an information processing device such as a general-purpose personal computer that can perform various functions by installing various programs.

[0078] The programs executed by the computer may be programs that are processed chronologically in the order described herein, or they may be programs that are processed in parallel or at necessary times, such as when a call is made.

[0079] Furthermore, the embodiments of the present invention are not limited to those described above, and various modifications are possible without departing from the spirit of the invention.

[0080] [Note] The contents described in some of the embodiments above can be understood, for example, as follows:

[0081] (1) The above-mentioned audio output control device 1 (Figure 1) In an audio output control device 1 that outputs a predetermined warning sound to alert a user who is in the vehicle, It has a volume determination unit 24 that determines the volume of the alarm sound that satisfies predetermined perceptuality and predetermined functionality, The volume determination unit 24 is, At a minimum, the volume of the alarm sound can be determined based on a multiple regression equation (equation (2)) obtained with the type of alarm sound (x1, x2), the volume of the running sound (x3), whether the running section is a tunnel section or an open section (x5), whether or not the vehicle is running on a railway bridge (x7), and the user's age (x9) as explanatory variables, and the volume of the alarm sound as the dependent variable.

[0082] With this configuration, the voice output control device 1 can determine a volume of an alarm sound that satisfies predetermined perceptibility and functionality based on easily obtainable information such as the type of alarm sound (x1, x2), the volume of the running sound (x3), whether the running section is a tunnel section or an open section (x5), whether or not it is running on a railway bridge (x7), and the user's age (x9). Since information such as the type of alarm sound is easily obtainable, the voice output control device 1 can easily determine a volume of an alarm sound that has perceptibility and functionality.

[0083] (2) Multiple regression equation The magnitude of the standardized partial regression coefficients in the aforementioned multiple regression equation for perceptibility is, in order of magnitude, the volume of the running sound (x3: 0.878), the type of the warning sound (x2: 0.331), whether the running section is a tunnel section or an open section (x5: ​​0.310), the age (x9: 0.116), and whether or not the vehicle is running on a railway bridge (x7: 0.079). The magnitude of the standardized partial regression coefficients in the multiple regression equation for the aforementioned functionality is largest in the following order: volume of the running sound (x3: 0.761), age (x9: 0.450), type of alarm sound (x2: 0.366), whether the running section is a tunnel section or an open section (x5: ​​0.213), and whether or not the train is running on a railway bridge (x7: 0.054) (Figure 6).

[0084] By using a multiple regression equation that satisfies the above-mentioned relationship between the magnitudes of the partial regression coefficients, the voice output control device 1 can control the output of alarm sounds that have sufficient perceptibility and functionality.

[0085] (3) Specific partial regression coefficients of the multiple regression equation Furthermore, the multiple regression equation for perceptuality (Equation (1)) is, y aud =55.214+0.874x1+1.160x2+0.204x3+0.028x4+1.022x5+0.129x6+0.299x7+0.227x8+0.382x9...(1) And, The multiple regression equation for the aforementioned functionality (Equation (2)) is: y aro =63.997+0.766x1+1.282x2+0.177x3-0.003x4+0.703x5+0.160x6+0.204x7+0.078x8+1.481x9...(2) And, In equations (1) and (2) x1 and x2 are the types of alarm sounds, x3 is the volume of the aforementioned running noise, x4 indicates whether the vehicle is a passenger vehicle or a freight vehicle. x5 determines whether the aforementioned section of travel is a tunnel section or an open-air section. x6 indicates whether the orbital state is a slab or ballast orbit. x7 is whether or not the vehicle is traveling across the aforementioned railway bridge. x8 is whether the window is open or not. x9 is age That is the case.

[0086] The inventor conducted a survey of 60 participants and performed multiple regression analysis based on the survey results to create the above-mentioned multiple regression equation. By using this multiple regression equation, the voice output control device 1 can control the output of alarm sounds that have sufficient perceptibility and functionality without performing multiple regression analysis. [Explanation of Symbols]

[0087] 1. Audio output control device 11. Operation Input Section 12 External status acquisition unit 13. User Status Acquisition Unit 14. Driving Information Acquisition Unit 15 Storage section 16 Control Unit 17 Audio output section 21 User State Determination Unit 22 External state determination unit 23. Audio output execution determination unit 24 Volume Determination Unit 25 Audio Output Control Unit

Claims

1. In an audio output control device that outputs a predetermined warning sound to alert a user who is in the vehicle, It has a volume determination unit that determines the volume of the alarm sound that satisfies predetermined perceptibility and predetermined functionality, The volume determination unit is, At a minimum, the volume of the alarm sound is determined based on a multiple regression equation obtained with the type of alarm sound, the volume of the running sound, whether the running section is a tunnel section or an open section, whether or not the train is running on a railway bridge, and the user's age as explanatory variables, and the volume of the alarm sound as the dependent variable. A voice output control device characterized by the following:

2. The audio output control device according to claim 1, The magnitude of the standardized partial regression coefficient in the multiple regression equation for perceptibility is greatest in the following order: volume of the running sound, type of the warning sound, whether the running section is a tunnel section or an open section, age, and whether or not the vehicle is running on a railway bridge. The magnitude of the standardized partial regression coefficients in the multiple regression equation for the aforementioned functionality is greatest in the following order: volume of the running sound, age, type of warning sound, whether the running section is a tunnel section or an open section, and whether or not the train is running on a railway bridge. A voice output control device characterized by the following:

3. The audio output control device according to claim 1, The aforementioned multiple regression equation for perceptuality (Equation (1)) is: y ａｕｄ =55.214+0.874x1+1.160 x2+0.204x3+0.028x4+1. 022x5+0.129x6+0.299x7+0.227x8+0.382x9・・・(1) And, The multiple regression equation for the aforementioned functionality (equation (2)) is: y ａｒｏ =63.997+0.766x1+1.282x2+0.177x3-0.003x4+0.703x5+0.160x6+0.204x7+0.078x8+1.481x9・・・(2) And, In equations (1) and (2) x1 and x2 are the types of the alarm sound, x3 is the volume of the aforementioned driving noise, x4 indicates whether the vehicle is a passenger car or a freight car. x5 is whether the aforementioned section of travel is a tunnel section or an open-air section. x6 indicates whether the orbital state is a slab or ballast orbit. x7 is whether or not the vehicle is traveling across the aforementioned railway bridge. x8 is whether the window is open or not. x9 is age That is A voice output control device characterized by the following:

4. In a voice output control method that outputs a predetermined warning sound to alert a user who is in the vehicle, The step includes determining the volume of the alarm sound that satisfies predetermined perceptibility and predetermined functionality, In the volume determination step described above, At a minimum, the volume of the alarm sound is determined based on a multiple regression equation obtained with the type of alarm sound, the volume of the running sound, whether the running section is a tunnel section or an open section, whether or not the train is running on a railway bridge, and the user's age as explanatory variables, and the volume of the alarm sound as the dependent variable. A method for controlling audio output, characterized by the following features.

5. In a program that can be executed by an input / output device and a computer capable of exchanging information, which outputs a predetermined alarm sound to alert a user in a vehicle, The step includes determining the volume of the alarm sound that satisfies predetermined perceptibility and predetermined functionality, In the volume determination step described above, At a minimum, the volume of the alarm sound is determined based on a multiple regression equation obtained with the type of alarm sound, the volume of the running sound, whether the running section is a tunnel section or an open section, whether or not the train is running on a railway bridge, and the user's age as explanatory variables, and the volume of the alarm sound as the dependent variable. A program that causes a computer to perform a process, characterized by the following features.

Images