JP2002027177A - Voice and image processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the input method of voice data in the case of requesting generation of an image sheet with voice. SOLUTION: The voice and image processor provided with a code conversion section 40 that converts a voice data into a voice code image coded so as to be optically readable and with a print section that prints out the voice code image and an image based on image data to generate an image sheet with a voice, is provided with a text input processing section 23 that processes received text data and generates a voice code image to reproduce a voice of the text data based on the text data processed by the text input processing section.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a code conversion unit for converting audio data into an audio code image coded so as to be optically readable, and the audio code image for producing an image sheet with audio. And a voice / image processing apparatus having a printing unit for printing an image based on image data.

[0002]

2. Description of the Related Art In recent years, in the era of multimedia, it has been actively attempted to utilize not only visual transmission but also audio transmission of information.
In particular, a photograph with sound is one of such attempts. For example, Japanese Patent Application Laid-Open No. Hei 6-231466 and Japanese Patent Application Laid-Open No. 7-181606 disclose sound in addition to figures, photographs, and characters. An image sheet with sound is disclosed in which a dot code (voice code image) that has been optically readable is printed on the same sheet of paper, and sound is heard by a scanner dedicated to reading the dot code. Such image sheets with sound can be used as language teaching materials, especially for studying pronunciation repeatedly, photographic pictorial books containing the sounds of animals, picture books with sounds, weddings, coming-of-age ceremonies,
It is applied as a photo that records a commemorative event such as Shichigosan with audio accompanying the event.

[0003]

Further, recently, a message in which a voice-coded message is added to an appropriate photograph has been attracting attention as a new message card. When making a request to a DP shop or the like, it is necessary not only to submit a photographic film containing images to be printed or a recording medium of a digital camera but also to blow a voice message through a microphone at a store. This is a rather embarrassing act for ordinary people, regardless of the content of the message, and for this reason many people hesitate to create a message card. To avoid in-store voice messages,
You may bring a cassette tape or MD into which a voice message has been previously blown at home, but it is often played back for confirmation, and it is troublesome to record at home each time for a simple message. In view of the above situation,
An object of the present invention is to improve a method of inputting audio data when requesting a creation of an image sheet with audio.

[0004]

In order to solve the above-mentioned problems, a code converter for converting audio data into an audio code image coded so as to be optically readable, and an image sheet with audio are created. A voice / image processing apparatus having a printing unit for printing an image image based on the voice code image and image data, the present invention provides a text input processing unit for processing input text data, and A voice code image for reproducing the voice of the text data is generated based on the text data processed by the input processing unit.

[0005] In this configuration, since the source data of the voice code image necessary for creating the image sheet with voice is used in the form of text data, the customer does not need to blow the message content by voice. As the input of the text data, for example, a message content may be directly input by using a keyboard connected to the voice / image processing apparatus, or a message prepared in advance by using a word processor or the like may be input to a floppy (registered trademark)
Or the like, and may be brought to a store. Furthermore, it is also possible to send the contents of the message to the store via e-mail. At this time, if the image data for the image sheet with sound to be created is sent as an attached file, the customer can order the image sheet with sound. No longer have to go to the store.

In a preferred embodiment of the present invention, there is provided a voice synthesizing section for generating synthetic voice data based on input text data, and the code converting section converts the synthetic voice data generated by the voice synthesizing section. It is configured to be used as source audio data for the audio code image.

[0007] In this configuration, as speech data necessary to create an image sheet with speech, speech data which is converted into synthesized speech data by using speech synthesis technology from text data first input is used. Again, the customer does not need to speak out the message content.

In a preferred embodiment of the present invention, as an example of a speech synthesizer, the input text data is analyzed by using a text analysis dictionary to identify its reading and further set by accent and prosody. A text-to-speech synthesis unit that generates synthesized speech data from the synthesized phoneme sequence using a synthesized speech element dictionary. In this configuration, a text analysis dictionary is created for text data entered using a keyboard, reading text data mixed with kana-kanji characters, text documents stored on storage media, or text documents sent via e-mail. A certain tone can be set by adjusting the power and the fundamental frequency of the speech through the process of editing the prosodic parameters while accessing the synthesized speech element dictionary while giving the pronunciation and the phrase accent. Therefore, the final synthesized voice data can be created by selecting a female tone, a male tone, an angry tone, or a joy tone according to the customer's request. In this regard, as a more preferable form, if the synthesized speech element stored in the synthesized speech element dictionary is created based on real voice data registered for each individual, the synthesized voice is familiar and similar to the real voice of the customer. It can also be voice.

The above-described text-to-speech synthesizing unit requires a high level of technology, and imposes a heavy burden on equipment and operation. In another embodiment, a voice editing / synthesizing unit is provided which sequentially converts input text data into synthesized voice data in a fragmentary manner using a registered voice element dictionary storing real voice data of vocabulary and phrases registered in advance. There is something. This is a method called editing and synthesis that generates sentence speech from fragments of the real voice with limited vocabulary and phrases. Generation of synthetic speech data is performed by registering text data fragments using a registered speech element dictionary. Therefore, high-speed processing can be performed and the apparatus cost can be reduced.

According to the present invention, in order to be able to listen to synthesized voice data of lower quality than the real voice obtained by such editing and synthesis with more familiarity, the registered real voice registered in the registered voice element dictionary is used. It is proposed to store the data. In other words, the minimum required audio elements for editing and synthesizing are registered in advance by the customer's own voice for the customer of the image sheet with sound. When ordering an image sheet with voice, submit text data and appropriate image data as the source of the voice message, and synthetic voice data will be created by editing and synthesizing using the registered voice element of the person, so the voice that flows fluently At least, since the real voice fragment is used, it will be reproduced as a familiar sound.

Further, as a preferred embodiment of the present invention, if the voice synthesizing unit includes a voice quality changing unit for changing the voice quality of the synthesized voice data, it is possible to generate voice data that does not exist in the world. This is particularly suitable for the purpose of exchanging image sheets with sound in a play-like manner. Such sound quality modification can be easily implemented by, for example, linearly converting the frequency of audio data. At this time, if the parameters of the sound quality deformation are managed for each customer, the customer can secure the voice data deformation parameter having the unique voice characteristic for himself / herself.

[0012] As a measure for customers who do not want to directly type message contents using a keyboard,
In one preferred embodiment of the present invention, a character recognition device is additionally provided, and the text data output by the character recognition device is used for voice code image conversion. Here, the character recognition device is a generic name of a device that reads a character handwritten on a sheet by OCR and converts it into text data, or reads a character written with a predetermined pen on a touch panel and converts it into text data. The method of inputting audio data when requesting the creation of an image sheet with audio is further simplified, and the input form is diversified.

As is apparent from the above description, an important feature of the present invention is to convert text data into speech. However, the text data handled in the present invention includes characters and numerals as printed text. -In a broad sense, as represented by a collection of symbols, data read by a scanner for printed matter, etc., a collection of characters, numbers and symbols as digitized text, and a group of character codes sequentially input through an input device. It should include all data that should be construed and recognized in some way as character information in computer media conversion technology. Other features and advantages according to the present invention will become apparent from the following description of embodiments with reference to the drawings.

[0014]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS One embodiment of an audio / image processing apparatus according to the present invention for producing an image sheet with audio is shown by the external view of FIG. 1 and the functional block diagram of FIG. The core of the audio / image processing apparatus is a general-purpose computer 1, which constructs various functions required for creating the image sheet with audio shown in FIG. 2 by hardware and software. This voice
The image processing apparatus is of a type that is arranged in a store such as a DP shop and performs a service of creating a photograph with sound at the request of a customer.

Various input devices and output devices are connected to the computer 1 via an I / O interface unit 10. As an output device, a silver halide photographic printer 3 (which is also used for printing a silver halide photographic film or the like) is used as a print unit for finally outputting a photograph 2 with sound as an image sheet with sound. The monitor 4 includes a monitor 4 for confirming an image inside and a speaker 5 for checking input audio data. The input devices include a microphone 6a and a cassette player 6b for directly inputting sound to the computer 1, and a card reader 7 for capturing an image captured by a digital camera.
a and a film scanner 7b for taking in a photographed image from a silver halide film. Further, as a device for inputting text data into a computer, a keyboard 8a, a flatbed scanner 8c for reading handwritten or printed characters, and a communication device 8d for receiving text data transmitted via the Internet
Is mentioned.

Also, a floppy drive 8e or MO which is often used for inputting / outputting audio data and image data is used.
The drive 8f is also built in the computer 1. The keyboard 8a is used together with the mouse 8b to give commands to the respective functions shown in FIG. 3, and the communication device 8d can receive not only text data but also image data.

The mechanism for creating the photograph 2 with sound using the input image data and sound data will be described later in detail. For the photograph 2 with sound output from the silver halide photographic printer 3, as shown in FIG. When a dedicated reading scanner 90 scans the voice code image area 2b arranged around the photographic image area 2a, the reading scanner 9
The audio signal corresponding to the audio code image is output by the operation of the audio reproducing circuit built in the audio device 0, and the sound can be heard with the earphone 91 or the like.

As shown in FIG. 2, the audio / image processing apparatus includes, as main functional units, an image input processing unit 21 for receiving image data as a source of a photographic image in the photograph 2 with sound, a photograph with sound, 2, a voice input processing unit 22 for directly receiving voice data as a source of a voice code image from the outside, a text input processing unit 23 for receiving text data to be a source of voice data to be converted to a voice code image, an input text A voice synthesizing unit 30 that generates synthesized voice data based on the data, a code converting unit 40 that converts the voice data into a voice code image coded so as to be optically readable, an image data storage unit 51, a voice code image The storage unit 52, and appropriately processed image data and audio code image And an image voice synthesizing section 60 for generating print data for speech with photos 2 and a.

The image input processing unit 21 includes an image editing unit 21a
And an image selection unit 21b, and a card reader 7a,
Image data input from the film scanner 7b, the communication device 8d, the floppy drive 8e, the MO drive 8f, and the like are selected by the image selection unit 21b as necessary,
The image editing unit 21a performs editing processing such as color tone correction and resolution conversion on the selected image data.

The audio input processing unit 22 is used when audio data as a source of an audio code image formed in the photograph 2 with audio is directly supplied from a customer, and includes a microphone 6a, a cassette player 6b, Voice data input from the card reader 7a (when using a digital voice recorder memory card) or the like can be
Selected by the audio selection unit 22b, the audio editing unit 22a
Performs the editing process.

The text input processing unit 23 is used when a customer gives text data as a source of a voice code image formed in the photograph 2 with voice, and is a text file stored on a floppy disk brought by the customer. After the text data sent in the form of an e-mail or the like is fetched through the floppy drive 8e or the communication device 8d, the text editing unit 23a performs necessary text editing. Further, text data directly input by the customer or the operator through the keyboard 8a is also processed by the text editing unit 23a. Further, as an option, a character recognizing unit 24 can be provided to have an OCR function. When the OCR function is provided, the message document presented by the customer is sent to the flatbed scanner 8.
After being read by c, the character recognition unit 24 converts the data into text data. That is, the flatbed scanner 8
c and the character recognition unit 24 constitute a character recognition device.

A speech synthesizer 30 for converting text data subjected to necessary editing processing by the text input processor 22 into synthesized speech data includes a text speech synthesizer 31, a text analysis dictionary 32, and a synthesized speech element dictionary 33. The text-to-speech synthesizing unit 31 analyzes the input text data using the text analysis dictionary 32 to identify the reading of the input text data, and further sets the accent and prosody to obtain the synthesized speech element dictionary 3 from the phoneme sequence obtained.
3 is used to generate synthesized speech data. Note that the voice as the source of the synthesized voice element dictionary 33 may be either a female voice or a male voice, but it is also possible to select and provide both voices. Furthermore, a configuration is also possible in which a number of synthesized speech element dictionaries 33 that use the voice of a specific person as a source are prepared and arbitrarily switched to be used.

Further, the voice synthesis section 30 is also provided with a voice quality deformation section 34 for deforming the voice quality of the synthesized voice data created as described above. In addition, by performing linear transformation of the frequency by up / down sampling and time axis adjustment, a modification similar to the fast or slow rotation of the tape recorder is performed and output. The voice deforming unit 34 can also perform voice deformation processing on voice data sent from the voice input processing unit 22.

A voice code conversion unit 40 for converting the real voice voice data transmitted from the voice input processing unit 22 and the synthesized voice data transmitted from the voice synthesis unit 30 into a voice code image is subjected to waveform coding, analysis and synthesis. An audio data compression / encoding unit 41 constructed by a method appropriately selected from known encoding methods such as encoding, and an audio code image generation for expanding the encoded audio code data into a two-dimensional code image The unit 42 determines the size (outer dimension) of the audio code image formed in the audio-accompanied photograph 2 so as to be convenient in layout editing of the audio-accompanied photograph of the image image and the audio code image based on the image data to be performed later. Precode image generator 43 to be calculated
And

The image data edited by the image input processing unit 21 is temporarily stored in the image data storage unit 51 as an image image, and the voice code image converted by the code conversion unit 21 is temporarily stored in the voice code image storage unit 52. The image / voice synthesis processing unit 60 converts the print data into a print data so as to be printed out by the printer 3 with a desired layout. For this reason, the image / sound synthesis processing unit 60 performs an image / sound code image layout editing unit 61 that performs a layout process of the image image stored in the image data storage unit 51 and the sound code image stored in the sound code image storage unit 52. And an image / sound code image synthesis processing unit 62 that synthesizes both images with the determined layout to generate print data. At the time of layout editing, a dummy box area based on the size of the audio code image calculated by the pre-code image generation unit 43 is displayed on the monitor 4, and an accurate dummy box area is displayed while comparing the positional relationship with the displayed image image. It enables layout work.

A typical procedure for creating the photograph 2 with sound by the above-described sound / image processing apparatus will be described with reference to the flowchart of FIG. Here, it is assumed that the order of the photograph 2 with sound is made by e-mail. When the e-mail arrives (# 1), image data as an attached file of the e-mail is input to the image input processing unit 21 (# 1).
1) and the image data is operated by the image editing unit 21a.
Editing processing such as color tone / gradation conversion and enlargement / reduction is performed through an operator's operation while checking the image on the monitor 4 (# 12). When there are a plurality of input images, the image is selected by the image selection unit 21b and then the editing process is performed. The edited image data is temporarily stored in the image data storage unit 51 (# 13).

On the other hand, the e-mail file containing the text data as the source of the voice code image is sent to the text editing unit 23a of the text input processing unit 23 (##
14) Then, text data including only a message to be captured as a voice code image in the photograph 2 with voice is cut out from the electronic mail (# 15).

The text data sent to the speech synthesizer 30 as text mixed with kanji kana is analyzed by the text-to-speech synthesizer 31 while accessing the text analysis dictionary 32 (# 21).
An accent is given (# 22). Next, the breathing position is set, the intonation of the entire sentence is determined, and a phoneme sequence composed of phoneme symbols and prosodic parameters is created (# 23). The synthesized speech elements are sequentially connected to the generated phoneme sequence while accessing the synthesized speech element dictionary 33 to generate synthesized speech data (# 24).

If voice synthesis processing is required for the synthesized speech data (branch # 25 YES), the voice quality transformation unit 34 performs frequency linear conversion or the like (# 26), and if it is not required (branch # 25 NO). The synthesized voice data is sent to the code conversion unit 40 as it is.

First, the synthesized voice data is sent to a voice data compression / encoding unit 41, where it is subjected to a compression process, and subsequently converted into an optically readable voice code image by a voice code image generation unit 42. (# 31). Further, the size (external dimensions) of the voice code image is calculated by the precode image generation unit 43 (# 32), and the size data is temporarily stored in the voice code image storage unit 52 together with the voice code image data (# 3).
3).

The image data stored in the image data storage unit 51 and the audio code image stored in the audio code image storage unit 52 are stored in the image / synthesis processing unit 60.
The layout editing process of the image image and the voice code image is performed by being taken into the voice code image layout editing unit 61 (# 40). In the actual layout editing processing, a layout editing screen is displayed on the screen of the monitor 4, and the layout editing of the dummy box area that simulates the image image and the audio code image is performed by the instruction of the cursor. For this layout editing, it is also possible to adopt a method of automatically injecting the image image and the audio code image using a template selected in advance. At this time, if the length of the audio code image exceeds the printable length, for example, re-editing is performed such that the audio code image is separated into two parts to form a two-stage configuration.

Image / voice code image synthesis processing unit 62
Upon receiving the layout information from the image / audio code image layout editing unit 61, the image data storage unit 5
1 and a request signal are transmitted to the voice code image storage unit 52, and the corresponding image data and voice code image data are received. The received image data and audio code image data are integrated based on the layout information and generated as print data (# 41). The print data is transmitted to the printer 3 so that the image image and the audio code image are exposed on the photographic paper, and the exposed photographic paper is subjected to a developing process, thereby creating the photograph 2 with sound as shown in FIG. (# 50).

[Another Embodiment] In the functional block diagram of another embodiment of the present invention shown in FIG. 5, the speech synthesizing section 30 is different from the previous embodiment shown in FIG. The difference is that a voice editing / synthesizing unit 35 is used instead of the unit 31.

In order to generate synthesized speech data in this method called edit synthesis in which sentence speech is generated from fragments of real voice having limited vocabulary and phrases, real voice data of vocabulary and phrases registered in advance are stored. The voice editing / synthesizing unit 35 fragments the text data sent from the text input processing unit 23, and replaces the fragment with a voice data fragment using the registered voice element dictionary. To go.

In this embodiment, the registered voice element dictionary 36 can store real voice data registered for each individual. In other words, the minimum required audio elements for editing and synthesizing are registered and stored in advance by the customer's own voice for the customer of the image sheet with sound, and when ordering the image sheet with sound, the registration of the person is performed. Synthesized speech data is created by edit synthesis using a speech element. For customers who are not registered, the voice elements prepared as standard are used.

The audio / image processing apparatus of this embodiment has a box-shaped appearance like an ID photo apparatus or a Purikura (registered trademark) apparatus as shown in FIG. After inputting the fee, the customer who intends to create the product according to the instruction message displayed on the monitor 4
While photographing oneself with the provided digital camera, the user inputs the text data to be converted into a voice message using the provided touch panel keyboard 8a, or inputs the text data in real voice through the microphone 6a.
In addition, a sublimation type thermal transfer printer is employed as the printing unit 3.

A typical procedure for creating a photograph 2 with sound by the sound / image processing apparatus of this embodiment will be described with reference to the flowchart of FIG. Here, the image source for the photograph 2 with sound is image data captured by a digital camera, and the sound source is text data directly input from the built-in keyboard 8a.

A customer who wishes to create a photograph 2 with sound
By inserting the specified coin into the coin slot (# 1
01) In accordance with the menu displayed on the monitor 4, first, the digital camera provided in the apparatus shoots the user in the same procedure as the ID photo apparatus and the print apparatus (# 110). Since this digital camera is directly connected to the I / O interface 10, image data obtained by the digital camera is immediately transferred to the image input processing unit 21 (#
111). The image data transferred to the image input processing unit 21 can be subjected to editing processing such as trimming and enlargement / reduction while checking the image on the monitor 4 by the function of the image editing unit 21a (# 112). The edited image data is temporarily stored in the image data storage unit 51 (#
113).

Next, since text data by keyboard input has been selected as source data for making a voice code image, a voice message to be incorporated into the photograph with voice is input as a sentence from the keyboard 8a (# 114). . Since the text editing unit 23a has a function as a text editor, it creates a sentence from data input through the keyboard 8a, and finally converts this text data into a format suitable for editing and synthesis and sends it to the speech synthesis unit 30. (# 115).

In the editing / synthesizing process, first, it is checked whether or not this customer has previously registered voice (# 12).
1). If the voice is registered, the registered voice element file of the customer is loaded (# 122). There are various modes for loading the registered voice element file. Here, two typical modes will be introduced.

The first method is that a customer registers a necessary vocabulary / phrase in a real voice by a voice element registration device in advance, and files the registered vocabulary / phrase in a format suitable for editing and synthesis. In this embodiment, the obtained audio element file is recorded on a memory card. By inserting the corresponding memory card into the card reader 7a at the stage of checking whether the voice is registered, the registered voice element file is loaded into the registered voice element dictionary 36 of the voice synthesizer 30. The second type is a form in which a voice element file created in advance by the voice element registration device is stored in the registered voice element dictionary 36 using the customer ID as a key. Is input, the registered voice element file of the customer is set so as to be used as the registered voice element dictionary 36 in the subsequent editing and synthesizing work. It is preferable that the registered voice element dictionary 36 is provided not in the voice / image processing apparatus but in a server connected by a communication line. That is, when the customer ID is input, the registered voice element file of the corresponding customer is stored in the registered voice element dictionary 36 of the voice synthesis unit 30 through the communication line.
It is configured to be loaded to

If no voice is registered, the standard voice element file stored in the registered voice element dictionary 36 is set so as to be used as the registered voice element dictionary 36 in the subsequent editing and synthesizing work. (# 12
3).

In any case, in the edit composition process,
First, the message sentence represented by the text data to be processed is decomposed into vocabulary and phrases (# 124), and fragmentary speech elements extracted from the speech element file as the registered speech element dictionary 36 are assigned to each of them, and synthesized. The audio data is generated (# 125).

When voice quality modification processing is required for the synthesized speech data (branch # 25 YES), the voice quality transformation unit 34 performs frequency linear conversion or the like (# 26), and when the voice quality modification processing is not required (branch # 25 NO). The synthesized voice data is sent to the code conversion unit 40 as it is, and as described above in steps # 31 to # 33, the synthesized voice data is converted into a voice code image, and the generated voice code image is stored in the voice code image storage unit 52. Is stored once.

The image data stored in the image data storage unit 51 and the voice code image stored in the voice code image storage unit 52 are laid out by an image / voice code image layout editing unit 61 using a preselected template. An editing process is performed (# 40).

Image / voice code image synthesis processing unit 62
Integrates the image data and the audio code image data based on the layout information to generate print data (# 41). By transmitting the print data to the printer 3, the image image and the voice code image are printed on a dedicated sheet, and discharged as a photograph 2 with voice as shown in FIG. Is performed (# 50).

In the above-described embodiment, the image data and the voice code image are synthesized by the image / voice synthesis processing unit 60. However, the image / voice synthesis processing unit 60 is omitted and the image data and the voice code image are printed out by the printer 3. However, the image data and the voice code image may be printed out by different printers. At this time, it is preferable that the sticker on which the voice code image is formed is attached to a sheet on which the image is formed, for example, a photo print, by using a sticker printer to print out the voice code image.

Further, in all the above-described embodiments, the input text data is once converted into synthesized voice data by the voice synthesis unit 30 and the synthesized voice data is converted into a voice code image. Part 2
It is also possible to directly convert the text data processed in step 3 into a voice code image. As shown in FIG. 8, such a voice / image processing apparatus includes a code conversion unit 40 which, instead of omitting a voice synthesis unit 30, generates a text element obtained by fragmenting text data into predetermined elements. A text / voice code image replacement unit 44 for sequentially assigning corresponding voice code images, and a voice code image dictionary 45 in which voice code images corresponding to text elements are registered. In other words, a speech code image corresponding to the vocabulary or the phrase constituting the text is applied and sequentially connected to create a final speech code image.

[Brief description of the drawings]

FIG. 1 is an external view showing an embodiment of a sound / image processing device according to the present invention.

FIG. 2 is a functional block diagram of the audio / image processing device according to FIG. 1;

FIG. 3 is an explanatory diagram showing a state in which sound is reproduced from a photograph with sound created by the sound / image processing device.

FIG. 4 is a flowchart showing a procedure for creating a photograph with sound using the sound / image processing device shown in FIG. 2;

FIG. 5 is a functional block diagram showing another embodiment of the audio / image processing device according to the present invention.

6 is an external view of the audio / image processing device according to FIG. 5;

7 is a flowchart showing a procedure for creating a photograph with sound using the sound / image processing apparatus shown in FIG. 5;

FIG. 8 is a functional block diagram showing still another embodiment of the audio / image processing device according to the present invention.

[Explanation of symbols]

2 Image Sheet with Sound (Photo with Sound) 3 Print Unit (Silver Film Photo Printer, Sublimation Type Thermal Transfer Printer) 21 Image Input Unit 22 Voice Input Unit 23 Text Input Processing Unit 24 Character Recognition Unit 30 Voice Synthesis Unit 31 Text Voice Synthesis Unit 32 Text Analysis Dictionary 33 Synthesized Speech Element Dictionary 34 Voice Quality Deformation Unit 35 Speech Editing / Synthesis Unit 36 Registered Speech Element Dictionary 60 Image Speech Synthesis Processing Unit

Continued on the front page F term (reference) 5C052 AA11 DD06 EE08 FA02 FA03 FE01 GA02 GA05 GB07 GD03 GE08 5C062 AA05 AB17 AC02 AC29 AE02 AE07 AE08 AE11 5D045 AA20 BA01

Claims (8)

[Claims] 1. A code conversion unit for converting audio data into an audio code image coded so as to be optically readable, and an image based on the audio code image and image data to create an image sheet with audio. An audio / image processing apparatus having a printing unit for printing an image, comprising a text input processing unit for processing input text data, and based on the text data processed by the text input processing unit. A sound / image processing device for generating a sound code image for reproducing the sound of the sound. 2. A speech synthesizing section for generating synthetic speech data based on text data processed by the text input processing section, wherein the code converting section converts the synthesized speech data generated by the speech synthesizing section into the synthesized speech data. The audio / image processing apparatus according to claim 1, wherein the audio / image processing apparatus is used as source audio data for an audio code image. 3. The speech synthesis unit analyzes input text data by using a text analysis dictionary to identify its reading, and further sets an accent and prosody to obtain a synthesized speech element dictionary from a phoneme sequence obtained. The voice / image processing apparatus according to claim 2, further comprising a text-to-speech synthesizing unit that generates synthesized speech data by using the text / speech data. 4. The speech / image processing apparatus according to claim 2, wherein the synthesized speech elements stored in the synthesized speech element dictionary are created based on real voice data registered for each individual. 5. A speech editing / synthesis unit for converting input text data into synthesized speech data in a fragmentary manner using a registered speech element dictionary storing real voice data of vocabulary and phrases registered in advance. The audio / image processing apparatus according to claim 2, further comprising a unit. 6. The voice / image processing apparatus according to claim 5, wherein said registered voice element dictionary stores real voice data registered for each individual. 7. The voice / image processing apparatus according to claim 2, wherein said voice synthesizing unit includes a voice quality changing unit for changing a voice quality of said synthesized voice data. 8. A character recognition device is additionally provided,
8. The voice / image processing device according to claim 1, wherein the text data output by the character recognition device is used for voice code image conversion.