JP3039733B2 - Voice recognition reporting system - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice recognition / reporting system, and more particularly to a voice recognition / reporting system for discriminating a speaker's voice and reporting to a predetermined report destination.

[0002]

2. Description of the Related Art Some conventional security reporting devices detect an abnormality by a security sensor or automatically report a required report destination in response to pressing of an emergency button. When a suspicious person invades a financial institution or a store where such a device is installed, if the emergency button can be pressed so that the suspicious person does not notice, the notification is automatically made. In some cases, the operation of the emergency button is noticed by a suspicious person, so that the button cannot be operated, and the security device installed at an angle may not be useful.

[0003]

SUMMARY OF THE INVENTION In view of the foregoing, the present invention registers a voice set in advance for reporting security or the like, compares the uttered voice with the registered voice,
It is an object of the present invention to provide a system for automatically dialing a preset telephone number, calling a report destination, and transmitting a voice message of a security report in response to an incoming call.

[0004]

In order to solve the above-mentioned problems, the present invention provides a voice input unit for inputting voice, a voice analysis unit for analyzing the input voice and extracting characteristic data, and a voice analysis unit. A storage unit for storing data of the memory, a memory unit for storing voice feature data set for notification when a security abnormality has occurred, and comparing the data recorded in the storage unit with the data read from the memory unit. A discriminating unit for discriminating; a telephone number storage unit for storing a telephone number of a security report destination; a dial signal generating unit for generating a dial signal based on data read from the telephone number storage unit; And a message storage unit for storing a voice input unit, a voice analysis unit, a storage unit, a memory unit, a determination unit, a telephone number storage unit, a dial signal generation unit, and a The control unit controls the message storage unit, and dials out the telephone number read from the telephone number storage unit based on the determination by the determination unit and sends it out to the telephone line. Is provided.

[0005]

With the above configuration, in the voice recognition and notification system according to the present invention, the voice input from the voice input unit extracts the characteristic data by the voice analysis unit and records it in the storage unit. The discriminating unit compares this feature data with the pre-registered feature data read from the memory unit, and when the match rate is equal to or higher than a predetermined matching rate, determines that there is a match. Read it out, dial it automatically, and send it out over the phone line. The message for the report is read out in response to the incoming call from the report destination, and sent out to the report destination by voice.

[0006]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of a voice recognition and notification system according to the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram of a main part of an embodiment of a voice recognition and notification system according to the present invention. In the figure, reference numeral 1 denotes a voice input unit for inputting voice using a microphone or the like. Reference numeral 2 denotes a voice analysis unit which analyzes a voice signal from the voice input unit 1 and extracts feature data. Reference numeral 3 denotes a storage unit that records the feature data analyzed by the voice analysis unit 2. Reference numeral 4 denotes a memory unit that stores the set audio feature data. Reference numeral 5 denotes a determination unit which compares data read from the storage unit 3 with data read from the memory unit 4 and outputs a signal when the coincidence ratio is equal to or higher than a predetermined coincidence rate. Reference numeral 6 denotes a telephone number storage unit that stores a telephone number set as a security report destination or the like. 7 generates a corresponding dial signal based on the data read from the dial signal generator digital and the telephone number storage 6. Reference numeral 8 denotes a message storage unit that stores a message set for security notification. Reference numeral 9 denotes a voice synthesizing unit that synthesizes a voice based on data from the message storage unit 8. An output unit 10 sends out a dial signal from the dial signal generating unit 7 or a voice from the voice synthesizing unit 9 to a telephone line. A control unit 11 controls each unit.

Next, the operation of the voice recognition and notification system according to the present invention will be described with reference to the flowchart of FIG. When a suspicious person enters, for example, microphones installed in various places, the words "Sasaki-san?"
And so on. This word is set as a keyword for the security report, and the voices of "Is Sasaki-san?" Of a plurality of persons registered as report personnel are feature-extracted in advance and registered in the memory unit 4. A signal from the microphone is input from a voice input unit 1 (step 1, hereinafter abbreviated as ST1), a feature is extracted by a voice analysis unit 2 via a control unit 11 (ST2), and the extracted data is temporarily stored in a storage unit 3. Record (ST3).

In response to the recording in the storage unit 3, the characteristic data registered in the memory unit 4 is read out via the control unit 11,
The determination unit 5 compares the data with the data read from the storage unit 3 via the control unit 11 (ST4). If it is equal to or higher than the predetermined coincidence rate (ST5: Yes), the control unit 11 based on this determination
(ST6), reads out a telephone number registered as a security report destination from the telephone number storage unit 6, generates a required dial signal via the dial signal utterance unit 7, and outputs the required dial signal. The data is transmitted to the telephone line (ST7). In response to the incoming call response from the other party (ST8: Ye
s), registered in the message storage unit 8, for example,
The message data such as "This is the XX-YYYY-ZZZZ number XX, burglary has invaded" is read out via the control unit 11 and synthesized into voice by the voice synthesis unit 9, and this voice is output to the output unit 10. For example, the information is repeatedly transmitted to the telephone line a required number of times (ST9).

If no registered voice matching the voice from the microphone is found (ST5: No), all data registered in the memory unit 4 are searched sequentially, and if no data matches (ST10: No). ), It is determined that the voice input from the microphone is not the voice of a person registered as a reporter (ST11), and no report is made assuming that no abnormal situation has occurred. The data recorded in the storage unit 3 is deleted when the notification device is started (ST6) or when the discrepancy is determined.

In the above description, the voice of the message is synthesized into the voice by the voice synthesizer 9 based on the data from the message storage unit 8. However, the message is recorded on a magnetic recording tape or a compact disk. This sound may be reproduced and transmitted.

[0011]

As described above, according to the voice recognition and notification system of the present invention, when a registered speaker utters a registered voice (specific word), a security notification or the like is automatically performed. Since it is performed, for example, if it is installed in a store or the like that operates at night with a small number of clerks, it is convenient that an intruder or the like can make a notification in a situation where it is difficult to operate an emergency button or the like.

[Brief description of the drawings]

FIG. 1 is a block diagram of a main part of an embodiment of a voice recognition and notification system according to the present invention.

FIG. 2 is a flowchart illustrating an operation of the voice recognition and notification system according to the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Voice input part 2 Voice analysis part 3 Storage part 4 Memory part 5 Discrimination part 6 Telephone number storage part 7 Dial signal generation part 8 Message storage part 9 Voice synthesis part 10 Output part 11 Control part

Claims (1)

(57) [Claims] 1. A voice input unit for inputting voice, a voice analysis unit for analyzing input voice and extracting feature data, a storage unit for storing data from the voice analysis unit, and a notification when a security abnormality occurs. A memory unit for storing voice feature data set for use, a discriminating unit for discriminating by comparing data recorded in the memory unit with data read from the memory unit, and storing a telephone number of a security report destination or the like. A telephone number storage unit, a dial signal generation unit that generates a dial signal based on data read from the telephone number storage unit, a message storage unit that stores a message voice such as a security report, the voice input unit, and voice analysis. Department,
The control section controls a storage section, a memory section, a determination section, a telephone number storage section, a dial signal generation section and a message storage section, and dials a telephone number read from the telephone number storage section based on the determination of the determination section. A voice recognition and notification system in which a call is transmitted and transmitted to a telephone line, and a voice from a message storage unit is output in response to an incoming call.