JP2018072509A - Voice reading device, voice reading system, voice reading method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To permit a user to easily recognize a content of a character string in a range selected by the user.SOLUTION: A voice reading device comprises: a display section for displaying text information; an operation input section for receiving operation input to select a part of or a whole character string included in the text information displayed by the display section; and a voice reproduction section for reproducing the voice on the basis of character string data showing the character string selected by the operation input.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a voice reading device, a voice reading system, a voice reading method, and a program.

  In recent years, portable terminals equipped with a small display such as a smartphone have become widespread. Along with the miniaturization of the display, the text size of the document displayed on the display is also reduced. However, this may make the text too small and difficult to read, particularly for elderly people who have diminished vision. For example, when you process a contract for a service from the screen of a smartphone, documents such as confirmation items and contracts related to the contract may be displayed. There are many. Therefore, for example, the insurance contract information providing system described in Patent Document 1 divides the clauses into a plurality of parts according to the contents in advance, and if there is an instruction to read the clauses, it should be presented in the electronic data of the entire clauses The electronic data of the target part is read from the clause database and displayed on the client terminal.

JP 2009-116610 A

  When an enlargement operation is performed on a part of the screen on which the terms and conditions are displayed, the enlarged image does not fit on the display screen, and the user needs to read while scrolling. On the other hand, the insurance contract information providing system described in Patent Document 1 previously divides the clauses into a plurality of parts according to the contents, reads out the electronic data divided for each part from the clause database, and provides it to the client terminal. Therefore, the user does not necessarily need to enlarge the entire part, but even when only a part of the part is desired to be confirmed, it is displayed including unnecessary data. In that case, it is not always easy for the user to confirm the contents.

  The present invention has been made in view of such circumstances, and an object of the present invention is to provide a speech reading device, a speech reading system, and a speech reading method capable of easily recognizing the contents of a character string in a range selected by a user. , And to provide a program.

  In order to solve the above-described problem, according to one embodiment of the present invention, a display unit that displays text information and an operation input that selects a part or all of a character string included in the text information displayed by the display unit are provided. A speech reading apparatus comprising: an operation input unit that accepts; and an audio reproduction unit that reproduces audio based on character string data indicating the character string selected by the operation input.

  Moreover, one aspect of the present invention is characterized in that the voice reproduction unit reproduces voice based on character string data indicating a character string obtained by performing language analysis on the character string based on the character string data using dictionary information. The speech reading apparatus according to (1).

  Further, according to one aspect of the present invention, the voice reproduction unit may include a character string in which a character string obtained by performing a linguistic analysis on a character string based on the character string data using dictionary information is further translated into another language. The voice reading apparatus according to (1), wherein voice based on data is reproduced.

Another embodiment of the present invention is a speech reading system including a speech reading device and a speech conversion server, wherein the speech reading device includes a display unit that displays text information and the text displayed by the display unit. An operation input unit that receives an operation input for selecting a part or all of a character string included in the information, and character string data indicating the character string selected by the operation input are transmitted to the second communication unit, and voice data is transmitted. A first communication unit that receives from the second communication unit; an audio reproduction unit that reproduces audio based on the audio data;
The voice conversion server receives a voice conversion unit that converts the character string data transmitted from the first communication unit into the voice data, and the character string data from the first communication unit, And a second communication unit that transmits the voice data converted by the voice conversion unit to the first communication unit.

  One embodiment of the present invention is a computer-to-speech reading method, in which a display unit displays text information, and an operation input unit includes characters included in the text information displayed by the display unit. An operation input step for receiving an operation input for selecting a part or all of the column; and an audio reproduction step for reproducing an audio based on character string data indicating the character string selected by the operation input. It is a voice reading method characterized by having.

  A display step for displaying text information on a computer, an operation input step for accepting an operation input by a user selecting a part or all of a character string included in the text information displayed by the display step, and the operation input And a sound reproduction step of reproducing sound based on character string data indicating the selected character string.

  As described above, according to the present invention, the contents of the character string in the range selected by the user can be easily recognized.

It is a block diagram which shows the function structure of the voice reading apparatus and the voice conversion server of the voice reading system by 1st Embodiment of this invention. It is the schematic which shows an example of the character string selection in the voice reading apparatus of the voice reading system by 1st Embodiment of this invention. It is a flowchart which shows operation | movement of the speech reading system by 1st Embodiment of this invention. It is a block diagram which shows the function structure of the speech conversion server of the speech reading system by 2nd Embodiment of this invention. It is a flowchart which shows operation | movement of the speech reading system by 2nd Embodiment of this invention. It is a block diagram which shows the function structure of the speech conversion server of the speech reading system by 3rd Embodiment of this invention. It is a flowchart which shows operation | movement of the speech reading system by 3rd Embodiment of this invention. It is a block diagram which shows the function structure of the speech reading apparatus of the speech reading system by 4th Embodiment of this invention.

<First Embodiment>
Hereinafter, a voice reading system according to a first embodiment of the present invention will be described with reference to the drawings.

[Configuration of the voice reading system]
FIG. 1 is a block diagram showing a functional configuration of a speech reading apparatus and a speech conversion server of the speech reading system according to the first embodiment of the present invention. The voice reading system 1 shown in FIG. 1 includes a voice reading device 10A, a voice conversion server 20A, and a communication network 50.

The voice reading apparatus 10A displays text information, accepts an operation input for selecting part or all of a character string included in the displayed text information, and receives character string data indicating a character string selected by the operation input. The data is transmitted to the voice conversion server 20A via the communication network 50. Further, the voice reading device 10A receives voice data from the voice conversion server 20A via the communication network 50, and reproduces voice based on the voice data.
The speech reading apparatus is a portable small information terminal, such as a smartphone.

The voice conversion server 20A receives the character string data transmitted from the voice reading device 10A via the communication network 50, converts the received character string data into voice data, and converts the converted voice data to the communication network 50. To the voice reading apparatus 10A.
The voice conversion server 20 includes a computer device such as a general-purpose computer or a personal computer.

The communication network 50 is a communication network in which the voice reading device 10A and the voice conversion server 20 are connected for communication. The communication network 50 is configured by, for example, the Internet, a WAN (Wide Area Network), a LAN (Local Area Network), or any combination of these communication networks.
Hereinafter, functional configurations of the voice reading device 10A and the voice conversion server 20A will be described.

  The speech reading system 1 according to the present embodiment includes the speech reading device 10A, the speech conversion server 20A, and the communication network 50, but is not limited thereto. For example, a configuration in which the speech reading apparatus 10A has the functions of the speech conversion server 20A as in the speech reading system 1 according to the fourth embodiment described later may be used. For example, a smartphone displays text information, accepts an operation input for selecting part or all of a character string included in the displayed text information, and converts character string data indicating the selected character string into voice data. A configuration that reproduces audio based on the audio data, that is, a configuration in which reading by audio is performed by a smartphone alone may be employed.

[Configuration of voice reading device]
As shown in FIG. 1, the voice reading device 10A includes a control unit 100, a storage unit 101, a communication unit 102, a display unit 103, an operation input unit 104, a selection range detection unit 105, and a voice reproduction unit 106. And comprising.

  The control unit 100 controls processing performed by each functional block of the speech reading apparatus 10A. The control unit 100 includes, for example, a CPU (Central Processing Unit).

The storage unit 101 stores various programs and various data used in the speech reading apparatus 10A. The storage unit 101 also stores content data such as text information (for example, a source file described in HTML format) included in an image displayed by the display unit 103 described later.
The storage unit 101 is a storage medium, for example, HDD (Hard Disk Drive), flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), RAM (Random Access read / write Memory) Memory), ROM (Read Only Memory), or any combination of these storage media.

  The communication unit 102 is a communication interface for communication connection with the communication network 50. The communication unit 102 transmits and receives various data between the speech reading apparatus 10 </ b> A and the speech conversion server 20 </ b> A via the communication network 50. The communication unit 102 (first communication unit), for example, transmits character string data indicating a character string selected by an operation input via the communication network 50 to the communication unit 202 (second second) of the voice conversion server 20A described later. To the communication unit). The communication unit 102 (first communication unit) receives voice data from the communication unit 202 (second communication unit) of the voice conversion server 20A described later via the communication network 50.

  The display unit 103 is a user interface that outputs image information to the user. For example, the display unit 103 displays an image including text information. The text information may be text information stored in the storage unit 101, or may be text information acquired from an external web server (not shown) or the like via the communication network 50. Further, for example, the display unit 103 applies an image (for example, a character string in a range selected by the user) indicating that the character string is in a range selected by the user among the character strings included in the text information. Displayed). The display unit 103 includes a display, for example, an LCD (Liquid Crystal Display) or an organic EL (electroluminescence) display.

  The operation input unit 104 is a user interface that receives an operation input from a user. For example, the operation input unit 104 receives an operation input for selecting a part or all of a character string included in the text information displayed by the display unit 103. The operation input unit 104 includes, for example, a touch panel type liquid crystal display in which a display constituting the display unit 103 and a touch operation detection sensor are integrated.

  The selection range detection unit 105 detects a selection range for selecting a character string based on the operation input received by the operation input unit 104, and generates character string data indicating a character string included in the detected selection range. A specific example of character string selection will be described later.

  The audio reproduction unit 106 is a user interface that outputs audio information to the user. For example, the audio reproduction unit 106 reproduces audio based on audio data received via the communication network 50 by the communication unit 102 (first communication unit). The audio reproducing unit 106 includes, for example, a speaker or headphones.

[Configuration of voice conversion server]
As illustrated in FIG. 1, the voice conversion server 20A includes a control unit 200, a storage unit 201, a communication unit 202, a voice information storage unit 203, and a voice conversion unit 204.

  The control unit 200 controls processing performed by each functional block of the voice conversion server 20A. The control unit 200 includes a CPU, for example.

  The storage unit 201 stores various programs and various data used in the voice conversion server 20A. The storage unit 201 is configured by a storage medium, for example, an HDD, a flash memory, an EEPROM, a RAM, a ROM, or any combination of these storage media.

  The communication unit 202 is a communication interface that is communicatively connected to the communication network 50. The communication unit 202 transmits / receives various data between the voice conversion server 20A and the voice reading device 10A via the communication network 50. The communication unit 202 (second communication unit), for example, transmits character string data indicating a character string selected by an operation input from the communication unit 102 (first communication unit) of the speech reading apparatus 10A via the communication network 50. Receive. In addition, the communication unit 202 (second communication unit) transmits the voice data, in which the character string is converted by the voice conversion unit 204 described later, via the communication network 50, to the communication unit 102 (first first) of the voice reading device 10A. Communication section).

  The voice information storage unit 203 stores voice information in which character string data and voice data are associated with each other. The audio information storage unit 203 is configured by a storage medium, for example, an HDD, a flash memory, an EEPROM, a RAM, a ROM, or any combination of these storage media.

  The voice conversion unit 204 uses the character string data transmitted from the communication unit 102 (first communication unit) of the voice reading apparatus 10A as a search key, and the character string data included in the voice information stored in the voice information storage unit 203. And the voice data associated with the searched character string data is acquired. Thereby, the voice conversion unit 204 converts the character string data transmitted from the communication unit 102 (first communication unit) of the voice reading apparatus 10A into voice data.

[Specific example of character string selection]
Hereinafter, an example of character string selection in the speech reading apparatus 10A will be described.
FIG. 2 is a schematic diagram showing an example of character string selection in the speech reading apparatus of the speech reading system according to the first embodiment of the present invention.

  FIG. 2 illustrates a smartphone that is the voice reading device 10 </ b> A. The smartphone is equipped with a touch panel type liquid crystal display that also serves as the display unit 103 and the operation input unit 104. As shown in the figure, the liquid crystal display displays an image showing a document starting with the words “XXXXX Corporation is ~”, and a pull-down menu is displayed above the image showing the document on the liquid crystal display. An image indicating pm1 and an image indicating the voice reading button bt1 are displayed.

  Further, as shown in the figure, in the image showing the document displayed on the liquid crystal display, the range of the character string from “technical or ~” to “optimize ~” is shaded. The shaded range is the character string selection range sa1, and on the liquid crystal display, the portion where the character string from "Technology or ~" to "Optimize ~" is traced by the user's finger It is an image showing. In this way, when the user visually recognizes a sentence on the liquid crystal display and there is a difficult part to read, the user selects a part of the character string in the document by tracing the character string of the part with a finger. You can specify (select a character string).

  Of the text displayed on the display unit 103 of the speech reading apparatus 10A shown in FIG. 2, for example, the user selects and designates the character string of the part “customer information transmission based on art and know-how”. To do. Thus, when it is detected that only a part of a word or idiom is selected and designated as in “jutsu” or “information transmission”, the speech reading apparatus 10 </ b> A has a range estimated as a delimiter between words and idioms. It is also possible to automatically expand the selection / designation range to “selection” from “technology” to “information transmission”.

[Operation of voice reading system]
Hereinafter, the operation of the speech reading system 1 according to the first embodiment will be described.
FIG. 3 is a flowchart showing the operation of the speech reading system according to the first embodiment of the present invention. The processing of this flowchart starts when content data including text information is output to the display unit 103 by the control unit 100 of the speech reading apparatus 10A.

(Step S001) Display unit 103 of speech reading apparatus 10A acquires content data including text information. Thereafter, the process proceeds to step S002.
The content data may be content data stored in advance in the storage unit 101 that is output from the storage unit 101 to the display unit 103 by the control unit 100, or may be a communication unit by the control unit 100. Content data acquired from an external content server (not shown) connected to the communication network 50 and output from the display 102 to the display unit 103 may be used.

(Step S002) The display unit 103 of the speech reading apparatus 10A displays an image indicating content based on the acquired content data. Thereafter, the process proceeds to step S003.

(Step S003) The operation input unit 104 of the voice reading device 10A detects a signal indicating a voice reading instruction based on a user operation input. For example, in the liquid crystal display shown in FIG. 2, when the part of the image showing the speech reading button bt <b> 1 is touched by the user's finger, a signal indicating a speech reading instruction is generated, and the operation input unit 104 detects the signal. To do. When the operation input unit 104 detects the signal, the operation input unit 104 enters a mode for receiving an operation input indicating character string selection by the user. Thereafter, the process proceeds to step S004.

(Step S004) The selection range detection unit 105 of the speech reading apparatus 10A detects a range in which a character string based on an operation input received by the operation input unit 104 is selected. For example, in the liquid crystal display shown in FIG. 2, the part of the character string selection range sa1 (that is, the character string range from “technology and” to “optimize”) is traced by the user's finger. When the touch operation detection sensor mounted on the liquid crystal display detects, the selection range detection unit 105 detects the character string selection range. Further, when the operation input unit 104 detects that the user's finger is separated from the liquid crystal display by the touch operation detection sensor, the operation input unit 104 switches from a mode in which an operation input indicating character string selection by the user is received to a normal mode. Thereafter, the process proceeds to step S005.

(Step S005) The selection range detection unit 105 of the speech reading apparatus 10A extracts the character string included in the image of the character string selection range detected in Step S004, and converts the extracted character string into text data. Generate. The control unit 100 transmits the character string data to the communication unit 202 (second communication unit) of the voice conversion server 20A via the communication unit 102 (first communication unit). Thereafter, the process proceeds to step S006.

(Step S006) The communication unit 202 (second communication unit) of the voice conversion server 20A transmits the character string data transmitted from the communication unit 102 (first communication unit) of the voice reading device 10A in step S005 to the communication network. 50 through. The control unit 200 of the voice conversion server 20A outputs the character string data received by the communication unit 202 to the voice conversion unit 204.
When the voice conversion unit 204 acquires the character string data received by the communication unit 202 from the control unit 200, the voice conversion unit 204 uses the character string data as a search key to convert the character string data included in the voice information stored in the voice information storage unit 203. Search is performed, and voice data associated with the searched character string data is acquired. Thereby, the voice conversion unit 204 converts the character string data transmitted from the communication unit 102 (first communication unit) of the voice reading apparatus 10A into voice data.
The control unit 200 of the voice conversion server 20A transmits the voice data converted by the voice conversion unit 204 to the communication unit 102 (first communication unit) of the voice reading device 10A via the communication unit 202 (second communication unit). ). Thereafter, the process proceeds to step S007.

(Step S007) The communication unit 102 (first communication unit) of the speech reading apparatus 10A transmits the voice data transmitted from the communication unit 202 (second communication unit) of the voice conversion server 20A in step S006 to the communication network 50. Receive via. The control unit 100 of the speech reading apparatus 10 </ b> A outputs the audio data received by the communication unit 102 to the audio reproduction unit 106.
When the audio reproducing unit 106 acquires the audio data received by the communication unit 102 by the control unit 100, the audio reproducing unit 106 reproduces audio based on the audio data.
Thus, the process of this flowchart is completed.

<Second Embodiment>
Hereinafter, a speech reading system according to a second embodiment of the present invention will be described with reference to the drawings.

[Configuration of voice conversion server]
FIG. 4 is a block diagram showing a functional configuration of the voice conversion server of the voice reading system according to the second embodiment of the present invention. The voice conversion server 20B shown in the figure includes a control unit 200, a storage unit 201, a communication unit 202, a voice information storage unit 203, a voice conversion unit 204, a dictionary storage unit 205, a language analysis unit 206, It is comprised including. In the figure, portions corresponding to those in FIG. 1 are denoted by the same reference numerals, and description thereof is omitted.

  The dictionary storage unit 205 concentrates on dictionary information in which character string data is associated with language information such as words, idioms, meanings, relationships with other data, origin, usage, format, and intonation. Remember. The dictionary storage unit 205 is configured by a storage medium, for example, an HDD, a flash memory, an EEPROM, a RAM, a ROM, or any combination of these storage media.

  The language analysis unit 206 uses the character string data transmitted from the communication unit 102 (first communication unit) of the speech reading apparatus 10A as a search key, and the character string data included in the dictionary information stored in the dictionary storage unit 205. The language information associated with the retrieved character string data is retrieved. As a result, the language analysis unit 206 analyzes the character string indicated by the character string data transmitted from the communication unit 102 (first communication unit) of the speech reading apparatus 10A, and breaks phrases or words in the character string. And the phrase and intonation included in the character string.

  The voice conversion unit 204 converts character string data into voice data using the language information (for example, information indicating a phrase and intonation) specified by the analysis by the language analysis unit 206. Thereby, the voice reading system 1 in the second embodiment can read out with a voice with a more natural pronunciation as compared with the voice reading system 1 in the first embodiment.

[Operation of voice reading system]
Hereinafter, the operation of the speech reading system 1 according to the second embodiment will be described.
FIG. 5 is a flowchart showing the operation of the speech reading system according to the second embodiment of the present invention. The processing of this flowchart starts when content data including text information is output to the display unit 103 by the control unit 100 of the speech reading apparatus 10A.

  Since the operation from step S101 to step S105 is the same as the operation from step S001 to step S005 described in the operation of the speech reading system 1 according to the first embodiment, the description thereof is omitted.

(Step S106) The communication unit 202 (second communication unit) of the voice conversion server 20A transmits the character string data transmitted from the communication unit 102 (first communication unit) of the voice reading device 10A in step S105 to the communication network. 50 through. The control unit 200 of the voice conversion server 20A outputs the character string data received by the communication unit 202 to the language analysis unit 206.
When the language analysis unit 206 acquires the character string data received by the communication unit 202 from the control unit 200, the language analysis unit 206 searches the character string data included in the dictionary information stored in the dictionary storage unit 205 using the character string data as a search key. The language information associated with the retrieved character string data is acquired. The control unit 200 outputs the language information acquired by the language analysis unit 206 to the voice conversion unit 204. Thereafter, the process proceeds to step S107.

(Step S107) When the speech conversion unit 204 of the speech conversion server 20A acquires the language information acquired by the language analysis unit 206 by the control unit 200, the speech conversion unit 204 uses the language information (for example, information indicating a phrase and intonation). Convert from character string data to voice data.
As a result, the voice conversion unit 204 converts the character string data, which has been linguistically analyzed by the language analysis unit 206, from the character string data transmitted from the communication unit 102 (first communication unit) of the voice reading apparatus 10A into voice data. Convert.
The control unit 200 of the voice conversion server 20A transmits the voice data converted by the voice conversion unit 204 to the communication unit 102 (first communication unit) of the voice reading device 10A via the communication unit 202 (second communication unit). ). Thereafter, the process proceeds to step S008.

Since the operation in step S108 is the same as the operation in step S007 described in the operation of the speech reading system 1 according to the first embodiment, a description thereof will be omitted.
Thus, the process of this flowchart is completed.

<Third Embodiment>
Hereinafter, a speech reading system according to a third embodiment of the present invention will be described with reference to the drawings.

[Configuration of voice conversion server]
FIG. 6 is a block diagram showing a functional configuration of the voice conversion server of the voice reading system according to the third embodiment of the present invention. The voice conversion server 20C shown in the figure includes a control unit 200, a storage unit 201, a communication unit 202, a voice information storage unit 203, a voice conversion unit 204, a dictionary storage unit 205, a language analysis unit 206, A foreign language dictionary storage unit 207 and a translation unit 208 are included. In the figure, parts corresponding to those in FIGS. 1 and 4 are denoted by the same reference numerals, and description thereof is omitted.

  The foreign language dictionary storage unit 207 stores foreign language dictionary information in which native language information and foreign language information are associated with each other. The foreign language dictionary storage unit 207 is configured by a storage medium, for example, an HDD, a flash memory, an EEPROM, a RAM, a ROM, or any combination of these storage media.

The translation unit 208 searches the language information of the native language included in the foreign language dictionary information stored in the foreign language dictionary storage unit 207 using the language information in the native language analyzed by the language analysis unit 206 as a search key, The foreign language language information associated with the searched native language information is acquired. Thereby, the translation unit 208 translates the native language indicated by the character string data transmitted from the communication unit 102 (first communication unit) of the speech reading apparatus 10A into the designated foreign language.
Note that the user can select a language using the pull-down menu pm1 shown in FIG. The translation unit 208 translates from the native language into the foreign language specified by the pull-down menu pm1.

[Operation of voice reading system]
Hereinafter, the operation of the speech reading system 1 according to the third embodiment will be described.
FIG. 7 is a flowchart showing the operation of the speech reading system according to the third embodiment of the present invention. The processing of this flowchart starts when content data including text information is output to the display unit 103 by the control unit 100 of the speech reading apparatus 10A.

  The operations in step S201 and step S202 are the same as the operations in step S001 and step S002 described in the operation of the speech reading system 1 according to the first embodiment, and thus the description thereof is omitted.

(Step S203) The operation input unit 104 of the speech reading apparatus 10A detects a signal indicating a language selection instruction based on a user operation input (for example, an operation input by the pull-down menu pm1 shown in FIG. 2). When the operation input unit 104 detects the signal, the control unit 100 temporarily stores information indicating the language selected by the user in the storage unit 101. Thereafter, the process proceeds to step S205.

  The operations in step S204 and step S205 are the same as the operations in step S003 and step S004 described in the operation of the speech reading system 1 according to the first embodiment, and thus the description thereof is omitted.

(Step S206) The selection range detection unit 105 of the speech reading apparatus 10A extracts the character string included in the image of the character string selection range detected in Step S205, and converts the extracted character string into text data. Generate. The control unit 100 transmits the character string data to the communication unit 202 (second communication unit) of the voice conversion server 20A via the communication unit 102 (first communication unit). In addition, information indicating the language selected by the user, which is temporarily stored in the storage unit 101 in step S203, is also transmitted. Thereafter, the process proceeds to step S207.

(Step S207) The communication unit 202 (second communication unit) of the speech conversion server 20A receives the character string data transmitted from the communication unit 102 (first communication unit) of the speech reading apparatus 10A in Step S206 and the user. Information indicating the selected language is received via the communication network 50. The control unit 200 of the voice conversion server 20A outputs the character string data received by the communication unit 202 to the language analysis unit 206.
When the language analysis unit 206 acquires the character string data received by the communication unit 202 from the control unit 200, the language analysis unit 206 searches the character string data included in the dictionary information stored in the dictionary storage unit 205 using the character string data as a search key. The language information associated with the retrieved character string data is acquired. The control unit 200 outputs the language information acquired by the language analysis unit 206 to the translation unit 208. Thereafter, the process proceeds to step S208.

(Step S208) When the translation unit 208 of the speech conversion server 20A acquires the language information of the native language acquired by the language analysis unit 206 by the control unit 200, the foreign language dictionary storage unit using the language information of the native language as a search key. The language information of the native language included in the foreign language dictionary information stored in 207 is searched, and the language information of the foreign language associated with the searched language information of the native language is acquired. Here, the translation unit 208 acquires from the foreign language dictionary storage unit 207 the foreign language language information indicated by the information indicating the language selected by the user, received from the communication unit 202 in step S207. The control unit 200 outputs the language information of the foreign language acquired by the translation unit 208 to the voice conversion unit. Thereafter, the process proceeds to step S209.

(Step S209) When the voice conversion unit 204 of the voice conversion server 20A acquires the language information of the foreign language acquired by the translation unit 208 by the control unit 200, the language information of the foreign language (for example, information indicating a phrase and intonation) ) To convert foreign language character string data to foreign language speech data.
As a result, the speech conversion unit 204 performs language analysis on the character string data of the native language transmitted from the communication unit 102 (first communication unit) of the speech reading apparatus 10A by the language analysis unit 206, and further by the translation unit 208. Foreign language character string data converted into a foreign language by translation is converted into voice data.
The control unit 200 of the voice conversion server 20A transmits the voice data converted by the voice conversion unit 204 to the communication unit 102 (first communication unit) of the voice reading device 10A via the communication unit 202 (second communication unit). ). Thereafter, the process proceeds to step S210.

The operation in step S210 is the same as the operation in step S007 described in the operation of the speech reading system 1 according to the first embodiment, and thus the description thereof is omitted.
Thus, the process of this flowchart is completed.

<Fourth Embodiment>
Hereinafter, a speech reading system according to a fourth embodiment of the present invention will be described with reference to the drawings.
The voice reading system 1 according to the first to third embodiments described above includes a voice reading device 10A and a voice conversion server 20 (20A, 20B, 20C) connected by a communication network 50 as shown in FIG. Consists of. In the speech-to-speech system 1 according to the first to third embodiments, the speech-to-speech device 10A receives an operation input from the user, performs speech-to-speech, and the speech conversion server performs conversion from character string data to speech data. However, the present invention is not limited to this configuration. For example, like the voice reading device 10B of the voice reading system 1 according to the fourth embodiment, the voice reading device 10B itself has the function that the voice conversion server 20 (20A, 20B, 20C) has. It may be.

[Configuration of voice reading device]
FIG. 8 is a block diagram showing a functional configuration of the speech reading apparatus of the speech reading system according to the fourth embodiment of the present invention. The voice reading apparatus 10B shown in the figure includes a control unit 100, a storage unit 101, a communication unit 102, a display unit 103, an operation input unit 104, a selection range detection unit 105, a voice reproduction unit 106, and a voice. The information storage unit 203, the voice conversion unit 204, the dictionary storage unit 205, the language analysis unit 206, the foreign language dictionary storage unit 207, and the translation unit 208 are configured. In the figure, parts corresponding to those in FIGS. 1, 4 and 6 are given the same reference numerals, and the description thereof is omitted.

  As described above, the speech-to-speech system 1 according to each embodiment of the present invention can easily recognize the contents of the character string in the range selected by the user.

  According to the speech-to-speech system 1 according to each embodiment of the present invention, the user can perform speech-to-speech by tracing a difficult-to-read character string portion with a finger in the document displayed on the display. The screen of a smartphone is generally large enough to fit in the palm of the hand, and when a long document (for example, a web page or app description display) is displayed on the display of the smartphone, the width of the document within the range of the width of the display In the state where the entire image is displayed, the displayed size per character is, for example, about 3 millimeters or less, and a portion that is too small to read is generated. However, according to the speech reading system 1 according to each embodiment of the present invention, since the voice corresponding to the designated character string is output, the user does not perform an operation for enlarging the display, and the user can It is easy to recognize the contents of the document displayed on the screen.

  Further, according to the speech reading system 1 according to each embodiment of the present invention, the user designates an arbitrary range by tracing a difficult-to-read character string portion with a finger in the document displayed on the display, The character string included in the range can be read out by voice. Thus, unlike the conventional technique, the speech reading system 1 according to each embodiment of the present invention is not limited such that only a predetermined document or character string can be read out by speech.

  In addition, the speech reading system 1 according to each embodiment of the present invention can perform speech analysis by performing language analysis on the selected character string and further translating it. Thus, for example, at a bank counter, a foreign customer selects a portion of a character string that cannot be translated in the displayed document with a finger and selects the selected character string with the mother of the foreigner. It can be read as a voice translated into Japanese.

  The speech reading apparatus 10 (10A, 10B) and the speech conversion server 20 (20A, 20B, 20C) in the above-described embodiment may be realized by a computer. In that case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be read into a computer system and executed. Here, the “computer system” includes an OS and hardware such as peripheral devices. The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. Furthermore, the “computer-readable recording medium” dynamically holds a program for a short time like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. In this case, a volatile memory inside a computer system serving as a server or a client in that case may be included and a program held for a certain period of time. Further, the program may be a program for realizing a part of the above-described functions, and may be a program capable of realizing the functions described above in combination with a program already recorded in a computer system. You may implement | achieve using programmable logic devices, such as FPGA (Field Programmable Gate Array).

  The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes designs and the like that do not depart from the gist of the present invention.

  DESCRIPTION OF SYMBOLS 1 ... Voice reading system, 10 (10A, 10B) ... Voice reading apparatus, 20 (20A, 20B, 20C) ... Voice conversion server, 50 ... Communication network, 100 ... Control part, DESCRIPTION OF SYMBOLS 101 ... Memory | storage part, 102 ... Communication part (1st communication part), 103 ... Display part, 104 ... Operation input part, 105 ... Selection range detection part, 106 ... Voice Playback unit, 200... Control unit, 201... Storage unit, 202 .. communication unit (second communication unit), 203... Voice information storage unit, 204. ..Dictionary storage unit 206 ... Language analysis unit 207 ... Foreign language dictionary storage unit 208 ... Translation unit bt1 ... Speech button, sa1 ... Character string selection range, pm1 ··pull-down menu

Claims (6)

A display for displaying text information;
An operation input unit that receives an operation input for selecting part or all of a character string included in the text information displayed by the display unit;
An audio reproduction unit for reproducing audio based on character string data indicating the character string selected by the operation input;
A speech-to-speech device comprising: The voice reading unit according to claim 1, wherein the voice reproduction unit reproduces voice based on character string data indicating a character string obtained by performing language analysis on the character string based on the character string data using dictionary information. apparatus. The voice reproduction unit reproduces voice based on character string data indicating a character string obtained by translating a character string based on the character string data using a dictionary information into a language. The speech reading apparatus according to claim 1, wherein A voice reading system having a voice reading device and a voice conversion server,
The voice reading device is
A display for displaying text information;
An operation input unit that receives an operation input for selecting part or all of a character string included in the text information displayed by the display unit;
A first communication unit that transmits character string data indicating a character string selected by the operation input to the second communication unit and receives voice data from the second communication unit;
An audio reproduction unit for reproducing audio based on the audio data;
With
The voice conversion server
A voice conversion unit that converts the character string data transmitted from the first communication unit into the voice data;
A second communication unit that receives the character string data from the first communication unit and transmits the voice data converted by the voice conversion unit to the first communication unit;
A speech-to-speech system characterized by comprising: A computer-to-speech reading method,
A display step for displaying text information;
An operation input step in which an operation input unit receives an operation input for selecting a part or all of a character string included in the text information displayed by the display unit;
An audio reproduction step for reproducing audio based on character string data indicating the character string selected by the operation input;
A speech reading method characterized by comprising: On the computer,
A display step for displaying text information;
An operation input step of accepting an operation input by a user who selects a part or all of the character string included in the text information displayed by the display step;
An audio reproduction step of reproducing audio based on character string data indicating the character string selected by the operation input;
A program for running

Images