JP2004133119A - Portable terminal device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a portable terminal device with a storage device which can prevent unnecessary information from being read aloud and also prevent a synthesized speech from illegally being used. <P>SOLUTION: The portable terminal device with the storage device is equipped with a portable terminal device 1 and the storage device 2 which is attachable to and detachable from the portable terminal device. Namely, the storage device has a phoneme database storage part 121, a synthesis purpose data storage part 122, and a terminal device interface part 120 and the portable terminal device has a storage device interface part 103, a system control part 101 which controls the whole, a reading-aloud selection processing part 110 which selects a range of synthesis purpose data, a speech synthesis processing part 102 which generates synthesized speech data from a phoneme database read out through the interface part and the synthesis purpose data read out according to the selected range, and a speech output processing part 104 which inputs the generated synthesized speech data and outputs it as a synthesized speech signal. <P>COPYRIGHT: (C)2004,JPO

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a portable terminal device that stores synthesis target data to be read in a storage device and converts the synthesis target data read from the storage device into voice.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, an apparatus for reading out e-mails and texts of a word processor has been realized by a personal computer because of its abundant storage capacity, high processing capability, and ample network functions. In addition, although the voice color of the output synthesized voice is a general voice such as a man or a woman, a voice synthesis method capable of generating a synthesized voice similar to human utterance has also been disclosed. That is, information on the reading kana, accent type, etc. is prepared in the dictionary, and an accent command value and / or phoneme duration time information are prepared in advance, and the parameter sequence of the phoneme segment data is determined using the phoneme duration time. By generating and synthesizing a speech waveform based on the generated speech, a synthesized speech similar to a human utterance is output (for example, see Patent Document 1).
[0003]
However, using a personal computer while walking is very inconvenient due to size and weight problems, and its operation is not easy. In addition, if the function only converts the speech data of the synthesis target data to be read, there is a problem that the cost performance is lacking. Also, the output voice is a general voice such as a male or female voice, and is not necessarily a voice output in a voice tone desired by the user.
[0004]
Therefore, as an apparatus for correcting these inconveniences, an input unit for inputting synthesis target data (an input unit for inputting from a storage device such as a memory card or an optical disk or a magnetic disk, an input unit for inputting from a network, and an input unit for inputting from a keyboard). A mobile terminal device that includes an input unit and the like, an output unit (speaker and headphones) that outputs a synthesized voice, and a voice synthesis processing unit that generates synthesized voice data from synthesis target data. The voice synthesis processing unit in the portable terminal device samples a real voice of an actual person and uses a phoneme database in which the sampled data is converted into a database. In addition, it is easy to attach to and detach from an information processing device, can be built into a small information processing device (small personal computer, etc.), and is a small, lightweight and portable IC card type text-to-speech system with a text-to-speech function. Is known. (For example, see Patent Document 2)
[0005]
[Patent Document 1]
JP-A-7-140999
[Patent Document 2]
JP-A-6-337774
[0006]
[Problems to be solved by the invention]
However, in the above-mentioned portable terminal device, supplementary information such as the creation date of the synthesis purpose data and the writer's career may be included, and these are also read aloud, but for the user, the reading of the information is not necessarily required. There was a problem that it was not necessary. Also, since the synthesized speech output from the mobile terminal device is close to the real voice of the actual person who is the provider of the phoneme database, there is a risk that the user of this device will impersonate the phoneme provider and perform unauthorized use in voice authentication and the like. there were.
[0007]
In the portable terminal device with a storage device, it is required to prevent reading of unnecessary information and prevent unauthorized use of synthesized speech.
[0008]
An object of the present invention is to provide a portable terminal device with a storage device capable of preventing unnecessary reading of information and preventing unauthorized use of synthesized speech in order to satisfy this demand. .
[0009]
[Means for Solving the Problems]
In order to solve the above problem, a portable terminal device with a storage device according to the present invention is a portable terminal device with a storage device, comprising a portable terminal device and a storage device that is detachable from the portable terminal device. A phoneme database storage unit that stores a phoneme database that is a database of phoneme data, a synthesis target data storage unit that stores synthesis target data to be read, and a terminal device interface unit that exchanges data with the portable terminal device. A portable terminal device, a storage device interface unit that exchanges data with the storage device, a system control unit that controls the whole, a reading selection processing unit that selects a range of synthesis target data, and a storage device interface unit And the phoneme database read from the phoneme database storage unit via the terminal device interface unit and the selected range And a speech output processing unit that inputs the generated synthesized speech data and outputs the synthesized speech data as a synthesized speech signal. ing.
[0010]
As a result, a portable terminal device with a storage device that can prevent unnecessary reading of information can be obtained.
[0011]
BEST MODE FOR CARRYING OUT THE INVENTION
A portable terminal device with a storage device according to claim 1 of the present invention is a portable terminal device with a storage device comprising a portable terminal device and a storage device detachable from the portable terminal device. A phoneme database storage unit that stores a phoneme database that is a database of phoneme data, a synthesis target data storage unit that stores synthesis target data to be read, and a terminal device interface unit that exchanges data with the portable terminal device. A portable terminal device, a storage device interface unit that exchanges data with the storage device, a system control unit that controls the whole, a reading selection processing unit that selects a range of synthesis target data, and a storage device interface unit. Compositing based on phoneme database and selected range read from phoneme database storage via terminal device interface And a voice output processing unit that receives the generated synthesized voice data and outputs the synthesized voice data as a synthesized voice signal. is there.
[0012]
With this configuration, the user can select the range of the synthesis target data as the reading target information and omit the reading of the unnecessary part, thereby efficiently reading the novel or the like desired without wasting time. It has the effect of being able to listen.
[0013]
The portable terminal device with a storage device according to claim 2 is the portable terminal device with a storage device according to claim 1, further including an identification sound synthesis processing unit instead of the reading selection processing unit, and the identification sound synthesis processing unit includes: An identification sound signal outside the audible range indicating that the signal is a synthesized sound signal is included in the synthesized sound signal.
[0014]
With this configuration, a synthesized speech including an identification sound outside the audible range indicating that the speech is an output speech of the speech synthesis is output from the portable terminal device. By providing the authentication device with a voice frequency analysis function, it is possible to detect that a frequency component of an identification sound that is not included in the actual voice of a real person is included, thereby preventing unauthorized use of synthesized voice. It has the effect of being able to.
[0015]
According to a third aspect of the present invention, a portable terminal device with a storage device includes an identification sound synthesis processing unit in place of the reading / selection processing unit of the portable terminal device with a storage device according to the first aspect, and the identification sound synthesis processing unit includes a synthetic voice. Instead of outputting an identification sound signal outside the audible range, which indicates that the signal is a signal, over all of the synthesized speech signals, an identification code in the synthesis target data is included as a trigger in the synthesized speech signal.
[0016]
With this configuration, even if the output voice of the portable terminal device is used for an unauthorized purpose, the voice authentication device is provided with a voice frequency analysis function, so that only the frequency analysis of the synthesized voice signal having the identification code is performed. Since it is possible to detect that the frequency component of the discriminating sound that is not included in the actual human voice is included, it is possible to prevent the illegal use of the synthesized voice by analyzing the frequency of a smaller number of signals. Having.
[0017]
Hereinafter, embodiments of the present invention will be described with reference to FIGS. 1 to 6.
[0018]
(Embodiment 1)
FIG. 1 is a configuration diagram illustrating a communication system including a mobile terminal device, a server device, a personal computer, and the like.
[0019]
In FIG. 1, reference numeral 1 denotes a portable terminal device having a display unit, an operation unit, and an audio output unit such as a headphone / speaker, and 2 denotes a storage device such as a memory card for storing synthesis target data and a phoneme database. The storage device 2 is detachable from the mobile terminal device 1. The storage device 2 includes a synthesis target data storage unit (described later) that stores synthesis target data such as a novel, and a phoneme database storage unit that stores a phoneme database including phoneme data. The phoneme database, which has already been described above, is a sample of the actual voice of a real person, and information on sounds such as sound duration, fundamental frequency, and power for each phoneme, and the data file name and name of the phoneme to which the phoneme belongs. Information such as the start position and end position of the phoneme in the file is labeled, and is stored in a database according to an arbitrary format. This phoneme database is an important element for determining the timbre and intonation of the synthesized speech output from the mobile terminal device 1. Reference numeral 3 denotes a server device on the Internet 5 for providing the synthesis target data a and the phoneme database b. Although only one server device is described here, a plurality of server devices may separately provide the synthesis target data and the phoneme database. Reference numeral 4 denotes a personal computer for downloading the synthesis target data a and the phoneme database b from a server device on the Internet 5 via the public line 6 and storing the data in the storage device 2.
[0020]
In FIG. 1, a user first downloads a synthesis target data such as a novel or a phoneme database of voice characters from a server device 3 on the Internet 5 through a personal computer 4 and stores the data through a personal computer 4 in a memory card or the like. Record on device 2. Next, the user inserts the storage device 2 into the portable terminal device 1, selects a synthesis target portion to be read on the portable terminal device 1, and performs a reproduction operation. A synthesized voice of the data in the synthesis target range selected by voice is output.
[0021]
FIG. 2 is a block diagram showing a portable terminal device with a storage device according to the first embodiment of the present invention, and shows the portable terminal device 1 and the storage device 2 of FIG. 1 in detail.
[0022]
2, 1 is a portable terminal device similar to that of FIG. 1, 2 is a storage device similar to that of FIG. 1, 101 is a system that exchanges data with each processing unit in the portable terminal device 1 and controls the entire device. It is a control unit. Reference numeral 102 denotes a voice for analyzing the synthesis target data, extracting and concatenating phoneme data optimal for each character data to generate synthesized voice data, and converting the data so that the data can be passed to a voice output processing unit 103 described later. A synthesis processing unit 103 is a storage device interface unit (storage device I / F unit) that receives an instruction from the system control unit 101 and reads and writes data in the storage device 2. An audio output processing unit 104 receives data from the audio synthesis processing unit 102, converts the format of the data, and outputs the data to a speaker 108 or headphones (not shown). Reference numeral 105 denotes a storage unit used as a storage area of a program for controlling the mobile terminal device 1 or a work area for data processing; 106, an operation unit by which a user gives his / her own instructions to the mobile terminal device 1; A display unit for displaying the operating state of the portable terminal device 1 to the user; 109, a power supply unit for supplying power to the mobile terminal device 1; 110, a synthesizing target based on the synthesis target data range selection information selected by the user from the operation unit 106; A recitation / selection processing unit that performs data configuration analysis and extracts synthesis target data of a selection range. A storage device interface unit 103 and a terminal device interface unit (terminal device I / F) that exchanges data with the portable terminal device 1. Unit), 121 is a phoneme database storage unit for storing a phoneme database, and 122 is a synthesis target data storage for storing synthesis target data. It is a part.
[0023]
The operation of the portable terminal device with a storage device configured as described above is performed using FIG. FIG. 3 is a flowchart showing the operation of the portable terminal device with a storage device of FIG. 2 (the operation of the system control unit 101).
[0024]
When the user turns on the power of the device 1 using the operation unit 106, the system control unit 101 issues a command to the storage device interface unit 103 to check whether or not the storage device 2 is connected to the portable terminal device 1 ( S1). If it is determined that the connection is not established, the font data is extracted from the storage unit 105, a message such as "Please insert a memory card." Is displayed on the display unit 107 (S2), and the portable terminal is displayed to the user. It prompts the device 1 to connect the storage device 2. If it is determined that the connection is established, the system control unit 101 waits for a reproduction operation from the operation unit 106 (S3). When the playback operation is performed, a message such as “Please select the data to be read aloud. 1. Full text (with accompanying information) 2. Only text (excluding accompanying information)” is displayed on the display unit ( S4) The user is caused to select a reading target portion of the synthesis purpose data (S5). After the selection, the range selection information of the synthesis target data is stored in the storage unit 105. Next, the system control unit 101 instructs the storage device interface unit 103 to read out the synthesis target data in the storage device 2. The storage device interface unit 103 reads out the synthesis target data while exchanging with the terminal device interface unit 120 in the storage device 2 and records it in the storage unit 105 in the portable terminal device 1 (S6).
[0025]
Next, the system control unit 101 causes the reading selection processing unit 110 to start processing. The read-aloud selection processing unit 110 reads out the synthesis target data from the storage unit 105, analyzes the configuration of the data, optimizes the data only for the part selected by the user, and records the data in the storage unit 105 (S7). For example, if the selection information from the user is only the text, the additional information such as the creator and the date of creation of the synthesis target data is omitted, and the processed synthesis target data is stored in the storage unit 105 again. . Next, the system control unit 101 issues a command to the speech synthesis processing unit 102 to start the processing. The voice synthesis processing unit 102 performs analysis while sequentially reading out the synthesis target data processed by the reading selection processing unit 110 from the storage unit 105, and reads out the phoneme data most suitable for each character data from the storage unit 105 or the storage device 2, The combined data is converted into data that can be processed by the voice output processing unit 104 to create synthesized voice data (S8). The voice output processing unit 104 receives the synthesized voice data from the voice synthesis processing unit 102, converts the format of the data, and outputs the data to the speaker 108 or headphones (S9).
[0026]
In this way, the user can listen to the reading of the synthesis target data in the selected range with the desired character voice.
[0027]
As described above, according to the present embodiment, the storage device 2 includes a phoneme database storage unit 121 that stores a phoneme database in which phoneme data is made into a database, and a synthesis target data storage unit that stores synthesis target data to be read. 122, and a terminal device interface unit 120 for exchanging data with the portable terminal device 1. The portable terminal device 1 includes a storage device interface unit 103 for exchanging data with the storage device 2, and a system for controlling the whole. The control unit 101, a reading selection processing unit 110 for selecting a range of synthesis target data, a phoneme database read from the phoneme database storage unit 121 via the storage device interface unit 103 and the terminal device interface unit 120, and the selected range. From the synthesis target data read from the synthesis target data storage unit 122 By having the voice synthesis processing unit 102 that generates synthesized voice data and the voice output processing unit 104 that inputs the generated synthesized voice data and outputs the synthesized voice data as a synthesized voice signal, the user can obtain the synthesis target data as the reading target information. Since it is possible to select a range and omit reading of unnecessary portions, the user can efficiently listen to reading of a novel or the like desired without wasting time.
[0028]
(Embodiment 2)
The configuration of the communication system having the portable terminal device with a storage device according to the second embodiment of the present invention is the configuration of FIG. 1 as in the first embodiment.
[0029]
FIG. 4 is a block diagram showing a portable terminal device with a storage device according to the second embodiment of the present invention, and shows the portable terminal device 1 and the storage device 2 of FIG. 1 in detail.
[0030]
4, a system control unit 101, a speech synthesis processing unit 102, a storage device interface unit 103, a speech output processing unit 104, a storage unit 105, an operation unit 106, a display unit 107, a speaker 108, a power supply unit 109, and a terminal device interface unit The reference numeral 120, the phoneme database storage unit 121, and the synthesis target data storage unit 122 are the same as those in FIG. Reference numeral 111 denotes an identification sound synthesis processing unit that synthesizes the identification sound signal with the synthesized audio signal output from the audio output processing unit 104.
[0031]
The operation of the portable terminal device with a storage device thus configured will be described with reference to FIG. FIG. 5 is a flowchart illustrating the operation of the portable terminal device with a storage device in FIG. 4 (the operation of the system control unit 101).
[0032]
When the user turns on the power of the device 1 using the operation unit 106, the system control unit 101 issues a command to the storage device interface unit 103 and checks whether the storage device 2 is connected to the portable terminal device 1 (S11). ). If it is determined that the connection is not established, the font data is extracted from the storage unit 105, a message such as "Please insert a memory card." Is displayed on the display unit 107 (S12), and the portable terminal is displayed to the user. It prompts the device 1 to connect the storage device 2. If it is determined that the connection is established, the system control unit 101 waits for a reproduction operation from the operation unit 106 (S13). When a reproduction operation is performed, the system control unit 101 issues a command to the storage device interface unit 103 to read out the synthesis target data in the storage device 2. The storage device interface unit 103 reads out the synthesis target data while exchanging with the terminal device interface unit 120 in the storage device 2 and records it in the storage unit 105 in the portable terminal device 1 (S14).
[0033]
Next, the system control unit 101 issues a command to the speech synthesis processing unit 102 to start the processing. The speech synthesis processing unit 102 performs analysis while sequentially reading out the synthesis target data from the storage unit 105, reads out the phoneme data most suitable for each character data from the storage unit 105 or the storage device 2, connects them, and connects them. Is converted into data that can be processed, and the data is stored in the storage unit 105 (S15). Subsequently, the system control unit 101 reads the data processed in step S15 from the storage unit 105, and passes the data to the audio output processing unit 104. Then, a command is issued to the identification sound synthesis processing unit 111 to start the processing. The identification sound synthesis processing unit 111 synthesizes an identification sound signal outside the audible range with the signal (synthesized audio signal) output from the audio output processing unit 104 (S16), and outputs the synthesized signal to the speaker 108 or headphones (S17).
[0034]
By combining the synthesized voice signal with the discrimination sound signal outside the audible range in this way, it is possible to include a frequency component that is not present in the actual voice of a real person. It can be disabled and unauthorized use can be prevented.
[0035]
As described above, according to the present embodiment, identification sound synthesis processing section 111 includes an identification sound signal outside the audible range, which is a synthesized sound signal, in the synthesized sound signal, so that portable terminal device 1 can output a sound. Since a synthesized voice including an identification sound outside the audible range indicating that it is a synthesized output voice is output, even if the output voice is used for an unauthorized purpose, the voice authentication device is provided with a voice frequency analysis function. Thus, it is possible to detect that a frequency component of the discrimination sound which is not included in the actual voice of the actual person is included, so that it is possible to prevent the illegal use of the synthesized voice.
[0036]
(Embodiment 3)
The configuration of the communication system having the portable terminal device with a storage device according to the third embodiment of the present invention is the configuration of FIG. 1 as in the first embodiment. The configuration of the portable terminal device with a storage device according to the third embodiment of the present invention is the same as that of the second embodiment shown in FIG.
[0037]
The operation of the portable terminal device with a storage device thus configured will be described with reference to FIG. FIG. 6 is a flowchart illustrating the operation of the portable terminal device with a storage device in FIG. 4 (the operation of the system control unit 101). Steps S21 to S24 in FIG. 6 are the same as steps S11 to S14 in FIG. 5, and a description thereof will be omitted.
[0038]
6, the system control unit 101 issues a command to the speech synthesis processing unit 102 to start the processing. The voice synthesis processing unit 102 performs analysis while sequentially reading out the synthesis target data from the storage unit 105 (S25). Then, it is determined whether or not the content of the read synthesis target data is an identification code (the identification code is manually input to an arbitrary place of the synthesis target data meaning text data in this case) (S26). When it is determined that the content of the synthesis target data is not the identification code, the phoneme data most suitable for each character data is read out from the storage unit 105 or the storage device 2 and extracted (S27). This processing is not performed if the identification code is determined. The extracted data and the identification code are connected one after another and stored in the storage unit 105 (S28).
[0039]
Next, the system control unit 101 reads the data (synthesized voice data) processed in step S28 from the storage unit 105. Then, it is determined whether or not the content of the read data is an identification code (S29). If it is determined that it is not the identification code, the data is passed to the audio output processing unit 104 (S30). The audio output processing unit 104 converts the format of the received data and outputs the data to the speaker 108 or headphones (S33). If it is determined that the identification code is the identification code, the system control unit 101 activates the identification sound synthesis processing unit 111 (S31). The identification sound synthesis processing unit 111 synthesizes an identification sound signal outside the audible range with the synthesized sound signal output from the sound output processing unit 104 (S32), and outputs the synthesized sound signal to the speaker 108 or headphones (S33).
[0040]
By combining the synthesized voice signal with the discrimination sound signal outside the audible range in this way, it is possible to include a frequency component that is not present in the actual voice of a real person. It can be disabled and unauthorized use can be prevented.
[0041]
As described above, according to the present embodiment, the identification sound synthesis processing unit 111 does not output the identification sound signal outside the audible range indicating that it is a synthesized audio signal over all of the synthesized audio signals, By including the identification code in the data as a trigger in the synthesized voice signal, even if the output voice of the portable terminal device 1 is used for an unauthorized purpose, the voice authentication device is provided with a voice frequency analysis function, thereby enabling the identification. By performing only the frequency analysis of the synthesized speech signal with a sign, it is possible to detect that the frequency component of the discriminating sound that is not included in the actual human voice is included. Unauthorized use of the synthesized speech can be prevented.
[0042]
【The invention's effect】
As described above, according to the portable terminal device with a storage device according to claim 1 of the present invention, the portable terminal with a storage device including the portable terminal device and a storage device that is detachable from the portable terminal device A storage device, a phoneme database storage unit for storing a phoneme database in which phoneme data is made into a database, a synthesis target data storage unit for storing synthesis target data to be read, and data transfer with the portable terminal device The portable terminal device has a storage device interface unit that exchanges data with the storage device, a system control unit that controls the whole, and a reading selection process that selects a range of synthesis target data. And a phoneme database and a phoneme database read from the phoneme database storage unit via the storage device interface unit and the terminal device interface unit. A voice synthesis processing unit that generates synthesized voice data from the synthesis target data read from the synthesis target data storage unit based on the selected range, and a voice output processing unit that inputs the generated synthesized voice data and outputs it as a synthesized voice signal , The user can select a range of the synthesis target data as the reading target information and omit the reading of the unnecessary part, so that the reading of novels or the like desired by himself can be efficiently performed without wasting time. Has the advantageous effect of being able to listen to music.
[0043]
According to the portable terminal device with a storage device according to claim 2, the portable terminal device with a storage device according to claim 1, further comprising an identification sound synthesis processing unit instead of the reading selection processing unit, and the identification sound synthesis processing unit. By including an identification sound signal outside the audible range indicating that the speech is a synthesized speech signal in the synthesized speech signal, the synthesized speech including the identification sound outside the audible range indicating the output speech of the speech synthesis is output from the portable terminal device. Since the voice is output, even if the output voice is used for an unauthorized purpose, the voice authentication device is provided with a voice frequency analysis function, so that a frequency component of an identification sound that is not present in the real human voice is included. Is detected, it is possible to obtain an advantageous effect that illegal use of synthesized speech can be prevented.
[0044]
According to the portable terminal device with a storage device according to claim 3, the portable terminal device with a storage device according to claim 1 is provided with an identification sound synthesis processing unit instead of the reading selection processing unit. Rather than outputting an identification sound signal outside the audible range indicating that it is a synthesized audio signal over all of the synthesized audio signals, the identification code in the synthesis target data is included in the synthesized audio signal as a trigger, so that the mobile terminal Even if the output voice of the device is used for an unauthorized purpose, the voice authentication device is equipped with a frequency analysis function of the voice, so that only the frequency analysis of the synthesized voice signal with the identification code is performed, Since it is possible to detect that the frequency component of the discriminating sound that does not exist is included, it is possible to prevent the illegal use of the synthesized voice by analyzing the frequency of a smaller number of signals. Effect can be obtained.
[Brief description of the drawings]
FIG. 1 is a configuration diagram illustrating a communication system including a mobile terminal device, a server device, a personal computer, and the like.
FIG. 2 is a block diagram showing a portable terminal device with a storage device according to the first embodiment of the present invention;
FIG. 3 is a flowchart showing the operation of the portable terminal device with a storage device of FIG. 2;
FIG. 4 is a block diagram showing a portable terminal device with a storage device according to the second and third embodiments of the present invention;
FIG. 5 is a flowchart showing the operation of the portable terminal device with a storage device of FIG. 4;
6 is a flowchart showing the operation of the portable terminal device with a storage device of FIG. 4;
[Explanation of symbols]
1 Mobile terminal device
2 Recording device
3 server device
4 PC
5 Internet
6 Public line
101 System control unit
102 Voice synthesis processing unit
103 Storage device interface unit
104 audio output processing unit
105 storage unit
106 Operation unit
107 Display
108 speaker
109 power supply
110 Reading selection unit
111 identification sound synthesis processing unit
120 Terminal device interface
121 Phoneme Database Storage
122 Synthetic Object Data Storage Unit

Claims (3)

A portable terminal device with a storage device including a portable terminal device and a storage device that is detachable from the portable terminal device,
The storage device is a phoneme database storage unit that stores a phoneme database that is a database of phoneme data, a synthesis target data storage unit that stores synthesis target data to be read, and a terminal that exchanges data with the portable terminal device. Device interface unit,
The portable terminal device includes a storage device interface unit that exchanges data with the storage device, a system control unit that controls the whole, a reading selection processing unit that selects a range of the synthesis target data, and the storage device interface unit. And a speech synthesis processing unit that generates synthesized speech data from the synthesis target data read from the synthesis target data storage unit based on the phoneme database read from the phoneme database storage unit and the selected range via the terminal device interface unit. And a voice output processing unit for inputting the generated synthesized voice data and outputting it as a synthesized voice signal. An identification sound synthesis processing unit is provided in place of the reading selection processing unit, and the identification sound synthesis processing unit includes an identification sound signal out of an audible range indicating the synthesized sound signal in the synthesized sound signal. The mobile terminal device according to claim 1. An identification sound synthesis processing unit is provided in place of the reading selection processing unit, and the identification sound synthesis processing unit outputs an identification sound signal outside the audible range indicating the synthesized voice signal over all of the synthesized voice signals. The portable terminal device according to claim 1, wherein an identification code in the synthesis target data is included in the synthesized speech signal as a trigger instead of the synthesis target data.

Images