JP2008090332A - Character information-speech converting method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a character information-speech converting method in which kinds of speeches to be output are determined according to contents of a document to be read aloud. <P>SOLUTION: The character information-speech converting method consists of: inputting character data 7 as electronic data; extracting a character string in unique representation from the character data 7; integrating predetermined points by kinds of speeches corresponding to the unique representation as to the character data 7; and outputting integrated point data 10 by kinds of speeches. Further, the character information-speech converting method voices and outputs the character data 7 with a speech of a kind corresponding to the highest points. Points are set to be higher for unique representation more characteristic of the kind of the speech. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a character information speech conversion method, and more particularly to a character information speech conversion method in a character information reading system used in a personal computer, a mobile phone, or the like.

  Advances in technology to convert digitized (electronic) character information (character data) into human speech (words), so that a natural voice (pronunciation) comparable to that of a voice actor reading aloud can be reproduced It has become. This text information reading technique is used in, for example, personal computers and mobile phones. Also, with this technology, one document (character information) can be mechanically synthesized with the voice of a specific voice actor, and characters can be read with the voice of a favorite voice actor.

A technique is known in which a female voice is synthesized into a female sentence and a male voice is synthesized into a male sentence and the sentence is read out (see, for example, Patent Document 1). In addition, when a sentence in a language in which an article or adjective has a female form male form is output as a voice, a technique for synthesizing and outputting a gender voice that matches the sentence form is known (for example, Patent Documents). 2).
JP 11-296193 A JP 58-225483 A

  As described above, in the text information reading technology, it is known to select speech by distinguishing gender according to the text content, but it is possible to output with voice according to the text content, or to output voice In addition, there is no change in the sentence (end of sentence).

  However, considering the various uses of the text-to-speech reading system, users who change the end-of-sentence expression according to the main character of the voice (gender, age, era, main character of the anime, etc.), even for the same dialogue For the (listener or reader), it becomes more familiar (with less discomfort). In addition, when text data is converted into voice and output, it is desired to output the voice according to the content of the text.

  An object of this invention is to provide the character information audio | voice conversion method which determines the kind of audio | voice to output according to the content of the text which is a reading-out object.

  The character information speech conversion method of the present invention is a character information speech conversion method in a speech conversion device that converts character information and outputs speech information. Character information that is electronic data is input, and the character information includes a unique expression. A character string is extracted, points predetermined for each type of speech corresponding to the specific expression are added to the character information, and the integrated points are output for each type of speech.

  According to the character information speech conversion method of the present invention, when text data is converted into speech and output, it can be output with a voice corresponding to the content of the text. As a result, it is possible to reproduce the speech in a speech that is more familiar (less uncomfortable) to the user (listener or reader). Therefore, the application of the character information reading system can be expanded.

  FIG. 1 is a block diagram of a character information / speech conversion method, showing a configuration of a character information / speech conversion method of the present invention.

  The character information speech conversion device includes an input device 1, a display device (speech selection screen) 2, a conversion processing device 3, an output device 4, a conversion processing database (DB) 5, and a speech sample DB 6. The conversion processing device 3 includes a CPU (Central Processing Unit) and a main memory, and performs expression conversion processing or voice determination processing. The conversion process DB 5 is for performing the expression conversion process and the voice determination process for the input character information (character data) 7. The DB (expression conversion DB) 51 used in the expression conversion process and the DB used in the voice determination process (Voice determination DB) 52 (see FIG. 4). The voice sample DB 6 is for outputting the character data 7 as the voice data 9.

  The expression conversion process and the sound determination process in the conversion processing device 3 are realized by executing the expression conversion process program and the sound determination process program existing on the main memory by the CPU. These programs can be provided by being stored in various computer-readable recording media such as a flexible disk, a CD-ROM, and a DVD, or downloaded via the Internet.

  The input device 1 is a means for a user to input character data 7 as electronic data to the conversion processing device 3, and is composed of, for example, a keyboard. The input device 1 may be, for example, the display screen of the display device 2, a mobile phone, an electronic book, or the like. The display device 2 is means for selectively inputting the type of sound, and displays an instruction input screen to the user in accordance with an instruction from the conversion processing device 3. The output device 4 is means for outputting converted character data, and includes, for example, a speaker that outputs sound, a printer that outputs documents, a storage device that records electronic data, or a storage medium (or recording medium) thereof. . In the case of a speaker, for example, the input character data 7 is output by voice with the highest accumulated point (speech data 9 is output). If it is a printer, the converted character data is printed out. If it is a storage device or its storage medium, electronic data such as text data 8 (.txt file) is stored in a medium such as a flexible disk. The output device 4 outputs point data 10 as will be described later.

  FIG. 2 is an explanatory diagram of character information voice conversion processing, and shows the expression conversion processing in the character information voice conversion method of the present invention.

  In the expression conversion process, the conversion processing device 3 extracts a converted character string composed of a normal expression from the character data 7 input from the input device 1 using the expression conversion DB 51 based on the selected speech type. Then, the portion is replaced with a converted character string composed of a unique expression, and the converted character data is output from the output device 4 as voice data 9 or text data 8. When outputting the audio data 9, the conversion processing device 3 uses the audio sample DB 6 (omitted in FIG. 2).

  Character data (in this example, text data) 7 is input directly from the keyboard 1 which is the input device 1 of the conversion processing device 3, for example, by directly reading a sentence to be read out, i. By doing. Alternatively, the mobile phone 1 as the input device 1 is connected to the conversion processing device 3 and a part of the text displayed on the display screen of the mobile phone 1 is selected and designated. May be input. Furthermore, the text to be recorded is displayed on the display screen from the character data 7 previously captured as electronic data in various recording media (CD-ROM, DVD) as in the so-called electronic book 1 as the input device 1. However, it is also possible to input by selecting and specifying a part of it, “Make it apart from me”.

  The conversion processing device 3 displays a sound selection screen 21 on the display device 2 for selection of the sound type. The voice selection screen 21 displays a plurality of options for the type of voice such as “Manga hero A”, and any one of them can be selected. The user who sees this selects one voice type, for example, “manga hero A”. The type of voice may specify a voice actor, or may be specified as “~ wind”. The type of sound displayed is, for example, the type of sound whose sound is sampled in the sound sample DB 6. Although not shown, the audio sample DB 6 is a DB having a well-known configuration, and stores sampling data of the audio for each character string consisting of a normal expression and each character string consisting of a unique expression.

  When the character data (text data) 7 is input and the type of speech is selected, the conversion processing device 3 starts the expression conversion process using the expression conversion DB 51. The expression conversion DB 51 stores a set of a converted character string made up of a normal expression and a converted character string made up of a corresponding unique expression for each type of speech. The normal expression is a commonly used expression (word), such as “I” or “~ Kure”. The specific expression is an expression (word) peculiar to the type of sound, that is, a person. For example, for the type of sound such as the hero A of the comic, “Maro” corresponding to “I” and “~ Kure” corresponding to “ ~ Tamare "etc. When other audio types are selected, these correspondences change. The expression conversion DB 51 collects as many utterance expressions, greeting words, and expressions that indicate the person and the other party as the speaker's unique expressions as much as possible.

  The conversion processing device 3 uses the expression conversion DB 51 to search in order from the beginning of the character data 7, extracts the converted character string consisting of the normal expression, and replaces the part with the converted character string consisting of the unique expression. . For example, when the character data 7 that says “I want to divide it into me” is searched in the expression conversion DB 51 of the selected voice type “Manga hero A”, the converted character string “I” is extracted first. The Therefore, this is replaced with the corresponding conversion character string “MARO”. Next, since the converted character string “~ Kure” is extracted, it is replaced with the corresponding converted character string “˜Tama”. As a result, the character data after the conversion that “one piece was also divided” is obtained. Thereby, the character data (sentence) to be processed can be changed according to the type of voice to be read out, and the voice to be read out can be matched with the sentence.

  The conversion processing device 3 outputs the converted character data as audio data 9 or text data 8 from the output device 4. Thereby, not only the converted voice data 9 but also converted text data (text data 8) can be obtained. When outputting the audio data 9, the conversion processing device 3 uses the audio sample DB 6 of the selected audio type “manga hero A”.

  In the same manner as described above, for example, when a male voice actor of a historical drama character is selected on the voice selection screen 21, the character data 7 saying “You, I do quite well” is input, and “You” Is replaced with “Onushi”, and “-Wane” at the end of the word is replaced with “-Na”, thereby obtaining text data 8 and voice data 9 of “Onusu, very good”. . In addition, contemporary expressions such as “well done”, “well done” and “well done” can be used as a historical drama-like expression saying “you can do it”.

  Further, for example, when an e-mail (entire) received on the mobile phone 1 as the input device 1 is selected as the character data 7 and a voice actor to be heard is selected from the voice actor list, the e-mail is read out with the voice of the voice actor. Can be. In this case, the text of the e-mail is converted by the conversion processing device 3 installed by the communication service provider so as to be a unique expression of the voice actor.

  In addition, for example, in learning software (software) for young children, when an interest is accompanied by a voice explanation, if the voice is a popular cartoon character (voice actor), the learning effect may be enhanced. It is done. However, it usually only speaks as it was recorded in advance. It is practically difficult to prepare audio for every progress. However, according to the present invention, it is possible to obtain text data 8 and voice data 9 that a cartoon character or the like naturally reads out based on a general sentence.

  FIG. 3A is a character information speech conversion processing flow, and shows the processing of the character information speech conversion method according to the present invention.

  The input device 1 designates or inputs character data 7 to be converted into the conversion processing device 3 in accordance with a user input instruction (step S11). Thereafter, when the conversion processing device 3 displays the voice selection screen 21 on the display screen of the display device 2, the user who sees it selects or inputs one voice type from the screen (step S12). ). In response to this, the conversion processing device 3 uses the speech type expression conversion DB 51 selected in step S12 to extract a character string to be converted consisting of normal expressions from the character data 7 input in step S11. Then, the portion is replaced with a converted character string consisting of a unique expression (step S13), and the converted character data is output. For example, the converted character data (text data 8) is stored in the specific expression output file (step S14).

  4 and 5 are explanatory diagrams of character information speech conversion processing, and show speech determination processing in the character information speech conversion method of the present invention.

  In the speech determination process, the conversion processing device 3 extracts a character string composed of the unique expression from the character data 7 input from the input device 1 and uses the speech determination DB 52 for each type of speech corresponding to the specific expression in advance. The determined points are integrated and output from the output device 4 as the audio data 9 with the highest point type using the audio sample DB 6 (not shown in FIG. 4).

  The input of the character data 7 is directly input from the keyboard 1 or selected from a part of the text of the mobile phone 1 or the electronic book 1 in the same manner as the voice conversion process described above. Here, it is assumed that “one piece was also divided” was entered.

  When the character data 7 is input, the conversion processing device 3 starts the expression conversion processing using the voice determination DB 52. As shown in FIG. 5, the speech determination DB 52 stores expression points for specific expressions (converted character strings) corresponding to normal expressions (converted character strings) for each type of sound. For example, for the type of voice such as the hero A of the comic, the specific expression “Maro” corresponding to “Ore” is 3 points, the specific expression “Tame” corresponding to “Kure” is 2 points, etc. is there. The point is set higher as the unique expression (representing the voice type better) is more characteristic.

  Note that the voice determination DB 52 also stores a voice link and morpheme information about the specific expression, as shown in FIG. The voice link indicates the storage destination address in the voice sample DB 6 of the word (phoneme piece) of the specific expression sampled in advance with the cooperation of the voice actor of the hero A of the comic character who is the type of the voice. The morpheme information indicates a morpheme for the specific expression.

  The conversion processing device 3 uses the voice determination DB 52 to search in order from the beginning of the character data 7, extracts a specific expression (converted character string consisting of), obtains a point about this, and obtains this character data. 7 is integrated. For example, when the character determination 7 that searches for the character data 7 “Maro also has been separated” in the speech determination DB 52, the unique expression “Maro” is first extracted. Therefore, the corresponding point “3 points” and the voice type “Manga hero A (no voice actor)” are obtained, and the point “3 points” is accumulated for this voice type “Manga hero A”. Next, since the proper expression “Tama” is extracted, the corresponding point “2 points” and the voice type “Manga hero A” are obtained, and the point is assigned to the voice type “Manga hero A”. The points are accumulated (counted), and the points are set to “5 points”. As a result, with respect to the character data 7 that says “I was divided into one piece”, the voice type “Manga hero A” is “5 points”, and the other voice type (no voice actor) is “0 points”. Is obtained.

  Thereafter, the conversion processing device 3 outputs the accumulated points or count values (point data 10) for each type of sound. For example, the user is notified that the voice type “Manga hero A” is “5 points” and the other voice type is “0 points”. Thereby, the user can know which (who) the type (for example, voice actor) of the voice suitable for reading the character data 7 is.

  Further, the conversion processing device 3 outputs the input character data 7 as the voice data 9 with the voice type having the highest accumulated point according to the user's instruction. In this case, the conversion processing device 3 uses the audio sample DB 6 of the audio type “Manga hero A (no voice actor)”. Thereby, the user can obtain the sound output (speech data 9) of the character data with the sound type (for example, voice actor) suitable for reading the character data 7. As a result, if the sentence contains expressions unique to the cartoon character, celebrity, voice actor, etc., it can be output in the voice of the cartoon character, celebrity, voice actor, etc., and the character data (text ) Can be output with sound that matches.

  For example, if the e-mail received by the mobile phone 1 as the input device 1 is selected as the character data 7 and the voice actor entrusting mode is set, for example, the voice tone list matches the tone of the e-mail. Voice actors can be selected and read out emails.

  FIG. 3B is another character information speech conversion processing flow, and shows processing of another character information speech conversion method according to the present invention.

  The input device 1 specifies or inputs character information to be converted into the conversion processing device 3 in accordance with a user input instruction (step S21). In response to this, the conversion processing device 3 uses the voice determination DB 52 to extract a specific expression (a character string to be converted) from the character information input in step S21, and to generate a voice corresponding to the specific expression. The predetermined expression points (points) are integrated for each type (step S22), and the integrated point data 10 is output for each type of voice (step S23). Thereafter, if there is an instruction input by the user, the conversion processing device 3 outputs the character information as the voice data 9 in accordance with the voice type having the highest accumulated point (step S24).

  Note that the user can select either the expression conversion process or the voice determination process. For this purpose, for example, the conversion processing device 3 displays a processing selection screen (not shown) on the display screen of the display device 2 prior to the input of character information to be converted by the user from the input device 1. To do. On this process selection screen, the user selects and inputs either the expression conversion process or the voice determination process. In response to this, the conversion processing device 3 starts either the expression conversion process or the voice determination process described above.

  Further, as shown in FIG. 4, the point data 10 for the inputted character data 7 is obtained, and then the character data 7 is obtained by selecting the type of voice having the highest point (voice actor etc.) as shown in FIG. ) May be converted into text data 8 or voice data 9 including a proper expression and output.

As can be seen from the above, the features of the embodiments and examples of the present invention are listed as follows.
(Supplementary Note 1) In a character information speech conversion method in a speech conversion device that converts character information and outputs speech information,
Enter text information that is electronic data,
Select and input the audio type,
Based on the type of speech, extract a converted character string consisting of a normal expression from the character information, and replace the part with a converted character string consisting of a unique expression,
A character information speech conversion method, wherein the converted character information is output as speech.
(Additional remark 2) The character information after the said conversion is output as text data. The character information audio | voice conversion method of Additional remark 1 characterized by the above-mentioned.
(Additional remark 3) The character information of Additional remark 1 characterized by converting the said character string to be converted into the said conversion character string by referring to the audio | voice conversion database which stores the said specific expression corresponding to the said normal expression. Voice conversion method.
(Appendix 4) Means for inputting character information that is electronic data;
Means for selecting and inputting the type of audio;
Means for extracting a converted character string consisting of a normal expression from the character information and replacing the part with a converted character string consisting of a unique expression;
And a means for outputting the character information after the conversion.
(Supplementary Note 5) A program for realizing a character information speech conversion method,
The program is stored in a computer.
A process of inputting character information that is electronic data;
Processing to select and input the type of audio,
A process of extracting a converted character string composed of a normal expression from the character information and replacing the part with a converted character string composed of a unique expression;
And a process for outputting the converted character information. A character information speech conversion program.
(Supplementary Note 6) In a character information speech conversion method in a speech conversion device that converts character information and outputs speech information,
Enter text information that is electronic data,
Extract a character string consisting of a unique expression from the character information,
For the character information, the points predetermined for each type of speech corresponding to the specific expression are integrated,
The accumulated point is output for each type of voice.
(Supplementary note 7) The character information speech conversion method according to supplementary note 6, wherein the character information is output as speech with the type of speech having the highest accumulated point.
(Supplementary note 8) The character information speech conversion method according to supplementary note 6, wherein the point is set to be higher as the characteristic expression is more characteristic.
(Supplementary note 9) means for inputting character information which is electronic data;
Means for extracting a character string comprising a unique expression from the character information;
For the character information, means for accumulating predetermined points for each type of speech corresponding to the specific expression;
And a means for outputting the accumulated points for each type of voice.
(Supplementary Note 10) A program for realizing a character information speech conversion method,
The program is stored in a computer.
A process of inputting character information that is electronic data;
A process of extracting a character string consisting of a unique expression from the character information;
For the character information, a process of accumulating predetermined points for each type of speech corresponding to the specific expression;
A character information-speech conversion program that executes a process of outputting the accumulated points for each type of speech.

  According to the present invention, in the text information speech conversion method, when text data is converted into speech and output, it can be output with a voice according to the content of the text, so that the speech is reproduced with a speech familiar to the user. can do. Therefore, the application of the character information reading system can be expanded.

It is a character information voice conversion method block diagram. It is character information voice conversion processing explanatory drawing, and shows an expression conversion process. It is a character information voice conversion processing flow. It is character information voice conversion processing explanatory drawing, and shows a voice determination process. It is character information voice conversion processing explanatory drawing, and shows a voice determination process.

Explanation of symbols

1 Input device 2 Display device 3 Conversion processing device 4 Output device 5 Conversion processing DB
6 Audio sample DB
7 Character data (character information)
8 Text data 9 Voice data

Claims (3)

In a character information voice conversion method in a voice conversion device that converts character information and outputs voice information,
Enter text information that is electronic data,
Extract a character string consisting of a unique expression from the character information,
For the character information, the points predetermined for each type of speech corresponding to the specific expression are integrated,
The accumulated point is output for each type of voice. The character information speech conversion method according to claim 1, wherein the character information is output as speech with the type of speech having the highest accumulated point. The character information-to-speech conversion method according to claim 1, wherein the point is set to be higher as the characteristic expression is more characteristic.

Images