JP2000184077A - Intercom system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an intercom system usable even by a person with hearing disability by visualizing the uttered contents of a visitor or converting it to voice for which the hearing characteristics of a listener are taken into consideration and usable even by a person with language disability by enabling coping by something other than the voice in coping with the visitor. SOLUTION: In this intercom system for transmitting and receiving signals between an intercom slave unit 1 installed outdoors and an intercom master unit 2 installed indoors, the intercom master unit 2 is provided with a voice recognition means 22 for recognizing the uttered sound of the visitor inputted to the microphone 6 of the intercom slave unit 1 and converting it to phoneme data, a data processing means 24 for converting the phoneme data to character codes and a display means 12 for displaying the character codes.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a door phone system, and more particularly, to a door phone system that can be used by persons with hearing impairment or speech impairment.

[0002]

2. Description of the Related Art In a conventional door phone system, a doorbell switch of a door phone slave set at an entrance or the like is depressed.
At the indoor doorphone master unit, for example, an image from the doorphone slave unit is displayed, a ringing tone is output from the speaker, and the call is started by indicating that the resident is willing to pick up the handset of the doorphone master unit and the like. Has become.

[0003]

In a conventional intercom system, the only means of communicating two-way intentions between a visitor and a resident is through voice. For this reason, there is a problem that it is difficult for a resident having a hearing impairment or a language impairment to use the door phone system. The present invention has been made in view of such a problem, and can be used by persons with hearing impairment by visualizing the utterance content of a visitor or converting it into a voice in consideration of the hearing characteristics of the listener. It is another object of the present invention to provide a door phone system that can be used by people with language impairment by making it possible to deal with visitors by means other than voice.

[0004]

A door phone system according to the present invention transmits and receives signals between a door phone slave unit for a visitor and a door phone master unit for a resident. Voice recognition means for recognizing voice from a utterance of a visitor inputted to the microphone of the intercom slave unit, data processing means for converting voice data recognized by the voice recognition means into a character code, and displaying the character code And display means for performing the operation. Also, the door phone master unit is provided with image recognition means for recognizing voice from a mouth shape and / or a lip shape when the visitor utters a voice input to the TV camera of the door phone slave unit, so that the resident can utter the visitor's voice. The content can be obtained as visual information.

The door phone system of the present invention transmits and receives signals between a door phone slave unit for a visitor and a door phone master unit for a resident, and the door phone master unit includes the door phone slave unit. Voice recognition means for recognizing voice from a visitor's utterance sound input to the microphone of the machine, means for registering and storing the hearing characteristics of the listener, and converting the voice data recognized by the voice recognition means to the hearing characteristics of the listener. And first speech synthesis means for synthesizing speech based on the speech.
Also, the door phone master unit may have a mouth shape and / or when the visitor utters a voice input to the television camera of the door phone slave unit.
Alternatively, by providing image recognition means for recognizing voice from the lip shape, the resident can obtain the utterance content of the visitor as visual information.

The door phone system of the present invention transmits and receives signals between a door phone slave unit for a visitor and a door phone master unit for a resident. The apparatus includes a character input unit that generates a character code of a character to be input, and a second voice synthesis unit that synthesizes a corresponding voice from the character code. In addition, since the character input means is capable of inputting a standard sentence, a resident can respond to a visitor without uttering with a simple input.

[0007]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a door phone system according to the present invention will be described in detail with reference to the drawings. FIG. 1 is an explanatory diagram showing a basic configuration of a door phone system according to the present invention, wherein 1 is a door phone slave unit installed outdoors such as an entrance, and 2 is a door phone master unit installed indoors. 1
The intercom master unit 2 transmits and receives signals using a communication medium such as a radio 5 via a signal line 3 or an antenna 4.

The intercom slave unit 1 has a microphone 6 to which a voice uttered by a visitor is input, a speaker 7 to output a sound from the intercom master unit 2, a television camera 8 for capturing an image of the visitor, and a residence for the visitor. A doorbell switch 9 for notifying a person is housed in a case 15. The door phone master unit 2 includes a microphone 10 to which a voice uttered by a resident is input, and a door phone slave unit 1.
Speaker 11 for outputting voices and ringing tones from a speaker, a display 12 for displaying an image of the television camera 8 of the intercom slave unit 1 and a handwriting input screen, etc., and an input pen 1 used for handwriting input
3. A response switch 14 indicating the will to respond to a call from the intercom slave unit 1 is housed in the case 16.

FIG. 2 is a block diagram showing the configuration of the door phone master unit of the first embodiment. The voice signal 21 uttered by the visitor is input from the microphone 6 of the intercom slave unit 1 and transmitted to the intercom master unit 2 via a communication medium such as the signal line 3 or the radio 5. The transmitted voice signal 21 is transmitted to the voice recognition unit 2
In step 2, recognition at the phoneme level such as vowels and consonants is performed using the speech recognition dictionary unit 28, and is converted into phoneme data. Next, the data processing unit 24 converts the phoneme data into a character code that can be processed by the display control unit 25.
Next, each character code is displayed on the display 1 by the display control unit 25.
By displaying the information in 2, the resident can obtain the utterance content of the visitor as visual information.

A visitor image signal 26 input from the television camera 8 of the intercom slave unit 1 is transmitted to the intercom master unit 2 via the signal line 3 or the wireless 5 communication medium. The transmitted image signal 26 is recognized in the image recognition unit 27 using the mouth shape and / or lip shape of the visitor and the image recognition dictionary unit 28, and is converted into phoneme data. Next, the data processing unit 24 converts the phoneme data into a character code that can be processed by the display control unit 25. Next, the display controller 25 displays each character code on the display unit 12, so that the resident can obtain the utterance content of the visitor as visual information.

FIG. 7 shows a flowchart of the operation of the first embodiment. The caller switch 9 of the intercom slave unit 1 is pressed by the visitor, and it is determined that there is a call from the intercom slave unit 1 (step S1), and it is determined that there is an image signal or an audio signal from the intercom slave unit 1. And (Step S
2) Phoneme data is generated by voice recognition processing (step S3), and phoneme data is generated by image recognition processing (step S4). Next, when the recognition results of the voice recognition and the image recognition match (step S5), the phoneme data is converted into a character code (step S6), and characters are output to the display 12 (step S7). As shown in this flowchart, more accurate recognition can be performed by performing the above-described voice recognition and image recognition together as means for recognizing the utterance content of the visitor.

FIG. 3 is a block diagram showing a configuration of a door phone master unit 2 according to a second embodiment of the present invention. A voice signal 21 uttered by the visitor, which is input from the microphone 6 of the intercom slave 1, is transmitted to the intercom master 2 via the signal line 3 or the wireless 5 communication medium. The transmitted voice signal 21 is recognized at a phoneme level such as vowels and consonants by a voice recognition unit 22 using a voice dictionary unit 23, and is converted into phoneme data. Next, the speech synthesizer 33 synthesizes a sound that is easy for the listener to hear using the auditory characteristic registration unit 31 and the audio synthesis dictionary unit 32 that hold the phoneme data and the auditory characteristics of the listener. The synthesized voice is amplified by the voice signal control unit 34, and the voice of the visitor is output to the speaker 11 of the door phone master unit 2 as a voice that is easy for the listener to hear.

A visitor image signal 26 input from the television camera 8 of the intercom slave 1 is transmitted to the intercom master 2 via the signal line 3 or the wireless 5 communication medium. The transmitted image signal 26 is recognized in the image recognition unit 27 based on the image of the visitor's mouth and / or lip and the image recognition dictionary unit 28, and is converted into phoneme data. Next, an auditory characteristic registration unit 31 and a speech synthesis dictionary unit 32 that hold the phoneme data and the auditory characteristics of the listener.
, The speech synthesizer 23 synthesizes a speech that is easy for the listener to hear. The synthesized voice is amplified by the voice signal control unit 34, and the voice of the visitor is output as a voice that is easy for the listener to hear from the speaker 11 of the door phone master unit 2.

FIG. 8 shows a flowchart of the operation of the second embodiment. Steps S11 to S15 are the same as steps S1 to S5 in FIG. 7, and if the recognition results match in step S15, a speech synthesis process corresponding to the recognized phoneme data is performed (step S16), and the speaker of the intercom master unit 2 11 (step S17). As shown in this flowchart, more accurate recognition can be performed by using both the voice recognition and the image recognition as a means for recognizing the utterance content of the visitor.

FIG. 4 is a block diagram showing a configuration of a door phone master unit 2 according to a third embodiment of the present invention. The resident uses the input pen 13 provided in the intercom base unit 2 to write a word to be transmitted to the visitor to the handwritten character input unit 51 on the touch panel 41 as shown in the display example of FIG. The written characters are converted into drawing data that can be processed by the handwritten character recognition unit 43 in the touch panel control unit 42. The handwritten character recognition unit 43 performs recognition of handwritten characters based on the drawing data and the character recognition dictionary unit 44. Generate character codes.

The generated character code is sent to the data processing unit 2
In step 4, the data is converted into phoneme data that can be processed by the voice synthesis unit 33. Based on the phoneme data and the speech synthesis dictionary unit 32, a speech synthesis unit 33 generates a synthesized speech. The generated audio signal 45 is transmitted to the intercom slave unit 1 via the signal line 3 or various communication media of the radio 5 and output from the speaker 7 of the intercom slave unit 1 so that the resident can respond to the visitor without speaking. Becomes possible.

Further, when the resident touches the fixed form input unit 61 and the Japanese syllabary input unit 62 as shown in the display example of FIG. At 42, a character code is generated. Next, this character code is converted into phonemic data that can be processed by the voice synthesizing unit 33 in the data processing unit 24, and the voice signal is converted in the voice synthesizing unit 33 using the converted phonemic data and the voice synthesizing dictionary 32. Synthesized. The generated audio signal 45 is transmitted to the intercom slave unit 1 via the signal line 3 or the wireless 5 communication medium, and is output from the speaker 7 of the intercom slave unit 1.

FIG. 9 shows a flowchart as an example of the processing procedure of the third embodiment. When the caller switch 9 of the intercom slave unit 1 is pressed by the visitor, it is determined that there is a call from the intercom slave unit 1 (step S21), and when it is determined that handwriting input is to be executed (step S22), handwritten character recognition is performed. Processing is performed (step S23). Step S
If it is determined in step S22 that handwriting input is not to be executed, it is determined in step S24 whether or not to input a fixed form sentence.
If so, a fixed form input process is performed (step S25).

In step S26, a character is output to the display unit 12, the character code is converted into phoneme data (step S27), and a voice synthesis process is performed in the voice synthesis unit 33 (step S28). (Step S29). As shown in this flowchart, the resident can respond to the visitor without uttering just by pressing the touch panel 41. Note that the present invention is not limited to the above embodiment. To make it easier for the hearing impaired to know the presence of a visitor by emitting a flash light instead of or in addition to emitting sound from the speaker of the door phone master unit when the doorbell is pressed. Can be.

[0020]

As described above in detail, according to the first aspect of the present invention, the resident has a hearing impairment by recognizing the utterance of the visitor and providing it to the resident as visual information. Even if it does, it becomes possible to understand the content of the utterance of the visitor. According to the third aspect of the present invention, by recognizing the utterance of the visitor and generating a synthesized voice that is easy for the resident to hear based on the pre-registered resident's hearing characteristics, Even if the person has a hearing impairment, it is possible to understand the utterance content of the visitor.

According to the fifth aspect of the present invention, the resident inputs words desired to be transmitted to the visitor from the touch panel,
By providing the words as speech to the visitor, it is possible to communicate the intention to the visitor even if the resident has a language disorder. Therefore, according to the door phone system of the present invention, even a resident with a hearing impairment or a speech disorder, which is difficult to handle with the conventional door phone system, can respond to visitors.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram showing the principle of a door phone system of the present invention.

FIG. 2 is a block diagram of a first embodiment of the present invention.

FIG. 3 is a block diagram of a second embodiment of the present invention.

FIG. 4 is a block diagram of a third embodiment of the present invention.

FIG. 5 is a display example of a door phone master unit in the third embodiment.

FIG. 6 is another display example of the door phone master unit in the third embodiment.

FIG. 7 is a flowchart showing the operation of the first embodiment.

FIG. 8 is a flowchart showing the operation of the second embodiment.

FIG. 9 is a flowchart showing the operation of the third embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Intercom handset 2 Intercom master unit 3 Signal line 4 Wireless 6 Microphone 7 Speaker 8 Television camera 10 Microphone 11 Speaker 12 Display 13 Input pen 22 Voice recognition unit 23 Voice recognition dictionary unit 24 Data processing unit 27 Image recognition unit 28 Image recognition Dictionary unit 31 Auditory characteristic registration unit 33 Voice synthesis unit 41 Touch panel 43 Handwritten character recognition unit 46 Standard character registration unit

Claims (6)

[Claims] 1. A door phone system for transmitting / receiving a signal between a door phone slave unit for a visitor and a door phone master unit for a resident, wherein the door phone master unit is a guest input to a microphone of the door phone slave unit. Voice recognition means for recognizing voice from an uttered voice of a person, data processing means for converting voice data recognized by the voice recognition means into a character code, and display means for displaying the character code. Door phone system. 2. The intercom base unit includes image recognition means for recognizing voice from a mouth shape and / or a lip shape when a visitor utters a voice input to a television camera of the intercom slave unit. 2. The door phone system according to 1. 3. A door phone system for transmitting and receiving signals between a door phone slave unit for a visitor and a door phone master unit for a resident, wherein the door phone master unit receives a customer input to a microphone of the door phone slave unit. Voice recognition means for recognizing a voice from a utterance of a listener, means for registering and storing the hearing characteristics of the listener, and a first voice for synthesizing a voice from the voice data recognized by the voice recognition means based on the hearing characteristics of the listener. And a combining means. 4. The intercom master unit includes image recognition means for recognizing voice from a mouth shape and / or a lip shape when a visitor utters a voice input to a television camera of the intercom slave unit. 3. The door phone system according to 3. 5. A door phone system for transmitting and receiving signals between a door phone slave unit for a visitor and a door phone master unit for a resident, wherein the door phone master unit generates a character code of a character input by a resident. And a second voice synthesizing means for synthesizing a corresponding voice from the character code. 6. The intercom system according to claim 5, wherein said character input means is capable of inputting a fixed text.