JPS5850599A - Output monitoring method for voice response system - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

DETAILED DESCRIPTION OF THE INVENTION The present invention branches a diagnostic voice message instructed by the main controller from the output of the voice response s and inputs it into the voice recognition section to output a specific voice output i&! This invention relates to an output monitoring method for a voice response system that performs self-diagnosis.

Conventionally, a voice input device that receives a voice input includes a voice response unit that guides the speaker's loud input according to commands from the main control device, and a voice response unit that guides the voice input by a voice input t-1. After outputting a message of guidance from the voice response section, a signal sound is emitted to prompt the person to speak, and in response to this, each digit of the specified number, such as an account number or PIN number, is pronounced in sequence. This is input to the voice recognition section, the parameter extraction section extracts the percentage through a filter, etc., the matching section matches it with the standard features stored in the dictionary, and the Omi judgment section gives the matching result. This is to make a judgment. As mentioned above, the main ii
It is connected online with the TTM device and the round voice response unit is connected to the voice liIiig! If an abnormality such as an error occurs in a voice response system that is combined through parts, m, and tt, it can be checked with one error detection path for each individual device, but decisions as a system must go through the speaker. Therefore, it was actually rare in the kingdom.

In this case, it is desirable to be able to self-diagnose at all times.

SUMMARY OF THE INVENTION It is an object of the present invention to provide an output monitoring system for a voice response system that is capable of constantly self-disconnecting a voice response system that is connected online with the above-mentioned main controller.

In order to achieve the above object, the output monitoring method of the voice response system of the present invention includes a voice response section that outputs a voice message that is instructed to guide the voice input of the speaker, and a voice response section that outputs a voice message that guides the voice input of the speaker. In the fyIII response system, which consists of a voice input unit with 41 channels, the voice message output according to the instruction from the main *t+lI41 device is branched and input into the voice-vR unit to output a constant voice t-1. It is characterized by adding 41J to the timed voice instruction of the diagnostic voice message from the control device and outputting the voice response.

The present invention will now be described in detail with reference to some examples.

This is an explanatory diagram of the configuration of an embodiment of the present invention, and shows an outline of a voice response system consisting of a voice response unit and voice gkIts.

In the same figure, the voice response s2 connected online to the main control device t11 receives and receives the command code, creates a digital signal of a voice message to guide the speaker, and creates a D/A
A voice message is output through the converter 1. At the same time, the command code from the main controller is branched to perform diagnosis I&
Input into the I/O instruction circuit 11 and the judgment circuit 12, and perform the diagnosis 1lia.
! The fiber instruction circuit 11 determines whether the voice message created from the instruction code is a diagnostic message.

#If it is a necessary message, a diagnosis instruction is issued to the determination circuit 12, and a recognition instruction is issued to the voice recording section 4.

On the other hand, the audio signal outputted from the audio response section 2 via the D/A converter 1 is branched and converted into a digital signal through the A/D converter 5, and sent to the audio transducer section 4. Then, the judgment diagram w is determined based on a specific voice output included in the voice message, such as “yes” or “no”. r
12, collates it with the specific voice instruction included in the corresponding command code, and sends the determination result to the main controller.

In this manner, self-diagnosis can be performed at all times by outputting the desired voice message while the voice response system is in the online operating state.

As explained above, according to the present invention, a diagnostic voice message instructed by the main 111I is branched from the output of the voice response section and sent to the voice recognition section to output a specific voice 11&! The system is designed to allow users to conduct self-diagnosis. This allows the ability to send normal voice messages to be constantly monitored. It is also possible to set up a voice message in use for diagnosis without preparing a voice message for diagnosis, and to constantly monitor the output.

[Brief explanation of drawings]

The figure is a detailed explanatory diagram of the present invention. In the figure, 1 is a D/A converter, 2 is a mine response unit, 6 is an AID converter, and 4 is a voice recognition i.
f! ! 11 is a diagnostic acid resistance indicating circuit, and 12 is a determination circuit. Patent applicant Fujitsu Co., Ltd. Sub-agent Patent attorney 1) Shigeru Saka

Claims (1)

[Claims] In a voice response system consisting of a voice response unit that outputs a voice message that guides the speaker's voice input as instructed by the main control device, and a voice human power that is connected to the voice input of the speaker, instructions from the main tBIJil1M- The outputted voice message is branched and put into the voice storage section for specific voice output, which is compared with the specific voice instruction of the diagnostic voice message from the main control device to determine the voice response. An output monitoring method for a voice response system characterized by monitoring output.