JP3899883B2 - Text-to-speech synthesizer for vehicles - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an apparatus for synthesizing a voice corresponding to text data and providing it to a vehicle occupant.
[0002]
[Prior art]
E-mail has become widespread as a means of business and private communication, and it is desired that it can be used while driving a vehicle. Since e-mail is sent as text data, it must be displayed on a display and read. However, it is necessary to watch the front of the vehicle while driving the vehicle, and it is impossible to read the mail displayed on the display.
[0003]
Therefore, whether to display text data on the display or to synthesize and output it based on the riding state, running state, operation state of attached equipment, weather state, driving state, vehicle position, etc. was selected. A navigation device has been proposed (see, for example, JP-A-2001-141475). In this device, display on the display is prohibited during traveling.
[0004]
[Problems to be solved by the invention]
However, in the conventional text-to-speech synthesizer, text data is synthesized and read out according to the running state of the vehicle, so there is no need to look at the display while driving, but when you are busy paying attention to driving operations and outside the vehicle. Even if the voice to be read out is heard, the contents cannot be understood, and as a result, information may not be transmitted.
[0005]
An object of the present invention is to provide a text-to-speech synthesizer for a vehicle in which text reading is interrupted, repeat positions are set, and reading is restarted in accordance with changes in the driving load of a vehicle occupant.
[0006]
[Means for Solving the Problems]
(1) The first aspect of the present invention is a speech synthesis means for synthesizing and outputting speech corresponding to text data, and a first driving load state in which the driving load state of the driver is detected and the driving load is high. rerun and determining the load state determining means for determining a lower second operation load condition operating load, storage means for storing a text position in the speech synthesized by the prior SL voice synthesis section, the voice synthesis output of text data than An operation member to be controlled, and a control unit that controls voice synthesis by the voice synthesis unit in accordance with a determination result by the load state determination unit and an operation of the operation member . When it is determined that the driving load state is 1, the text position during speech synthesis is stored in the storage unit, the speech synthesis by the speech synthesis unit is temporarily stopped, and the load state determination unit When the second driving load state is determined by the stage, the text position during speech synthesis is stored in the storage unit, the speech synthesis by the speech synthesis unit is continued, and the operation member is operated The speech synthesis unit executes speech synthesis from the text position stored in the storage unit, thereby achieving the above object.
(2) In the vehicle text-to-speech synthesizer according to claim 2 , when the second driving load state continues for a predetermined time or more by the load state determination unit, it is determined as a third driving load state, and the control unit Thus, when the load state determination unit determines that the third driving load state is established, the speech synthesis by the speech synthesis unit is temporarily stopped .
(3) In the vehicle text-to-speech synthesizer according to claim 3, the load state determination means detects a driving operation of the vehicle driver and an in-vehicle device operation, and determines a driving load state based on the driving operation and the in-vehicle device operation. It is what you do.
(4) In the vehicle text-to-speech synthesizer according to claim 4, the driving operation includes a steering operation, an accelerator pedal and a brake pedal switching operation, and a turn signal switch operation, and the in-vehicle device operation includes an audio device, Operation of the air conditioner and navigation device is included .
(5) The text-to-speech synthesizer for a vehicle according to claim 5 detects the driver's line of sight by the load state determination means, and determines the driving load state based on the driver's line-of-sight direction. is there.
(6) A text-to-speech synthesizer for a vehicle according to claim 6 detects the vehicle speed by the load state determination means and determines the driving load state based on the vehicle speed .
[0007]
【The invention's effect】
(1) According to the first aspect of the invention, it is possible to interrupt text reading, set repeat locations, and resume reading in accordance with changes in the driving load of the vehicle driver .
(2) According to the invention of claim 2, the text-to-speech synthesis is continued unnecessarily in a situation where the content cannot be understood even if the voice is heard due to the continuation of the second driving load state. Can prevent the situation that is difficult to deal with.
(3) According to the inventions of claims 3 and 4, the operating load state can be accurately determined .
(4) According to the invention of claim 5 , it is possible to reliably determine a high driving load state in which the driver cannot watch the foreground of the own vehicle .
(5) According to the invention of claim 6 , it is possible to reliably determine a high driving load state when the vehicle starts .
[0008]
DETAILED DESCRIPTION OF THE INVENTION
<< First Embodiment of the Invention >>
FIG. 1 shows the configuration of the first embodiment. The driving operation detection device 1 detects a vehicle driving operation of the driver. The driving operation detection device 1 includes a steering angle sensor that detects the steering angle of the steering wheel, an accelerator sensor (throttle opening sensor) that detects the depression amount of the accelerator pedal, a brake sensor that detects the depression force of the brake pedal, and a turn signal. A switch is included. The driving operation detection device 1 may include a light switch, a wiper switch, and the like in addition to the above devices.
[0009]
The in-vehicle device operation detection device 2 detects a driver's operation of the in-vehicle device. The in-vehicle devices include an audio device, an air conditioner device (air conditioner), a navigation device, and an in-vehicle communication device (e-mail receiver), and the in-vehicle device operation detection device 2 detects operations of these in-vehicle devices. In-vehicle equipment may include an auto speed control device in addition to the above equipment. The repeat switch 3 is a switch that is operated when the driver wants to repeatedly hear a text that has already been read out.
[0010]
The text database (DB) 4 is a storage device for storing text data to be read out. The text data is read from a medium such as a CD or DVD in addition to the text data of the e-mail received by the in-vehicle communication device. Contents such as novels and driving guides are stored. The text-to-speech synthesizer 5 is a device that synthesizes speech corresponding to text data, and outputs the synthesized speech from the speaker 6.
[0011]
The controller 10 includes peripheral components such as a microcomputer 10a, a memory 10b, and a timer 10c. The controller 10 executes a control program to be described later and drives the driver based on the detection results of the driving operation detection device 1 and the in-vehicle device operation detection device 2. The load is determined, and the text reading is interrupted, the repeat location is set, and the reading is restarted according to the driving load. The memory 10b stores a reading position on the text when it is determined that a high driving load state has occurred. More specifically, the title of the text being read out, the number of the paragraph that was read out, and the sentence number in the paragraph (the order of the sentences divided for each phrase) are stored. The timer 10c measures the duration of the state where the driving load is high.
[0012]
The correspondence between the constituent elements of the claims and the constituent elements of the first embodiment is as follows. That is, the text-to-speech synthesizer 5 and the speaker 6 constitute speech synthesis means, the controller 10 constitutes load state determination means and control means, the memory 10b constitutes storage means, and the repeat switch 3 constitutes an operation member.
[0013]
FIG. 2 is a flowchart showing a text-to-speech synthesis control program. The operation of the first embodiment will be described with reference to this flowchart. When the main switch (not shown) of the vehicle text-to-speech synthesizer is turned on, the controller 10 starts executing this control program.
[0014]
In step 1, it is confirmed whether or not text-to-speech processing (TTS; Text to Speech) is currently being performed. The process waits until the text-to-speech process is started. When the text-to-speech process is started, the process proceeds to step 2. In step 2, the driving operation detection device 1 detects the driver's driving operation, the in-vehicle device operation detection device 2 detects the driver's in-vehicle device operation, and reads the detection result. In step 3, the driving load of the driver is determined based on the detection results of the driving operation and the in-vehicle device operation, and “whether the high load state has occurred”, “the high load state has continued for a predetermined time or more”, or “high It is determined whether the load state is resolved.
[0015]
Here, a method for determining the operating load will be described. (1) When a sudden driving operation such as a sudden braking operation with a deceleration of 0.3 [G] or more, or a sudden steering operation with a steering angular velocity of π / 2 [rad / sec] or more is detected, the driving load is highest. Is immediately determined to be “high load state continues for a predetermined time or more”.
[0016]
(2) Normal operation, such as when the steering operation continues at a steering angular velocity of π / 4 [rad / sec] or higher, when frequent accelerator pedal and brake pedal switching operations continue for 5 [times / 10 sec] or higher. If the state continues within the range of operation, it is determined that “a high load state has occurred”. In addition, when a steering operation with a steering angular velocity of π / 4 [rad / sec] or more continues for 10 [sec] or more, frequent accelerator pedal and brake pedal switching operations of 5 [times / 10 seconds] or more are performed with 30 [sec]. When it is in the range of normal driving operation, such as when it continues for a long time, but the state continues for a predetermined time or more, it is determined that the high load state is continuing for a predetermined time or more.
[0017]
(3) When any operation of the in-vehicle device (audio device, air conditioner device, navigation device) is detected, “high load state occurs”. Further, when the operation of these in-vehicle devices continues for 5 [sec] or more, it is determined that “the high load state continues for a predetermined time or more”.
[0018]
(4) When the turn signal switch is operated and the turn signal lamp starts blinking, when the vehicle's behavior changes, it is necessary to pay more attention to the situation around the vehicle. Occurrence ". Further, when the state as described above continues for a predetermined time or longer, such as when the turn signal lamp continues to blink for 1 minute or longer, it is determined that the high load state is continuing for a predetermined time or longer.
[0019]
If it is determined in step 3 of FIG. 2 that “the occurrence of a high load state”, the process proceeds to step 4 where the text position currently being read out is stored in the memory 10b. At this time, the text reading continues. Then, it returns to step 1 and repeats the process mentioned above.
[0020]
If it is determined in step 3 that “the high load state is continuing for a predetermined time or longer”, the process proceeds to step 5 to temporarily stop the text reading process. Normally, before it is determined that “the high load state has continued for a predetermined time or longer”, it is once determined that “high load state has occurred”, and the process of storing the text position being read out in step 4 described above is performed. Is called. Therefore, when a repeat operation is performed after the reading process is paused, the text position stored in the memory 10b at the time of “high load state occurrence” is returned to, and the text reading can be resumed from that position.
[0021]
However, of the above-described driving load determination methods, (1) when a sudden driving operation is detected, the determination is made that “the high load state continues for a predetermined time or more without immediately determining“ the occurrence of a high load state ”. Therefore, only when a sudden driving operation is performed, the reading is paused and the reading position of the text at that time is stored in the memory 10b.
[0022]
After it is determined that the “high load state is continuing for a predetermined time or longer” and the text reading is paused, the process proceeds to step 7. Step 7 is a step of confirming whether or not a repeat operation has been performed by the repeat switch 3, and this repeat operation selects a high load state experienced by itself. If no repeat operation is performed, the process returns to step 1 with the text reading paused, and the above-described processing is repeated.
[0023]
After the text reading is paused, if the driver selects a high load state experienced by himself such as a sudden handle or a sudden brake and repeats the operation, the corresponding high load state stored in the memory 10b in step 8 occurs. The corresponding text position at the time or when an abrupt driving operation is performed is retrieved, and in step 9 the text reading is resumed from that position. Then, it returns to step 1 and repeats the process mentioned above.
[0024]
When all of the above-described high load states are resolved in step 3 and it is determined that the “high load state is resolved”, the process proceeds to step 6 and the high load state is determined before it is determined that “the high load state continues for a predetermined time or longer”. Check if the problem has been resolved. When the high load state is resolved before it is determined that the high load state continues for a predetermined time or longer, text reading is continued. Therefore, in order to confirm whether or not the driver wants to hear the text again from the time of occurrence of the high load state, it is confirmed in step 7 whether or not the repeat operation has been performed by the repeat switch 3. If no repeat operation has been performed, it is determined that the driver understands the text read out from the time of occurrence of the high load state to the time of cancellation, and does not want to listen again, and returns to step 1 to perform the above-described processing. repeat.
[0025]
On the other hand, when the high load state experienced by himself / herself is selected and the repeat operation is performed, it is determined that the driver desires to re-read the text from the time when the high load state occurs, and is stored in the memory 10b in step 8. The corresponding text position at the time of occurrence of the high load condition is searched, and in step 9 the text reading is resumed from that position. Then, it returns to step 1 and repeats the process mentioned above.
[0026]
When it is determined that “the high load state is continuing for a predetermined time or longer” and the high load state is resolved, the text reading is already suspended (step 5). In this case, since the high load state of driving operation or in-vehicle device operation has continued for a long time, the driver fully understands the content of the text read out from the point of occurrence of the high load state until the reading is stopped. It is not considered. Therefore, the process proceeds to step 8 without confirming the repeat operation of the driver in step 7, and the text position at the time of occurrence of the high load state stored in the memory 10b is read, and in step 9 the text is read out from that position. Resume. Then, it returns to step 1 and repeats the process mentioned above.
[0027]
As described above, according to the first embodiment, the driver's driving operation and the in-vehicle device operation are detected to determine the driving load state, and the text being read out (speech synthesis) when a high driving load state occurs. When the repeat switch 3 for storing the position and re-reading the text is operated, the read-out is executed from the stored text position. The position of the text being read out is memorized when the driving load becomes high and it becomes difficult to pay sufficient attention to text reading, and even if text reading continues as it is, the high driving load state is resolved When it becomes possible to re-listen, the text-to-speech can be re-executed from the position where you want to re-listen. Ri out operation is unnecessary, wasteful re-run from does not need to text first re-hear is avoided.
[0028]
According to the first embodiment, when it is determined that the high driving load state continues for a predetermined time or longer, the text reading (speech synthesis) is temporarily stopped. Even in the situation where the user cannot understand the content even if he / she can hear the voice due to the continuation, it is possible to prevent the driver from struggling to deal with the situation because the text reading is continued unnecessarily.
[0029]
Further, in the first embodiment, when the repeat switch 3 is operated when the text data reading (speech synthesis) is paused, the text reading is executed from the stored text position. Even if a high driving load condition continues for a predetermined time or longer and text reading is paused, the text position where a high driving load condition has occurred and the contents cannot be fully understood will always be at the convenience of the driver Text reading can be resumed.
[0030]
Furthermore, according to the first embodiment, text reading is resumed from the stored text position when the high driving load state is resolved after the text data reading (speech synthesis) is temporarily stopped. The text reading is automatically restarted from the text position where the content is not fully understood due to the occurrence of a high driving load state, and the operability and the convenience can be improved.
[0031]
According to the first embodiment, the repeat operation is input together with the selection of the high load state. However, the present invention is not limited to this, and the repeat operation is requested because it is uniquely high load. Of course, the system can be simplified.
[0032]
<< Second Embodiment of the Invention >>
In the first embodiment described above, an example is shown in which the driving operation and the in-vehicle device operation of the driver are detected to determine the driving load. However, the driver's line-of-sight direction is detected, and the detection result of the line-of-sight direction is detected. A second embodiment for determining the operating load will be described.
[0033]
FIG. 3 shows the configuration of the second embodiment. In addition, the same code | symbol is attached | subjected with respect to the apparatus similar to the apparatus shown in FIG. 1, and it demonstrates centering around difference. The line-of-sight detection device 7 detects the direction of the driver's line of sight. As a technique for detecting the driver's line of sight, for example, a technique disclosed in Japanese Patent Laid-Open No. 10-244892 is used.
[0034]
The operation of the second embodiment is different from the operation of the first embodiment shown in FIG. 2 only in the operation load determination method in Step 3, and only the difference will be described. In the second embodiment, when the driver's line of sight is stopped in a direction other than the own vehicle foreground, such as when the driver's line of sight has stopped for 3 [sec] or more in a specific direction other than the own vehicle foreground. And “occurrence of high load state”. Further, when the driver's line of sight has stopped in a specific direction other than the foreground of the vehicle for a predetermined time, for example, 10 [sec] or more, it is determined that “the high load state continues for a predetermined time or more”.
[0035]
Thus, according to the second embodiment, the vehicle driver's line of sight is detected, and the driving load state is determined based on the driver's line of sight direction. In addition to the effect, it is possible to reliably determine a high driving load state in which the driver cannot watch the foreground of the host vehicle.
[0036]
<< Third Embodiment of the Invention >>
A third embodiment for determining the driving load based on the vehicle speed will be described. FIG. 4 shows the configuration of the third embodiment. In addition, the same code | symbol is attached | subjected with respect to the apparatus similar to the apparatus shown in FIG. 1, and it demonstrates centering around difference. The vehicle speed sensor 8 detects the vehicle speed of the vehicle.
[0037]
The operation of the third embodiment is different from the operation of the first embodiment shown in FIG. 2 only in the operation load determination method in step 3, and only the difference will be described. In general, when the vehicle starts, attention to the outside of the vehicle must be taken more carefully. Therefore, in the third embodiment, it is determined that “the high load state continues for a predetermined time or more” until the vehicle starts and reaches a predetermined vehicle speed, for example, 30 [km / h], from the vehicle speed 0. However, if a vehicle start is detected, it is immediately determined that the high load state has continued for a predetermined period of time without going through the determination of the occurrence of a high load state. Then, the reading position of the text at that time is stored in the memory 10b.
[0038]
Thus, according to the third embodiment, since the vehicle speed is detected and the driving load state is determined based on the vehicle speed, in addition to the above-described effects of the first embodiment, A high operating load state can be reliably determined.
[0039]
Note that the determination method of the driving load of the driver is not limited to the determination methods of the first to third embodiments described above.
[Brief description of the drawings]
FIG. 1 is a diagram showing a configuration of a first exemplary embodiment.
FIG. 2 is a flowchart showing a text-to-speech synthesis control program according to the first embodiment.
FIG. 3 is a diagram showing a configuration of a second exemplary embodiment.
FIG. 4 is a diagram showing a configuration of a third exemplary embodiment.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 Driving | operation operation detection apparatus 2 Car equipment operation detection apparatus 3 Repeat switch 4 Text database 5 Text speech synthesizer 6 Speaker 7 Eye-gaze detection apparatus 8 Vehicle speed sensor 10 Controller 10a Microcomputer 10b Memory 10c Timer

Claims (6)

Speech synthesis means for synthesizing and outputting speech corresponding to text data;
Load state determination means for detecting a driver's driving load state and determining whether the driving load is a first driving load state having a high driving load or a second driving load state having a lower driving load ;
Storage means for storing the text position in the speech synthesized by the prior Symbol speech synthesis means,
An operation member that re-executes speech synthesis output of text data;
Control means for controlling speech synthesis by the speech synthesizer in accordance with a determination result by the load state determination unit and an operation of the operation member ;
The control means stores the text position during speech synthesis in the storage means and suspends speech synthesis by the voice synthesis means when the load status judgment means judges the first driving load state. When the load state determination means determines that the second driving load state is established, the storage unit stores the text position during speech synthesis, continues speech synthesis by the speech synthesis means, and the operation member when operated, the vehicle text speech synthesizing apparatus according to claim Rukoto to execute the speech synthesis by the speech synthesizing means from the text position stored in the storage means. The vehicle text-to-speech synthesizer according to claim 1,
The load state determination means determines the third operation load state when the second operation load state continues for a predetermined time or more,
The vehicle text-to-speech synthesizer characterized in that the control means pauses the speech synthesis by the speech synthesizer when the load condition determination means determines the third driving load condition . The vehicle text-to-speech synthesizer according to claim 1 or 2,
The vehicle text-to-speech synthesizer characterized in that the load state determination means detects a driving operation and an in-vehicle device operation of a vehicle driver and determines a driving load state based on the driving operation and the in-vehicle device operation . The vehicle text-to-speech synthesizer according to claim 3 ,
The driving operation includes a steering operation, an accelerator pedal / brake pedal switching operation and a turn signal switch operation, and the in-vehicle device operation includes an audio device, an air conditioner and a navigation device. Text-to-speech synthesizer for vehicles. The vehicle text-to-speech synthesizer according to claim 1 or 2 ,
The vehicle text-to-speech synthesizer characterized in that the load state determination means detects the driver's line of sight and determines the driving load state based on the driver's line of sight . The vehicle text-to-speech synthesizer according to claim 1 or 2 ,
The vehicle text-to-speech synthesizer characterized in that the load state determination means detects a vehicle speed and determines a driving load state based on the vehicle speed .

Images