JPH0863463A - Document reading device - Google Patents

Abstract

(57) [Summary] [Purpose] To read a document naturally in a manner suitable for the context and situation. [Arrangement] The analysis result buffer 7 stores the Japanese analysis result of the specified document in the document data file 1 by the Japanese analysis unit 4. When the voice data generation unit 8 creates voice data from the Japanese analysis result, the special character processing rule table 21 corresponds to the numeric character strings before and after the special character is detected by the special character detection unit 17. When the special pattern detection unit 19 detects a numeric character string of a special pattern by applying a special reading in accordance with the rule, a corresponding character in the special pattern processing rule table 22 is dealt with. According to the rule, a special reading is applied to generate voice data and the voice data is stored in the voice data file 10. The voice synthesizer 11 converts the voice data into a voice signal and outputs the voice signal by the voice output unit 13. Therefore, a numeric character string such as a telephone number or a postal code in the read-aloud document is also read appropriately.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention reads a document by analyzing the reading target document in Japanese, generating voice data, and outputting the voice obtained by synthesizing the voice data to the outside. Regarding the device.

[0002]

2. Description of the Related Art In a conventional speech reading apparatus, in an analysis result obtained by analyzing the reading target document data in Japanese, for example, for a character string of numbers, a bar reading is performed in a preset mode, The voice data is generated by reading either the digit or the digit. As a concrete example, as the analysis result, "03 (123) 456" is obtained.
If “7” is obtained, the voice data generation unit normally responds to “Zerosa ^ // ^^ / hyakuni ^ 30 // ^^ / onse for this numeric character string. It generates a reading "^ / Gohyakukurojana ^ na", which is the customary way of reading when it is a telephone number, "Zerosa ^ no / Ichinii ^ san / Yongo-Rokuna". I didn't generate a reading saying "^".

Also, even if a character string of a number including a symbol for special reading such as "10:13", which has some variations in reading, is obtained as the analysis result, the voice data generating section Depending on the words that appear before and after, it is necessary to distinguish whether "juta ^ i / ju ^ u-san" is "ju ^ uji / ^ jusa ^ mpun", which is either one of the preset settings. I could only read it. Therefore, when reading the document data with the conventional document reading device, if the above example appears, it does not necessarily make a natural reading suitable for the context or scene, which gives the listener a feeling of discomfort. At the same time, there was a problem that listeners sometimes got the meaning wrong. Incidentally, in this example, those including special symbols such as parentheses and ":" in the numeric character string are collectively read as the numeric character string.

[0004]

In the conventional voice reading device as described above, when the Japanese analysis result of the read target document data is a numeric character string indicating a telephone number or a postal code, the time and ratio are set. If it is a numeric character string that includes a special symbol that indicates, only the preset reading is performed, and there are cases where natural reading appropriate for the context or scene is not performed. There is a problem in that the listener feels uncomfortable and the listener sometimes misunderstands the meaning.

In view of the above circumstances, the present invention can always perform natural reading suitable for a context or a scene with respect to a numerical character string that is conventionally and specially read in reading target document data. It is an object of the present invention to provide a document reading apparatus in which the user can arbitrarily set the special reading method.

[0006]

According to a first aspect of the present invention, voice data is generated according to a voice data generation rule from an analysis result obtained by analyzing Japanese of document data to be read aloud, and the voice data is synthesized by a voice synthesizer. First storage means for storing data in which a list of a plurality of special words is used in a document reading device that converts the obtained voice signal into a voice by a voice output device and outputs the voice to the outside. When,
Special word detection means for detecting a special word stored in the storage means from the Japanese analysis result, and a numeric character string existing close to before and after the special word detected by the special word detection means are extracted. Extraction means, second storage means for storing data in which a list of rules determined corresponding to each of the plurality of special words stored in the first storage means is stored, and the extraction means extracts the data. Voice data generation for generating voice data from the numeric character string by applying reading according to the rule stored in the second storage means to the numeric character string corresponding to the special word detected by the detection means And a first registration unit that registers the special word in the first storage unit and the rule in the second storage unit.

According to a second aspect of the present invention, voice data is generated according to a voice data generation rule from an analysis result obtained by analyzing the document data to be read aloud in Japanese, and the voice data is converted into an electric voice signal by a voice synthesizer. In a document reading device which converts the obtained voice signal into a voice by a voice output device and outputs the voice to the outside, a third storage means for storing data listing a plurality of special numeral character string patterns, Corresponding to a special pattern detecting means for detecting the special numeric character string pattern stored in the first storage means from the Japanese analysis result, and a plurality of special numeric character string patterns stored in the third storage means And a special number character string pattern detected by the special pattern detection means and a fourth storage means for storing data in which the rules determined by Voice data generating means for generating voice data from the numeric character string pattern by applying reading according to the rule stored in the fourth storage means corresponding to the character string pattern, and the third storage means. And a second registration means for registering the special numerical character string pattern and the rule in the fourth storage means.

According to a third aspect of the present invention, voice data is generated according to a voice data generation rule from an analysis result obtained by analyzing the document data to be read out in Japanese, and the voice data is converted into an electric voice signal by a voice synthesizer. In a document reading device which converts the obtained voice signal into a voice by a voice output device and outputs the voice to the outside, a first storage means for storing data in which a plurality of special words are listed, and the Japanese language analysis. A special word detecting means for detecting a special word stored in the storage means from the result, and an extracting means for extracting a numeric character string existing before and after the special word detected by the special word detecting means, Second storage means for storing data in which a list of rules determined corresponding to each of the plurality of special words stored in the first storage means is stored; The first numerical character string is converted into voice data by applying reading to the numerical character string according to the rule stored in the second storage means corresponding to the special word detected by the detecting means. Of voice data generation means, first registration means for registering special words in the first storage means and the rules in the second storage means, and a list of a plurality of special numeral character string patterns. Third storage means for storing data, special pattern detection means for detecting the special numeral character string pattern stored in the third storage means from the Japanese analysis result, and the third storage means. Fourth storage means for storing data in which a list of rules determined corresponding to each of the plurality of special numeric character string patterns is stored, and a special numeric character string detected by the special pattern detection means. Voice data generating means for generating voice data from the numeric character string pattern by applying a reading according to a rule stored in the fourth storage means in response to the special numeric character string pattern, The third storage means is provided with a special number character string pattern and a second registration means for registering the rule in the fourth storage means.

[0009]

In the document reading apparatus according to the first aspect of the present invention, the first
The storage means stores data in which a plurality of special words are listed. The special word detecting means detects the special word stored in the storage means from the Japanese analysis result. The extracting means extracts a numeric character string existing before and after the special word detected by the special word detecting means. The second storage means stores data in which a list of rules determined corresponding to each of the plurality of special words stored in the first storage means is listed. The voice data generating means applies the reading according to the rule stored in the second storing means to the numeric character string extracted by the extracting means in correspondence with the special word detected by the detecting means. Generates voice data from numeric character strings. The first registration means registers the special word in the first storage means and the rule in the second storage means.

In the document reading apparatus of the invention of claim 2,
The third storage means stores data in which a plurality of special numeric character string patterns are listed. The special pattern detection means detects the special numeric character string pattern stored in the third storage means from the Japanese analysis result. The fourth storage means stores data as a list of rules determined corresponding to each of the plurality of special numeral character string patterns stored in the third storage means. The voice data generating means applies the reading in accordance with the rule stored in the fourth storage means to the special numeral character string pattern detected by the special pattern detecting means in correspondence with the special numeral character string pattern. Voice data is generated from the numeric character string pattern. The second registration means registers the special numeral character string pattern in the third storage means and the rule in the fourth storage means.

In the document reading apparatus of the invention of claim 3,
The first storage means stores data in which a plurality of special words are listed. The special word detecting means detects the special word stored in the storage means from the Japanese analysis result. The extracting means extracts a numeric character string existing before and after the special word detected by the special word detecting means. The second storage means stores data in which a list of rules determined corresponding to each of the plurality of special words stored in the first storage means is listed. The first voice data generation means applies the reading according to the rule stored in the second storage means to the numeric character string extracted by the extraction means corresponding to the special word detected by the detection means. As a result, voice data is generated from the numeric character string. The first registration means registers the special word in the first storage means and the rule in the second storage means. The third storage means stores data in which a plurality of special numeric character string patterns are listed. The special pattern detection means detects the special numeric character string pattern stored in the third storage means from the Japanese analysis result. The fourth storage means stores data as a list of rules determined corresponding to each of the plurality of special numeral character string patterns stored in the third storage means. The voice data generating means applies the reading in accordance with the rule stored in the fourth storage means to the special numeral character string pattern detected by the special pattern detecting means in correspondence with the special numeral character string pattern. Voice data is generated from the numeric character string pattern. The second registration means registers the special numeral character string pattern in the third storage means and the rule in the fourth storage means.

[0012]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing an embodiment of the document reading apparatus of the present invention. Reference numeral 1 is a document data file storing document data in a form that can be handled on a computer, 2 is an input device for inputting various setting data at the time of reading, and 3 is a control unit for performing comprehensive control when reading the document data. 4, morphologically refers to the document data to be read out by referring to the word dictionary 6,
A Japanese analysis unit for syntactically and semantically analyzing, 5 is a setting buffer in which various setting data at the time of reading are stored, 6 is a heading, part of speech, reading, accent, meaning, and other information for analyzing document data Is a word dictionary collected as a list, 7 is an analysis result buffer for storing the analysis result of the Japanese analysis unit 4, and 8 is voice data generation for generating voice data corresponding to the analysis result of the Japanese analysis unit 4. Department,
Reference numeral 9 is a voice data generation rule file storing a voice data generation rule referred to when voice data is generated by the voice data file 10, and 10 is a voice data generation unit 8
A voice data file for storing the voice data generated by, 11 is a voice synthesizer for regularly synthesizing voice signals based on the voice data read from the voice data file 10, and 12 is a "zip code" or "ratio, etc." A special character table that holds a list of special characters that read the numeric character string that follows these characters in a special way, such as
3 is an audio output unit such as a speaker that outputs an audio signal, and 14
Is a display device such as a CRT or LCD for displaying the display data on the screen, 15 is a display data creating section for creating the display data to be displayed on the display device 14 from audio data, 16 is a display data file for saving the display data, 17 Is a special character detection unit for detecting special characters held in the special character table 12 from the Japanese analysis result, and 18 is a list of special numeric character string patterns such as numeric character strings indicating telephone numbers. The special pattern table 19 includes a special pattern detecting unit 19 for detecting the special pattern held in the special pattern table 18 from the Japanese analysis result, and 20.
Is a special numeric character processing unit for reading out the rule information in the special character processing rule table 21 or the special pattern processing rule table 22 and processing the special numeric character processing unit 21 for processing the voice data for the special numeric character string. A special character processing rule table holding a list of voice data generation rules for special characters, 22 is a special pattern processing rule table holding a list of voice data generation rules for the patterns of the special numeric character strings, 23 Is a confirmation data generation unit for generating confirmation data for confirming the special characters and the special patterns and the special reading rules registered by the operator in the special character table 12 and the special pattern table 18.

Next, the operation of this embodiment will be described. First, before using the document reading apparatus shown in FIG. 1, the operator registers in advance how to read the numeric character string for special reading. When the control unit 3 receives an operator's registration instruction from the input device 2, the control unit 3 sets the device to the registration mode and displays a special character registration screen as shown in FIG. Looking at this screen, the operator inputs “〒” representing a postal code as a special character from the input device 2 into the control unit 3, and the control unit 3 displays this “〒” on the screen of the display device 14 as shown in FIG. To display. After that, the operator reads from the input device 2 a special reading rule that "-" in the numeric character pattern following "" is read as "no" and the numeric part is read as a stick. As a result, the control unit 3 displays the special reading rule regarding the numeric character pattern on the screen of the display device 12 as shown in FIG. However, the special character is, for example, a postal code that limits the reading of the numerical character pattern before and after this character, a character such as a telephone, or a symbol representing these.

At the same time that the control unit 3 performs the above-mentioned display processing, the input "" is displayed in the special character table 12 as shown in FIG.
The special processing rule table 2
In order to attach a link with 1, a connector called rule A as shown in FIG. 13 is generated. After that, the control unit 3 sets the special reading rule input next to the special character processing rule table 21.
As shown in FIG. 14, it is registered by using the connector of the rule A.

When the special characters have been registered, the control unit 3 displays a special numeral pattern registration screen as shown in FIG. 3 on the display device 14. Looking at this screen, the operator inputs a "numeral (numeral) number" as a special numeral pattern from the input device 2 to the controller 3, and the controller 3 displays this numeral (numerical number) on the screen of the display device 14. Display as shown in. After that, the operator reads "(" and ")" in the number pattern as "no" and inputs a special reading rule that the number portion is read as a stick from the input device 2. As a result, the control unit 3 displays the special reading rule regarding the numeric character pattern on the screen of the display device 12 as shown in FIG. However, the special numeric pattern is a numeric character string that is read specially, such as a telephone number.

At the same time that the control section 3 performs the above-mentioned display processing, the inputted "numeric (numeric) numeral" is registered in the special character pattern table 18 as shown in FIG.
In order to link with the special pattern processing rule table 22, a connector called rule AP as shown in FIG. 16 is generated. After that, the control unit 3 registers the special reading rule to be inputted next in the special pattern processing rule table 22 using the connector called the rule AP as shown in FIG.

After the registration as described above, the control unit 3 activates the confirmation data generation unit 23 when receiving an instruction from the input device 2 to confirm the registration rule from the operator. The confirmation data generation unit 23 refers to the special character table 12 and the special processing rule table 21 for the special reading rules related to this, for example, “〒” registered by the operator as described above, and the confirmation data as shown in FIG. Is generated and sent to the control unit 3. The control unit 3 performs the same processing as the reading of a normal document, which will be described later, and reads it from the voice output unit 13, so that the operator can confirm the registered content. It should be noted that the confirmation data generation unit 23 selects the appropriate number from the numerical data held therein when the confirmation data is created, so that the confirmation data generation unit 23 shown in FIG.
Numbers such as 3 and 456 are automatically generated.

Next, the document reading operation of the document reading apparatus shown in FIG. 1 will be described with reference to the flowchart shown in FIG. The document data stored in the document data file 1 is a plurality of documents stored in a form that can be processed by a computer, and these document data are created by a document creation device such as a Japanese word processor or by a computer such as OCR. It has been read in.

When the control unit 3 receives an instruction from the input device 2 such as a keyboard, the document reading process is started. At this time, the control unit 3 is given an instruction from the input device 2 by an operator to specify a document to be read aloud and a condition for reading the document. The operator can set this work by the control unit 3 while following the guide displayed on the display device 14 such as a CRT or LCD.

In response to the operation of the operator as described above,
The control unit 3 reads the document designated by the input device 2 from the document data file 1 in step 501 of FIG.
A process of selecting a document to be read is performed, and the selected document is passed to the Japanese analysis unit 4. Next, the control unit 3 performs step 502.
The reading condition input from the input device 2 is written in the setting buffer 5. Here, a part of the document data designated by the input from the operator's input device 2 is as shown in FIG. 6, for example. Further, the operator can set the reading condition from the input device 2 while the control unit 3 follows the guide displayed on the display device 14. The settings include basic reading speed, sound quality, Height, strength, set time for reading end, presence / absence of special reading of emphasized characters, changes during special reading of emphasized characters, presence / absence of reading, rest length,
Whether or not the reading of special characters has been changed, etc., the condition data is stored in the setting buffer 5 as shown in FIG.

A Japanese analysis unit 4 which receives an instruction from the control unit 3.
Is a word dictionary 6 containing morphologically, syntactically, and semantically-analyzed the received document in step 503, and including word morphological information, reading information, accent information, co-occurrence information between words, and the like. The document is divided into words, divided into words, and the analyzed result is written in the analysis result buffer 7, and then the control unit 3 is informed that the document analysis is completed. Send a signal to indicate.

Here, the word dictionary 6 used by the Japanese analysis unit 4 has a data structure example as shown in FIG.
The analysis result buffer 7 in which the analysis result by the Japanese analysis unit 4 is stored has an example of data structure as shown in FIG. When the Japanese analysis unit 4 analyzes the document and guides the reading, and when there are a plurality of readings for one word, the co-occurrence information described in the word dictionary is used. To determine the appropriate reading.

Upon receiving the signal indicating that the analysis of the document is completed, the control unit 3 activates the voice data generation unit 8. The voice data generation unit 8 refers to the data in the voice data generation rule file 9 to generate voice data corresponding to the Japanese analysis result in the analysis result buffer 7, and stores this in the voice data file 10. At this time, the voice data generation unit 8 refers to the special character table 12 via the control unit 3 and registers the Japanese analysis result in the analysis result buffer 7 in the special character table 12 as shown in FIG. Step 50: Check if there are any special characters (words)
4, the special character table 1 if it exists
After the rule (connector) corresponding to the searched special character in 2 is read, the process proceeds to step 507, and if it does not exist, the process proceeds to step 505.

When the voice data generation unit 8 proceeds to step 507, it extracts the numeric character strings before and after the detected special character from the Japanese analysis result, and extracts the numeric character string and the special character table. The rule read from 12 is given to the special numeric character processing unit 15 via the control unit 3 to activate it. As a result, the special numeric character processing unit 20 reads the rule corresponding to the given rule from the data in the special character processing rule table 21 as shown in FIG. 14 through the control unit 3 in step 508. The audio data generation unit 8
Give to. The voice data generation unit 8 generates voice data by adding readings and accents in accordance with the rules corresponding to the given number character string in step 509.

On the other hand, the voice data generation unit 8 performs step 50.
When the process proceeds to step 5, the special pattern table 17 as shown in FIG. 16 is referred to via the control unit 3, and the special pattern table 1 is included in the Japanese analysis result in the analysis result buffer 7.
It is determined in step 505 whether or not the special pattern registered in No. 8 exists, and if it exists, the rule corresponding to the searched special pattern in the special pattern table 17 is read out, and then in step 506. If it does not exist, the process proceeds to step 509. When the voice data generation unit 8 proceeds to step 506, the rule read from the special pattern table 18 via the control unit 3 is given to the special numeric character processing unit 20 via the control unit 3 to activate it. Call. As a result, in step 508, the special numeric character processing unit 20 sends the rule corresponding to the given rule in the data in the special pattern processing rule table 22 having the structure shown in FIG. 17 via the control unit 3. Read out, and this is read out by the voice data generation unit 8
To the controller via the control unit 3. The voice data generation unit 8 generates voice data by adding a reading and an accent in accordance with the rule corresponding to the detected special numeral character string in step 509.

Next, the specific processing contents of the above steps 504 to 509 will be described. For example, in the case where "postal code" is not registered in the special character table 12 as a special character string for the sentence "His postal code is 123-45" as shown in the upper part of FIG. The reading "123-45" in the row is given as "Hyaku ni ^ 13 / san / mainasu / yo ^ ju / go".
"Postal code" is a special character table 1 as shown in FIG.
When registered in No. 2, the special character detecting unit 17 detects "zip code" as a special character, the special numerical character processing unit 20 is activated, and the special numerical character processing unit 20 performs special character processing. The reading is generated with reference to rule 21. In this example, the special character processing rule 21 describes a rule that the adjacent numbers are read as sticky readings, and the reading of "no" is given to "-". 12 is read as "Ichinii ^ san / san / gongo ^-" as shown in the lower part of FIG.

Further, the character string "0" as shown in the upper part of FIG.
3 (123) 4567 ”in the document, the special pattern table 18 referred to by the special pattern detection unit 19
When the pattern that corresponds to is not registered, "Zerosa ^ / / ^ kko / Hyaku ni ^ san / ka ^ kko /
"Yonsei / Goyakurokujana" is added. However, if the special pattern table 18 having the structure as shown in FIG. 16 has a registration of "numeral (numeral) numeral", the special character detection unit 17 collates the patterns and the input character string is converted into the special pattern table. If it is in the data in 18, the special numeric character processing unit 20
Is started, and the special numeric character processing unit 20 is activated as shown in FIG.
The reading is generated by referring to the special character processing rule table 21 as shown in FIG. In this example, in the special character processing rule table 21, the adjacent numbers are read as stick readings,
There is a rule that applies "no" to "(" and ")". According to this rule, the reading for the input character string is "zero" Good-good! ” Therefore, the character string "03 (12
3) The reading given to "4567" is as shown in the lower part of FIG.

Similarly, "10: 0" in the reading target document
For the character string "0", the special pattern table 1
If the pattern "Numeric: Numerical" is registered in 8, the special pattern detector 19 detects the pattern "Numeral: Numerical" by comparing the character string with the pattern, and the special numeral character processor 20 To start up. As a result, the special numeral character processing unit 20 refers to the data in the special pattern processing rule table 22 to generate the reading. In this example, ":" stands for ":"
There is a rule that you can read "Jun" and "Fun" after the number in the back, and it will be read "Juujiuji / Zerozero ^ fun". Incidentally, in this example, the reading "ju ^ uji / zero ^ un" or "ju ^ uji" can be generated according to the rules described in the special character processing rule table 21. Voice data creation unit 8
Will generate voice data in response to the above reading in step 209.

If there is a character string that matches both the special character detecting unit 17 and the special pattern detecting unit 19 as a numeric character string sent to the special numeric character processing unit 20, the rule of the special character detecting unit 17 is set. Prioritize. For example, regarding the sentence “the ratio is 10:13”, if the numeric character string “10:13” is registered in the data in the special pattern table 18 as “number: number”, the special pattern detection unit 19 When the input character string matches the special pattern data, the special numeric character processing unit 20 is activated, and the special numeric character processing unit 20 refers to the data of the special pattern processing rule table 22. Then, the reading is generated. In this example, the rule is to put the reading "ji" for ":" and add the reading "fun" after the number after it, which is called "ju ^ uji / jusa ^ mpun". Be read. The voice data creation unit 8 will create voice data for the above reading in step 509.

However, the "ratio" is displayed in the special character table 12.
If is registered, the special character detection unit 17 detects the “ratio” as a special character from the special character table 12, and the special numeric character processing unit 20 is activated. The reading is generated with reference to the character processing rule table 21. In this example, the special character processing rule table 21 describes a rule that the adjacent numbers are read as stick readings and "tai" is read for ":".
The reading for "0:13" will be "Jutta ^ i / Ju ^ san", and the whole reading will be "the secret
You can get the reading "I / Ju U-san / Aru".
In such a case, as described above, the reading obtained by the detection by the special character detection unit 17 is prioritized, so that the voice data generation unit 8 is "the secret is / 13 ^ / / The readings “Ru” are adopted, and voice data for these readings is created in step 509.

In the case where the detection of the special character and the detection of the special pattern described above occur simultaneously for the same numeric character string, the priority order can be preset in the control unit 3 from the input device 2. Therefore, the control unit 3 sets this priority in the voice data generation unit 8 so that the above processing is performed. Therefore, if the priorities are set in the control unit 3 in reverse, the special pattern detection unit 19
The voice data generation process by the detection of is prioritized and executed.

The voice data generator 8 has an analysis result buffer 7
For a portion of the Japanese analysis result data that is not a special character or a special pattern, the voice data generation rule file 9 is referred to in step 508, and then the voice data file 10 is generated. The voice data is generated for the reading applied to, and stored in the voice data file 10. When the creation of the audio data is completed, the audio data generation unit 8 sends a signal indicating that the creation of the audio data is completed to the control unit 3.

Here, a part of the voice data generation rule is shown in FIG.
The audio data file 10 shown in FIG.
Shown in FIG. 10 shows an example of a rule in which the accent form is not O-type in the case of a five-verb, and the accent form is O-type when the inflectional form is incomplete. Also, FIG.
Shows the format of the audio data file 10. However, in the reading character string data, katakana characters represent voice data, “^” represents the position of accent, and “.” Represents a break of the length set in the setting buffer 5.

Upon receiving the signal indicating that the voice data creation is completed, the control section 3 transfers the voice data in the voice data file 10 to the voice synthesizer 11. The voice synthesizer 11 sets the speed set in the setting buffer 5 in step 510,
A voice is output from the voice output unit 13 such as a speaker by converting the voice data into an electric signal according to sound quality, height, and strength. Here, the speech synthesizer 11 includes a phoneme example,
It is a device for converting data, which is composed of a special control code, into an electric voice signal, and the data has the same format as the voice data in the voice data file 10. That is, when the voice synthesizer 11 receives a character string in the format of the voice data file 10, it can be said that the voice synthesizer 11 is capable of performing regular voice synthesis. Rule composition is performed on the incoming character string.

The document is read aloud by a series of processes of steps 503 to 510 shown in FIG. The control unit 3 determines in step 511 whether or not the reading target document has been read to the end. If not, the process returns to step 503, and if the reading has ended, the process ends.

According to the present embodiment, when the voice data is created from the Japanese analysis result, the digit string and the normal digit reading which are not digit-reading such as telephone numbers and postal codes are used. The numeric character string to be performed is identified, and for the numeric character string to be read aloud in a special way, the pattern of this numeric character string, or the telephone number or zip code before and after this numeric character string, etc. Since the special characters can give a reading suitable for the context or scene, it is possible to always read appropriately the numerical character string as described above. As a result, when special characters such as "(,)" and "-" are adjacent to numbers that meet the conditions,
"Zerosan's / Ichinii's / Japanese-Good
Such as `` na '' etc., it is possible to realize natural document reading suitable for reading phone numbers and zip codes. The performance of the device can be improved. Moreover, since the operator can arbitrarily register the pattern of the numerical character string and the special reading rules and special characters and special reading rules related thereto, depending on the type of the reading target document and the circumstances of the operator side,
The special numeric character string as described above can be freely determined, and the special way of reading can also be freely determined, so that the degree of freedom when reading a document can be further improved.

[0037]

As described above, according to the document reading apparatus according to the first to third aspects, the numerical character string which is conventionally read specially in the reading target document data is always suitable for the context and the scene. Natural reading can be performed, and the user can arbitrarily set the special reading.

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment of a document reading apparatus according to the present invention.

FIG. 2 is a diagram showing an example of a registration screen for registering special characters displayed on the display device shown in FIG. 1 and special reading rules related thereto.

FIG. 3 is a diagram showing an example of a registration screen for registering a special numeral pattern displayed on the display device shown in FIG. 1 and a special reading rule related thereto.

FIG. 4 is a diagram showing an example of data for confirming the registered content generated by the confirmation data generating unit shown in FIG.

5 is a flowchart showing a document reading process of the apparatus shown in FIG.

6 is a diagram showing a part of the document data in the document data file shown in FIG.

7 is a diagram showing an example of contents of a setting buffer shown in FIG.

8 is a diagram showing an example of the structure of the word dictionary shown in FIG.

9 is a diagram showing an example of contents of an analysis result buffer shown in FIG.

10 is a diagram showing an example of data in the voice data generation rule file shown in FIG.

11 is a diagram showing an example of audio data in the audio data file shown in FIG.

FIG. 12 is a diagram showing an example of special character in a document and audio data generated by applying a special character processing rule.

13 is a diagram showing an example of special characters in the special character table shown in FIG.

14 is a diagram showing an example of special character processing rules in a special character processing rule buffer shown in FIG.

FIG. 15 is a diagram showing an example of special patterns in a document and audio data generated by applying special pattern processing rules.

16 is a diagram showing an example of a special pattern in the special pattern table shown in FIG.

17 is a diagram showing an example of a special pattern processing rule in the special pattern processing rule buffer shown in FIG.

[Explanation of symbols]

1 ... Document data file 2 ... Input device 3 ... Control unit 4 ... Japanese analysis unit 5 ... Setting buffer 6 ... Word dictionary 7 ... Analysis result buffer 8 ... Voice data generation unit 9 ... Voice data generation rule file 10 ... Voice data file 11 ... Voice synthesizer 12 ... Special character table 13 ... Voice output unit 14 ... Display device 15 ... Display data generation unit 16 ... Display data file 17 ... Special character detection unit 18 ... Special pattern table 19 ... Special pattern detection unit 20 ... Special Numerical character processing unit 21 ... Special character processing rule table 22 ... Special pattern processing rule table 23 ... Confirmation data generation unit

Claims (3)

[Claims] 1. A voice data is generated according to a voice data generation rule from an analysis result obtained by performing Japanese analysis on document data to be read out, and this voice data is converted into an electric voice signal by a voice synthesizer to obtain the voice data. In a document reading device for outputting the obtained voice signal as voice by a voice output device to the outside, first storage means for storing data in which a plurality of special words are listed, and the storage means from the Japanese analysis result. A special word detecting means for detecting a special word stored in the special memory, an extracting means for extracting a numeric character string existing before and after the special word detected by the special word detecting means, and the first memory. The second storage means for storing data as a list of rules determined corresponding to each of the plurality of special words stored in the means, and the numerical character string extracted by the extraction means. Voice data generation means for generating voice data from the numeric character string by applying reading according to the rule stored in the second storage means corresponding to the special word detected by the note detection means; A document reading device comprising: a first storage unit for registering a special word in the first storage unit and a first registration unit for registering the rule in the second storage unit. 2. A voice data is generated according to a voice data generation rule from an analysis result obtained by performing Japanese analysis on document data to be read out, and this voice data is converted into an electric voice signal by a voice synthesizer, and the voice data is obtained. In a document reading device for converting the obtained voice signal into a voice by a voice output device and outputting it to the outside, a third storage means for storing data listing a plurality of special numeric character string patterns, and the Japanese analysis result The special pattern detecting means for detecting the special numeric character string pattern stored in the first storage means and the plurality of special numeric character string patterns stored in the third storage means are determined in correspondence with each other. Fourth storage means for storing data in which rules are listed, and special numeric character string patterns detected by the special pattern detection means are paired with the special numeric character string patterns. Accordingly, the voice data generating means for generating voice data from the numeric character string pattern by applying the reading according to the rule stored in the fourth storage means, and the special numeric character in the third storage means. A document reading device comprising: a second registration unit that registers a row pattern and registers the rule in the fourth storage unit. 3. A voice data is generated according to a voice data generation rule from an analysis result obtained by analyzing the document data to be read out in Japanese, and this voice data is converted into an electric voice signal by a voice synthesizer to obtain the voice data. In a document reading device for outputting the obtained voice signal as voice by a voice output device to the outside, first storage means for storing data in which a plurality of special words are listed, and the storage means from the Japanese analysis result. A special word detecting means for detecting a special word stored in the special memory, an extracting means for extracting a numeric character string existing before and after the special word detected by the special word detecting means, and the first memory. The second storage means for storing data as a list of rules determined corresponding to each of the plurality of special words stored in the means, and the numerical character string extracted by the extraction means. First voice data generation means for generating voice data from the numeric character string by applying a reading in accordance with a rule stored in the second storage means corresponding to the special word detected by the note detection means. A first registration means for registering a special word in the first storage means and the rule in the second storage means; and a data storing list of a plurality of special numeral character string patterns. 3 storage means and the third from the Japanese analysis result
A list of special pattern detecting means for detecting the special numeric character string pattern stored in the storage means and a rule determined corresponding to each of the plurality of special numeric character string patterns stored in the third storage means. And a rule stored in the fourth storage means corresponding to the special numeric character string pattern in the special numeric character string pattern detected by the special pattern detection means. Voice data generating means for generating voice data from the numeric character string pattern by applying the reading according to the above, and a special numeric character string pattern is registered in the third storage means and the rule is stored in the fourth storage means. And a second registration means for registering the document reading device.