JPH0388592A - Video telephone system - Google Patents

Abstract

PURPOSE:To easily and securely grasp the transmission intension of a called party by converting recognized sounds into character information in a character code conversion part, supplying these converted character information to a display part and inserting these character information to one part of a picture. CONSTITUTION:Received sound signals are reproduced by a receiver 2, converted into digital signals by an A/D converter 23 and stored in a sound memory 24 afterwards. The sound signals read from the sound memory 24 are supplied to a sound recognition part 30 and the recognition processing of the sounds is executed. Then, recognized results are supplied to a memory 25 for character code conversion and sound information are converted into the character information. These character information are synthesized to a self-picture or a received picture in a picture synthesizing part 15 and supplied to a monitor 4. Thus, the received sound signals are projected on the monitor 4 as the character information.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention relates to a video telephone device that transmits and receives images and sounds, and particularly to a videophone device that can convert received audio information into text information and display it. The present invention relates to a videophone device.

[Prior Art] Videophone devices using public telephone lines have become widespread.

In this videophone device, images are recognized by a monitor (a display device such as a CRT), and sounds are recognized by the ears.

[Problems to be Solved by the Invention] Since videophone devices are installed in a location desired by the user, they may be installed in locations where the usage environment is not very favorable, such as along roadsides with heavy traffic. . In such a case, there may be cases where the received audio cannot be sufficiently BE-IJed. At that time, the same question is asked again to the other party.

Also, when reception conditions are poor, it can be difficult to hear the other person's voice in the same way.

In view of this, the present invention proposes a videophone device that improves on these points and is able to reliably grasp the received voice even in a place where the installation environment or reception conditions are poor.

[Means for Solving the Problems] In order to solve the above-mentioned problems, the present invention provides a videophone device in which audio and image information are transmitted and received using telephone lines, respectively. and a character code conversion unit, the voice recognition unit includes means for recording the voice of the recipient, and means for comparing and recognizing the recorded voice based on the voice data inputted in advance, The recognized voice is converted into character information in the character code conversion unit, and the converted character information is supplied to the display unit, and the character information is inserted into a part of the image. That is.

[1 Effect] The received voice information is recognized by the voice recognition section 30 and converted into character information (character code) by the character code conversion section 25 based on the recognition result.

This text information is supplied to the monitor 4 together with image information,
Text information is inserted into a part of the image. For example, superimposed.

This way, even if the reception is poor or there is a lot of noise in the surrounding area and the voice cannot be recognized accurately, the voice will be converted to text information and can be monitored as part of the image. Be able to understand the content accurately.

[Example] Next, an example of the videophone device according to the present invention will be described in the first example.
This will be explained in detail with reference to the figures and FIG.

FIG. 1 is a basic configuration diagram of the present invention.

In FIG. 1, 1 is a public line, and 2 is a receiver for inputting and outputting audio.

3 is a Pideme camera built into the main body of the device to capture images for transmission.

Reference numeral 4 denotes a monitor (a display device such as a CRT) for checking images to be transmitted and for displaying received images.

Reference numeral 5 denotes an operation unit (keyboard), on which a numeric keypad is used to directly input telephone numbers and the like.

6 is a control unit with a built-in computer;
It is composed of a PU 7, a program ROM 8, and a work RAM 9.

It is assumed that the program ROM 8 stores various control programs such as voice recognition processing, transmission processing, and monitor display processing. Therefore, the control section 6 performs various processes based on various information input from the operation section 5.

When the line is connected using the telephone number input from the operation unit 5, the changeover switches 14, 18, and 19 are respectively switched to the state shown by solid lines, so that only audio can be transmitted and received.

And image information (self-portrait) captured by video camera 3
is converted into digital No. 48 by the A/D converter N12 and then stored in the image memory 13, and the stored image signal is supplied to the D/A converter 16 via the changeover switch 14 and the image synthesis section 15, and is converted into an analog signal. After being returned to , it is supplied to the monitor 4 and a self-portrait is displayed. When the changeover switch 18 is switched to the solid line position,
Image information cannot be transmitted to the destination.

When the mode is switched to the image transmission mode, the changeover switch 18 is switched to the mode shown by the broken line.

Now, the image information read from the image memory 13 is
The signal is converted into an analog signal by the /A converter 20, and sent to the public line 1 side in the form of analog 4g signal. When this image information is being transmitted, the control unit 6 controls the image signal from the video camera 3 so that it is not stored in the image memory 13.

When the transmission of the image is completed, the sender is notified that the transmission of the image has been completed, and the changeover switch 18 is automatically switched to the state shown by the solid line, so that only audio can be transmitted and received. At this time, the image memory 13 is in a write enabled state.

On the other hand, the image information of the other party transmitted through the public line 1 is supplied to the A/D converter 21 via the changeover switch 19, converted into a digital signal, and then stored in the image memory 22. The image information read from the image memory 22 is sent to the D/A converter 16 via the changeover switch 14 and the image composition section 15.
The signal is then supplied to the system and reconverted into an analog signal. Thereafter, the image is supplied to the monitor 4 and the image of the other party is displayed on the monitor 4. Switching of the changeover switch 14 is instructed by the operation unit 5.

The received audio signal is played back on the handset 2, and the A/
After being converted into a digital signal by the D converter 23, it is stored 17 in the voice memo υ24.

The voice signal read from the voice memory 24 is supplied to the voice recognition unit 30, where voice recognition processing is executed, and the recognition result is also supplied to the memory 25 for character code conversion, where the voice information is converted into character information. is converted to

This character information is combined with the self-portrait or the received image by the image combining section 15 and supplied to the monitor 4.

The received audio signal or text information is then displayed on the monitor 4.

The speech recognition section 30 can be configured as shown in FIG.

In the figure, audio signal data supplied to an input terminal 31 is subjected to frequency analysis by an acoustic analysis section 32, and changes in the audio spectrum analysis are examined. The analysis results are normalized on the time axis in the information compression section 33 to absorb variations due to changes in the sounding speed. By performing these processes, voice recognition can be performed for an unspecified person.

On the other hand, the phoneme (syllable) learning section 35 has some voice data of the sender inputted in advance at the beginning of the call. and,
The audio data (foreshadow information) sent from the information compression unit 33 is subjected to phoneme recognition processing, specifically phoneme information extraction processing, in the phoneme recognition unit 34 based on data from the phoneme learning unit 35. .

By using the phoneme learning section 35 and the phoneme recognition section 34, when the same foreground information is input a second time or later, the phoneme can be extracted immediately.

The extracted phoneme information is compared with the word information from the word dictionary section 37 in the word (clause) recognition section 36, and the word recognition process is completed, and the recognized word information is obtained at the output terminal 38. By supplying this word information as an address to the character code memory 25, the word information is converted into character information (character code) for expressing characters.

Such voice recognition processing is performed based on a control program for voice processing stored in the control unit 6, and in response to a command from the operation unit 5, this text information is synthesized with the self-portrait or received image and displayed on the monitor. 4 will be displayed on the screen.

It is assumed that the display position of characters on the screen, vertical writing, horizontal writing, font, etc. can all be specified using the operation unit 5. Of course, displaying only characters or displaying only images can also be specified using the operation unit 5.

[Effects of the Invention] As explained above, according to the configuration of the present invention, received voice can also be displayed on the screen as text.

Therefore, the receiving environment or the recipient's i! f
[I! Even in this case, it has the characteristic of being able to easily and clearly grasp the other party's intention to communicate.

[Brief explanation of drawings]

Figure 1 is a basic configuration diagram of this invention. Figure 2 is audio It is a system diagram of a recognition part. 14° 1・ 2・ 3・ 4・ 5・ 6・ 13, 22 ・ 18, 19 ・ 24・ 25・ 30・ 32・ 33・ 34・ ・Public line ・Telephone receiver ·Video camera ·monitor ・Operation unit ・Control unit ・Image memory ・Choice switch ・Voice memory ・Character code conversion section ・Speech recognition section ・Acoustic analysis department ・Information compression section ・Phoneme recognition section 35　・・ ・Phoneme learning department 36　・・ ・Word recognition part 37・・ ・Word dictionary section

Claims (1)

[Claims] (1) A videophone device configured to transmit and receive audio and image information using telephone lines, respectively, is provided with a voice recognition section and a character code conversion section, and the voice recognition section records the voice of the recipient. and a means for recognizing the voice by comparing and referring to the recorded voice based on the voice data inputted in advance, and the recognized voice is converted into character information in the character code conversion section, and the converted character is converted into character information. 1. A video telephone device characterized in that information is supplied to a display section and the text information is inserted into a part of an image.