JP2003202233A - Information regeneration device, information regeneration method, and storage medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To announce the contents of utterance within a time based on a situation of an own vehicle by selecting the contents of utterance in accordance with the situation of the own vehicle. <P>SOLUTION: Own vehicle speed and own vehicle position are obtained (step S301). The time T till the completion of announcement is inferred using these data (step S302). When T is inferred in this way, the contents of announcement indicating the contents to be newly announced and having the highest point among the contents of announcement utterable within the time T are selected (step S303). By the way, it is necessary to obtain the number of phonemes of the whole sentence and utterance time for each phoneme, and the number of mora is calculated in a car navigation device using a selected table for reading the contents of announcement when the tables for reading the contents of announcement are added to the contents of each announcement in advance in a pair and the contents of announcement are selected. Utterance time of each phoneme is fixed and is stored in an utterance content storage memory 201 in advance. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information reproducing apparatus and information reproducing method for reproducing traveling route guidance information according to a set course, and a storage medium.

[0002]

2. Description of the Related Art A conventional car navigation system displays the position of the vehicle on a map displayed on a display in the vehicle. Further, by setting a destination before or during traveling, it is possible to search for a route to the destination, and guide the driver to the route by displaying the route on the display or voice guidance.

The voice guidance of the car navigation system includes a method of reproducing what actually recorded the guidance voice of a human being,
Some use speech synthesis technology. In addition, as the vehicle approaches an intersection where it should turn, the timing of route guidance is changed in consideration of the speed of the vehicle and the traffic congestion on the road to improve the certainty of route guidance to the driver.

[0004]

[Problems to be Solved by the Invention] When a driver is instructed to turn around an intersection by using a distance from a corner as a key for starting route guidance, when the road is flowing smoothly and traffic jams occur. The time it takes to actually reach the intended intersection will change depending on whether you are there or not. As a result, the driver may forget to turn or be forced to change lanes just before the intersection.

In order to avoid this, it is possible to change the timing of route guidance in consideration of the speed of the own vehicle and the congestion situation of the road, but when it is necessary to continuously turn at an intersection, the route guidance Sometimes it is not possible to deal with it simply by changing the timing of vocalization.

The present invention has been made in view of the above-mentioned problems, and by selecting the utterance content according to the situation of the own vehicle, the utterance content is announced within the time based on the situation of the own vehicle. The purpose is to

[0007]

In order to achieve the object of the present invention, for example, an information reproducing apparatus of the present invention has the following configuration. That is, an information reproducing apparatus that is installed in a vehicle and performs voice synthesis based on the content of a text sentence, based on an acquisition unit that acquires state information of the vehicle and state information of the vehicle acquired by the acquisition unit. , Of the calculation means for calculating the time limit and the text sentence of the content to be uttered,
Selection means for selecting a text sentence that can be uttered within the time limit from a predetermined storage means that stores text sentences of a plurality of utterance contents, and generation for generating a speech synthesis parameter from the text sentence selected by the selection means. And means.

Further, for example, the information reproducing apparatus of the present invention has the following configuration. That is, it further has a conversion means for converting into a synthesized voice based on the voice synthesis parameter generated by the generation means.

[0009]

BEST MODE FOR CARRYING OUT THE INVENTION The present invention will be described in detail below with reference to the accompanying drawings with reference to the accompanying drawings.

[First Embodiment] FIG. 2 is a diagram showing a schematic configuration of an information reproducing apparatus as a car navigation apparatus in the present embodiment. Hereinafter, the schematic configuration of the car navigation device according to the present embodiment will be described with reference to FIG.

Reference numeral 201 denotes an utterance content storage memory in which a plurality of utterance content texts are stored. Speech content storage memory 2
The contents of 01 will be described later. When the car navigation device makes an announcement according to a certain utterance content, the utterance content selection unit 202 refers to the inside of the utterance content storage memory 201 and selects the text of the content to be uttered by a method described later. In some cases, the utterance content may be an e-mail to the driver downloaded from the information server wirelessly connected to the car navigation main body, news, or the like.

The announcement completion time estimation unit 205 is connected via a vehicle speed measurement unit 210, a vehicle position measurement unit 211, a congestion state acquisition unit 212 and a running state information acquisition unit 206 outside the voice synthesizer 208. From these measurement results, the time from the present time to reach the announcement completion point (announcement completion time) is estimated. This estimation result is
The text is sent to the utterance content selection unit 202, and the text at that time is selected by the method described below.

The utterance content text thus selected is
Prosody parameter generation unit 20 in the car navigation device
Sent to 3. The prosody parameter created by the prosody parameter generation unit 203 according to the sent utterance content text is sent to the phoneme unit connection unit 204, and the phoneme unit connection unit 20.
4 is a phoneme piece dictionary 207 according to the transmitted prosodic parameters.
By connecting the phoneme data stored in, the synthetic speech to be uttered is generated. The method of generating the prosody parameters according to the utterance content text data is not particularly limited in the description of the present embodiment, and thus the description thereof is omitted here.

When a synthesized voice is created by the voice synthesizer 208, the data is stored in the voice output device 20 such as a speaker.
It is sent to 9 and is output as voice.

FIG. 3 is a flow chart of processing in the voice synthesizer 208 of the car navigation system in this embodiment. Here, as an example, a process in which a route guidance for turning right or left at an intersection is guided by a synthetic voice is shown. or,
The program code according to the flowchart shown in FIG. 3 is stored in a memory such as a ROM or a RAM (not shown) in the car navigation device according to the present embodiment, and is read and executed by the CPU in the device. The car navigation device of this embodiment performs the processing described below.

When a request for route guidance is received from a predetermined instruction unit, first, the vehicle speed measuring unit 210 and the vehicle position measuring unit 21.
The own vehicle speed and the own vehicle position respectively measured by 1 are acquired via the traveling state information acquisition unit 206 (step S
301). Using these data, the announcement completion time estimation unit 205 estimates the time T to the announcement completion point (step S302). That is, the time limit for making an announcement is estimated. T can be estimated by the following equation.

T = distance to announcement completion point / own vehicle speed Further, not the current own vehicle speed, but the own vehicle speed for a few minutes until now is measured, and the average value of the measured data is used to obtain more reliability. It is a highly estimated value.

When T is estimated in this way, the utterance content selection unit 202 causes the utterance content storage memory 201 as shown in FIG.
Refers to the content to be announced, and
Among the announcement contents that can be uttered within the time T, the one with the highest point is selected (step S303).
In addition, the more carefully the announcement content is, the higher this point is. In the "Announcement Content" item in the table, () is a place where a specific name is entered. In order to determine whether or not utterance is possible within the time T, it is necessary to acquire the number of mora (number of phonemes) of the entire sentence and the utterance time of each phoneme.

The number of mora is attached in advance to each announcement content in pairs with their reading tables, and when selecting the announcement content, the reading table of the selected announcement content is used in the car navigation system. May be counted in advance, or may be counted in advance and stored in the utterance content storage memory 201 as a pair with the content of the announcement.

In the reading of the announcement content shown in FIG. 4, since the part other than () is a sentence which is not changed, the number of mora of this sentence should be predetermined. Therefore, if this mora number is stored in advance in the utterance content storage memory 201, the time required for the process of counting the mora number is shortened.

Further, the utterance time of each phoneme may be fixed and stored in advance in the utterance content storage memory 201.
The utterance time of each phoneme may be strictly measured beforehand, and the measured utterance time may be stored in the phoneme piece dictionary 207 in pairs with each phoneme.

As a result, it becomes possible to calculate the time required for uttering the contents to be uttered. FIG. 7 shows a method of calculating the time required for uttering the contents to be uttered.

Reference numeral 701 denotes a content to be uttered, and here, the word "akasaka" is used as an example. 701a-70
1d is each phoneme that constitutes the content 701 to be uttered.
The time required to utter each phoneme is t1, t2, t, respectively.
3, t4, and the respective times (t1, t2, t3, t4) may be exact values measured in advance as described above,
All may have the same average value. And as a result,
The time required to utter the content 701 to be uttered is (t
1 + t2 + t3 + t4).

When the text indicating the announcement content to be uttered is selected by the utterance content selection unit 202, a prosody parameter is generated from the text (step S30).
4), a phoneme piece is connected according to the prosody parameter to generate a synthetic waveform, which is output from the voice output device 209 such as a speaker (step S305).

With the above configuration, one announcement content that can be uttered within the time calculated according to the position and speed of the vehicle can be selected from a plurality of announcement contents corresponding to different utterance times. It was

Further, for example, as shown in FIG. 1, when the announcement completion point 102 is defined as a point at which an announcement to be made from now on must be completed, the time required for the vehicle 101 to reach there is the distance L and the vehicle speed. Estimated by V, the announcement text that can be uttered within that time is selected from the utterance content storage memory. As a result, it becomes possible to continue the route guidance even when the vehicle continuously turns at an intersection, for example.

[Second Embodiment] In the present embodiment, the first embodiment
In the car navigation device of the above embodiment, a process in the voice synthesizing device 208 that reads out news while route guidance is not performed will be described. It is assumed that the time until the next route guidance is known is the time required from the present time to the next corner such as an intersection.

FIG. 5 is a flow chart of the processing in the speech synthesizer 208 in this embodiment. This car navigation device is connected to a news server via a wireless network, and downloads news text from a news server into a predetermined memory buffer in the car navigation device in real time or at regular time intervals. The driver has registered the news genre of interest in advance, and the car navigation system
Speech synthesis is performed for news in the registered news genre. The program code according to the flowchart shown in FIG. 5 is stored and executed as described in the first embodiment, and as a result, the car navigation device in this embodiment performs the processing described below.

FIG. 6A is a diagram showing an example of a news database registered in the car navigation system. A driver who has registered this news database in a car navigation system is interested in temporary news (point 3) and sports-related (point 2) news, and must read aloud political and economic news (point 0). Considering the above, I registered the reading of each genre as described above. Each point attached to each genre will be described later, but in the present embodiment, the driver uses the point to mean the degree of interest in each news item.

In addition to the table representing this news database, the voicing content storage memory 201 also stores a table to which specific news contents and their mora (phoneme) numbers are attached (FIG. 6B). . The number of mora may be counted inside the car navigation device when the news is sent, or may be counted before being sent by the news server and the pair of news content and the number of mora may be sent. This mora number is used to estimate the approximate reading time when reading a news sentence. The unread flag is set to 0 when the car navigation device has read the news, and set to 1 when it is unread. 1 for this flag when new news is captured
Set.

When an instruction to read the news is input from a predetermined instruction section, the voice synthesizer 208 displays the vehicle speed and the vehicle position measured by the vehicle speed measuring section 210 and the vehicle position measuring section 211, respectively. , Running state information acquisition unit 20
6 through step 6 (step S501). Using these data, the announcement completion time estimation unit 205 estimates the time T to the next route guidance start point (step S5).
02). The next route guidance start point is the same as the point where the reading of the news must be finished.

Next, variables PB and IB used below are cleared to 0 (step S503). PB is a variable that holds the highest point of the news genre, and IB is a variable that holds the number of the news (not shown) that points to the highest point.

All the downloaded news sentences are searched, and one that is not read (step S505) and has a reading time shorter than T (step S507) is selected from the news genres with the highest points. (Step S508 to step S510). At this time, it is necessary to estimate the reading time of the news sentence, but it can be calculated by an equation such as the estimated reading time T ′ = the number of mora × α (α changes depending on the voice synthesis setting) (step S506).
Further, the estimated reading time T ′ may be calculated by the method shown in FIG. 7 as in the first embodiment.

If there is no appropriate one in all the news sentences (step S512), this process ends without combining anything. When an appropriate one is found, the news sentence is read aloud using composition (step S51).
3), 0 is set to the unread flag of the news sentence (step S514).

By the above processing, it is possible to select and read out a news sentence of a length that does not hinder the next route guidance from among the news sentences that the driver is interested in.

[Other Embodiments] Incidentally, even when the present invention is applied to a system composed of a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), a device consisting of one device ( For example, it may be applied to a copying machine, a facsimile machine, etc.).

Further, an object of the present invention is to supply a storage medium (or a recording medium) recording a program code of software for realizing the functions of the above-described embodiment to a system or apparatus, and to supply a computer of the system or apparatus ( Alternatively, by the CPU or MPU) reading and executing the program code stored in the storage medium,
It goes without saying that it will be achieved. In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the storage medium storing the program code constitutes the present invention.
Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also based on the instruction of the program code,
An operating system (OS) running on the computer does some or all of the actual processing,
It goes without saying that the processing includes the case where the functions of the above-described embodiments are realized.

Furthermore, after the program code read from the storage medium is written in the memory provided in the function expansion card inserted in the computer or the function expansion unit connected to the computer, based on the instruction of the program code. , The CPU provided in the function expansion card or the function expansion unit performs some or all of the actual processing,
It goes without saying that the processing includes the case where the functions of the above-described embodiments are realized.

When the present invention is applied to the above storage medium, the storage medium stores the program code corresponding to the above-described flowchart (shown in FIG. 2 or 5).

[0040]

By selecting the utterance content according to the situation of the vehicle, it is possible to announce the utterance content within the time based on the situation of the vehicle.

[Brief description of drawings]

FIG. 1 is a diagram showing the relationship between a vehicle 101 and an intersection.

FIG. 2 is a diagram showing a schematic configuration of an information reproducing device as a car navigation device according to the first embodiment of the present invention.

FIG. 3 is a flowchart of a process in a voice synthesis device 208 of the car navigation device according to the first embodiment of the present invention.

FIG. 4 is a diagram showing the contents of an utterance content storage memory 201.

FIG. 5 is a flowchart of a process in a voice synthesizer 208 of the car navigation system according to the second embodiment of the present invention.

FIG. 6A is a diagram showing an example of a news database registered in the car navigation device.

FIG. 6B is a diagram showing a table to which specific news content stored in the utterance content storage memory 201 and its mora number are attached.

FIG. 7 is a diagram showing a method of calculating a time required for uttering contents to be uttered.

   ─────────────────────────────────────────────────── ─── Continued front page    F term (reference) 2F029 AA02 AC02 AC06 AC18                 5D045 AA20                 5H180 AA01 BB15 DD04 FF04 FF12                       FF14 FF25 FF32

Claims (14)

[Claims] 1. An information reproducing apparatus which is mounted on a vehicle and performs voice synthesis based on the content of a text sentence, comprising: acquisition means for acquiring vehicle status information; and status information of the vehicle acquired by the acquisition means. Based on the above, the calculation means for calculating the time limit, and the text sentences that can be uttered within the time limit, out of the text sentences of the contents to be uttered, are stored in a predetermined storage means that stores the text sentences of a plurality of utterance contents. An information reproducing apparatus comprising: a selecting unit for selecting and a generating unit for generating a voice synthesis parameter from a text sentence selected by the selecting unit. 2. The information reproducing apparatus according to claim 1, wherein the status information of the vehicle includes a speed and a position of the vehicle, and a congestion status of a road on which the vehicle exists. 3. The selecting means further acquires the number of each phoneme when uttered based on each text sentence stored in the storage means and the time required for uttering each phoneme. The information reproducing device according to claim 1. 4. The selecting means further calculates a time required for uttering each of the text sentences by using the number of phonemes and a time required for uttering each of the phonemes, and the time and the limit. The information reproducing apparatus according to any one of claims 1 to 3, wherein a text sentence that can be spoken within the time limit is selected by comparing with time. 5. The selection means further selects, from among the text sentences that can be uttered within the time limit, a text sentence having a highest point attached in advance to each text sentence. 4. The information reproducing device according to any one of 4 above. 6. The information reproducing apparatus according to claim 5, wherein the point is set higher as the content of the text sentence is more careful. 7. The information reproducing apparatus according to claim 5, wherein the points are set to be high if the degree of interest of the user is high. 8. The information reproducing apparatus according to claim 7, wherein the points are rewritable by a user. 9. The information according to claim 1, wherein at least one of contents of a route instruction, contents of news, and contents of an electronic mail addressed to an individual is stored in the predetermined storage means. Playback device. 10. The predetermined storage means stores a flag indicating whether or not at least one of the content of the news or the content of the electronic mail addressed to the individual is unread. The information reproducing apparatus according to claim 9, 11. The information reproducing apparatus according to claim 1, further comprising conversion means for converting to a synthesized voice based on the voice synthesis parameter generated by the generation means. 12. The information reproducing apparatus according to claim 11, wherein the voice synthesis parameter is a prosody parameter. 13. An information reproducing method, which is installed in a vehicle and performs voice synthesis based on the content of a text sentence, comprising: an acquisition step of acquiring vehicle status information; and a status information of the vehicle acquired in the acquisition step. Based on the above, a calculation process for calculating the time limit, and among the text sentences of the contents to be uttered, the text sentences that can be uttered within the time limit are stored in a predetermined storage means that stores the text sentences of the plurality of utterance contents. An information reproducing method comprising: a selecting step of selecting and a generating step of generating a voice synthesis parameter from the text sentence selected in the selecting step. 14. A storage medium, which is installed in a vehicle and stores a program that functions as an information reproducing device that performs voice synthesis based on the content of a text sentence, comprising: a program of an acquisition step for acquiring state information of the vehicle; Based on the state information of the vehicle acquired in the acquisition process, a calculation process program for calculating the time limit, and a plurality of text sentences that can be uttered within the time limit out of the text sentences of the content to be uttered Storage comprising a program of a selection step for selecting from a predetermined storage means storing a text sentence of utterance content and a program of a generation step for generating a speech synthesis parameter from the text sentence selected in the selection step Medium.