JPH0775075A - Video telephone system - Google Patents

Abstract

PURPOSE:To exactly transmit a message to a hearing handicapped person. CONSTITUTION:For example, a talking with hand operation by the hearing handicapped person is recognized as a talking with hand pattern by a talking with hand pattern recognizing and analyzing part 13, converted into a voice signal corresponding to the talking with hand pattern by a voice converting part 14, and transmitted to an opposite terminal 30. On the other hand, the voice signal from the opposite terminal is recognized by a voice recognizing part 18, the talking with hand pattern pertinent to the recognized voice signal is generated by a talking with hand pattern generating part 19, and displayed on a display part 5. Thus, the message can be exactly transmitted to the hearing handicapped person.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a video telephone device capable of transmitting information to a hearing impaired person.

[0002]

2. Description of the Related Art FIG. 2 shows the configuration of a receiving side of a conventional videophone device. In the figure, 1 is a public telephone network, 2 is an interface circuit connected to the public telephone network 1 via a telephone line L, 3 is a voice decoder for decoding a voice signal from the other party via the public telephone network 1, Reference numeral 4 is an image decoder for decoding an image signal similarly transmitted from the other party via the public telephone network 1, and 5 is a display unit for displaying the decoded image signal.
The voice signal of the other party decoded by the voice decoder 2 can be output from either the receiver HS or the speaker SP by switching the switch SW.

That is, in the present videophone apparatus, when a call is being made with the other party's apparatus, the voice signal is transmitted to the other party's apparatus through the telephone line L and the public telephone network 1 together with the image signal picked up by a camera not shown. At the same time, the audio signal and the image signal from the partner device via the public telephone network 1 and the telephone line L are decoded by the audio decoder 3 and the image decoder 4, respectively. Then, the decoded audio signal is heard from the handset HS or the speaker SP, and the image signal is displayed on the display unit 5.

[0004]

In this type of videophone apparatus in which the image signal of the other party is displayed together with the audio signal,
If the user is a hearing impaired person, for example, a voice signal cannot be heard even if it is transmitted. Therefore, a sign language or a character image is used to transmit a message as an image signal. However, when a message is transmitted to a hearing-impaired person using sign language instead of a voice signal, the message transmitter requires special training. There is a demand for development of a device capable of transmitting.

Therefore, an object of the present invention is to accurately transmit a message to a hearing-impaired person in a videophone device.

[0006]

In order to solve such a problem, the present invention comprises a display section and a camera, and transmits an image signal taken by the camera during a call together with a voice signal to a partner device. In a videophone device that receives an image signal transmitted together with a voice signal from a partner device and displays it on a display unit, a sign language pattern storage unit that stores each sign language pattern for a deaf person and a voice that stores each voice data. The data storage unit, the voice recognition unit that recognizes the voice signal received from the partner device based on the voice data of the voice data storage unit, and when the voice data recognized by the voice recognition unit is input, it responds to the sign language pattern of the sign language pattern storage unit. And a sign language pattern creating unit for creating the displayed pattern and displaying it on the display unit. Further, when the image data photographed by the camera is input, the sign language pattern recognition unit for recognizing the image data based on each sign language pattern in the sign language pattern storage unit, and the sign language pattern recognized by the sign language pattern recognition unit for the voice data storage unit. And a voice conversion unit for converting the voice data into a voice signal based on the voice data and transmitting the voice signal to the partner device.

[0007]

The voice signal from the partner device is recognized by the voice recognition unit, and the sign language pattern corresponding to the recognized voice signal is generated by the sign language pattern generation unit and displayed on the display unit.
As a result, the message can be automatically transmitted to the hearing impaired person. In addition, for example, a sign language operation by a deaf person is recognized as a sign language pattern by the sign language pattern recognition unit, converted into a voice signal corresponding to the sign language pattern by the voice conversion unit, and transmitted to the partner device. As a result, the hearing impaired person can transmit a message to the other party only by the sign language operation.

[0008]

The present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing an embodiment of a videophone device according to the present invention. In the figure, 11 is a camera,
Reference numeral 12 is an image input unit for inputting an image signal captured by the camera 11, and 13 is a sign language pattern recognition / analysis unit for recognizing and analyzing a sign language pattern for a deaf person from the input image. Also, 14 is a sign language pattern recognition / analysis unit 1.
A voice converter that converts the image of the sign language pattern analyzed by 3 into a voice signal, and 15 is a network control that transmits the voice signal converted by the voice converter 14 to the partner terminal 30 via the telephone line L and the public telephone network 1. It is a department.

Reference numeral 16 is a sign language pattern recognition / analysis unit 1.
3, a sign language pattern data storage unit for storing sign language pattern data necessary for analysis processing;
Is a voice data storage unit for storing voice data necessary for voice conversion. Further, 18 is a voice recognition unit that performs voice recognition based on the voice data stored in the voice data storage unit 17 when voice data is received from the partner terminal 30 via the network control unit 15 and the like, and 19 is the voice recognition unit 18 The sign language pattern creating unit for inputting the voice data recognized by and extracting the image of the corresponding sign language pattern from the sign language pattern data storage unit 16 and creating the sign language pattern, and the display unit 5 for displaying the created image of the sign language pattern. An image output unit for outputting and displaying the image. Reference numeral 21 is a telephone unit, and the telephone unit 21 makes a normal call with a partner terminal via the network control unit 15, the telephone line L and the public telephone network 1.

Next, the operation of the videophone device configured as described above will be described. Here, it is assumed that the present videophone device is used by a hearing-impaired person and the partner terminal 30 is used by a normally-hearing person. This videophone device is a public telephone network 1
When a sign language operation is performed by the hearing impaired person while connected to the partner terminal 30 via, the image is captured by the camera 11 and sent to the image input unit 12 as an image signal. Image input section 1
In 2, the analog image signal is quantized into a digital image signal and sent to the sign language pattern recognition / analysis unit 13.

When this digital image signal is input, the movement of the hand is extracted from this digital image data, and the sign language pattern recognition / recognition is performed with reference to each sign language pattern image data stored in advance in the sign language pattern data storage unit 16.
Perform analysis processing. Then, the corresponding sign language pattern image is sent to the voice conversion unit 14. Then, the voice conversion unit 14 converts the sign language pattern image data from the sign language pattern recognition / analysis unit into one of the voice data stored in the voice data storage unit 17 in advance, and the network control unit 15 and the telephone Line L
And to the partner terminal 30 via the public telephone network 1.

As a result, the sign language motion by the deaf person can be converted into the corresponding voice signal and transmitted to the partner terminal 30. Note that the network control unit 15 is connected to the telephone unit 21 that makes a normal call as described above, and when a predetermined operation is performed on the telephone unit 21, the network control unit 15 detects this operation. The call mode of the hearing impaired person is stopped, that is, the transmission of the voice signal converted from the sign language data to the partner terminal is stopped. Then, the voice signal of the telephone unit 21 is directly transmitted to the partner terminal 30, and the partner terminal 30
Control is performed so that the voice signal from the device is sent to the telephone unit 30 as it is.

Next, the voice signal from the partner terminal 30 input to the network control unit 15 through the public telephone network 1 and the telephone line L during the call mode by the deaf person has the voice recognition unit 18 by the network control unit 15. Sent to. When the voice signal from the partner terminal 30 is input, the voice recognition unit 18 recognizes the input voice signal while referring to each voice data stored in the voice data storage unit 17 in advance. Then, the corresponding voice data is sent to the sign language pattern creating unit 19. When the recognized voice data is input, the sign language pattern creating unit 19 creates a sign language pattern corresponding to the input voice data while referring to each sign language pattern stored in the sign language pattern data storage unit 16, and the image output unit 20 Send to. The image output unit 20 converts the created sign language pattern image data into an analog signal and sends it to the display unit 5 to display it as a sign language image. That is, the voice signal from the partner terminal 30 can be displayed on the display unit 5 as a sign language image.

As described above, this videophone device transmits the sign language operation as a voice signal to the partner terminal 30, and
The display unit 5 displays the voice signal from the partner terminal 30 as a sign language image.
If this device is used by a hearing-impaired person, the message can be easily exchanged with the hearing-impaired person. Although a large amount of memory capacity is required to store image data such as sign language patterns, the image data used for videophones can be efficiently compressed and coded (digitalized). The memory capacity of 16 can be reduced. Further, when the scale of the sign language image output to the display unit 5 is large, character data can be displayed instead of the sign language image.

[0015]

As described above, according to the present invention, the voice signal from the partner device is recognized by the voice recognition unit, and the sign language pattern corresponding to the recognized voice signal is generated by the sign language pattern generation unit and displayed. Since the message is displayed on the section, when the message is transmitted to the hearing-impaired person using the videophone, the message can be accurately transmitted without requiring special sign language training. Further, for example, the sign language pattern recognition unit recognizes a sign language motion by a hearing impaired person as a sign language pattern, and the voice conversion unit converts the signal into a voice signal corresponding to the sign language pattern and transmits the voice signal to the partner device. The message can be transmitted to the other party only by the sign language operation.

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment of a videophone device according to the present invention.

FIG. 2 is a block diagram showing a configuration of a receiving side of a conventional videophone device.

[Explanation of symbols]

 1 Public telephone network 5 Display unit 11 Camera 13 Sign language pattern recognition / analysis unit 14 Voice conversion unit 15 Network control unit 16 Sign language pattern data storage unit 17 Voice data storage unit 18 Voice recognition unit 19 Sign language pattern creation unit L telephone line

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Jun Ota 2-3-2 Shimeguro, Meguro-ku, Tokyo Inside Tamura Electric Co., Ltd.

Claims (2)

[Claims] 1. A display unit and a camera, wherein an image signal captured by the camera during a call is transmitted to a partner device together with a voice signal, and an image signal transmitted from the partner device together with the voice signal is received. In the videophone device for displaying on the display unit, a sign language pattern storage unit for storing each sign language pattern for a hearing impaired person, a voice data storage unit for storing each voice data, and a voice signal received from a partner device for the voice data. A voice recognition unit that is recognized based on the voice data in the storage unit, and a sign language pattern creation unit that creates a pattern corresponding to the sign language pattern in the sign language pattern storage unit when the voice data recognized by the voice recognition unit is input and is displayed on the display unit. A videophone device characterized by being provided with. 2. A display unit and a camera, wherein an image signal captured by the camera during a call is transmitted to a partner device together with a voice signal, and an image signal transmitted from the partner device together with the voice signal is received. In the videophone device for displaying on the display unit, when a sign language pattern storage unit for storing each sign language pattern for the hearing impaired person, a voice data storage unit for storing each voice data, and image data taken by the camera are input, A sign language pattern recognition unit that recognizes this image data based on each sign language pattern in the sign language pattern storage unit, and converts the sign language pattern recognized by the sign language pattern recognition unit into a voice signal based on the voice data in the voice data storage unit. Then, a video telephone device is provided with a voice conversion unit for transmitting to a partner device.