JP2001256035A - Sound data input/output system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve a problem that a sound data input/output device capable of flexibly performing input/output of sound data is desired. SOLUTION: The sound data input/output device is constituted by a portable terminal 10 for input/output of the sound data and a host computer 21. A CPU 12 of the terminal 10 is made possible to perform communication with the host computer 21 via a radio part 20. The host computer 21 performs an analysis processing and an interactive control processing and is provided with a large-capacity storage device. Thus, since data to be required for input/output of the sound data is only to be mainly stored in a storage device of the host computer 21, the capacity of a RAM 14 of the terminal 10 is reduced.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice data input / output system that can be used for data collection, work instructions, data search, and the like.

[0002]

2. Description of the Related Art Heretofore, there has been known a portable voice data input / output terminal device in which an operator can input data by voice. For example, JP-A-59-27346 and JP-A-61-290530 disclose this type of portable audio data input / output terminal device.

According to the portable audio data input / output terminal device described in JP-A-59-27346, measurement data read from each instrument by a measurer is input as audio to a portable radio, and The data is supplied to the speech recognition device via the transmission line. Then, the voice data is recognized by the voice recognition device, and the recognized voice data, that is, the measurement data is stored as digital data. The recognized measurement data is returned to the portable wireless device via the transmission line, and is appropriately checked by a measurement person.

[0004] In the apparatus described in Japanese Patent Application Laid-Open No. 61-290530, while performing a landing operation, necessary information is provided in accordance with a voice output command from a host computer through a wireless voice input device equipped with a helmet. Voice input. Then, the input information is fed back and output as voice to the input person, so that the operator can check the input information. The input information is checked based on inputting "yes" if the voice output to be fed back is exactly as input by the operator, and inputting "no" if incorrect.

A similar data input method is disclosed in, for example, Japanese Unexamined Patent Publication No. 3-15099, in addition to the above publication.

[0006]

According to the conventional portable voice data input / output terminal device capable of inputting / outputting data by voice, a worker or the like can input data while working. In addition, since the input data can be confirmed by the synthesized voice, there is an advantage that accurate data input can be performed while continuing a predetermined operation.

However, in a conventional audio data input / output device, as described in, for example, Japanese Patent Application Laid-Open No. 61-290530, data input / output is performed according to a predetermined procedure specified in a management computer or the like. However, there is a disadvantage that the flexibility in the data input / output procedure is poor. Therefore, in the case of the conventional voice data input / output device, it is not possible for the operator to ask a question with respect to the input instruction output in the synthesized voice and to answer the question. On the other hand, when the input voice of the operator cannot be recognized, the apparatus cannot make an inquiry to the operator. That is, according to the conventional voice data input / output device, the voice data input by the operator can be confirmed, but the voice data can be input only according to a predetermined procedure. Therefore, even if the operator does not understand the meaning of the voice instruction given from the device during the operation, the operator must continue to input the voice data, and the reliability of the voice data input cannot be sufficiently guaranteed. was there.

Further, even when the voice data input / output device cannot correctly grasp the meaning of the input data input by the operator, if the operator confirms that the input voice data is correct, the device cannot correctly understand the meaning. Processing must be performed based on the data, and erroneous processing may be performed. Therefore, the present invention provides a voice data input / output system including a portable terminal device and a host computer, and allows the portable terminal device to have an interactive function with an operator, so that data input / output between the operator and the device is interactive. An object of the present invention is to provide a voice data input / output system capable of efficiently performing data input / output operation by voice.

[0009]

According to the first aspect of the present invention,
An audio data input / output system including an audio data input / output mobile terminal device and a host computer, wherein the audio data input / output mobile terminal device includes means for outputting an instruction voice,
Speech recognition means for recognizing speech data input in response to the output of the instruction speech, means for outputting given data as synthesized speech, and wireless means for performing wireless communication with a host computer In the host computer, based on the analysis result of the analysis means for analyzing the type of voice data recognized by the voice recognition means given via the wireless means, and the analysis means, the input data is appropriate, When it is the data that answers the instruction voice, the data is adopted, and the input data is appropriate, but when it is the inquiry data from the operator, the data that responds to the inquiry from the operator as the data to be output. Is determined, and if it is determined that the input data is not appropriate, the inquiry data for dialog To determine, characterized in that is provided with interactive control means for giving to the audio data input portable terminal apparatus determined data via the wireless unit,
It is an audio data input / output system.

[0010]

The operation of the present invention will be described with reference to FIG. The input voice is provided to voice recognition means 1. The voice recognition means 1 is provided with a dictionary registered in advance. The speech recognition means 1 recognizes what content the input speech has while referring to the dictionary. Therefore, the operator can input data by voice and does not need to operate a keyboard or the like.

The content recognized by the voice recognition means 1, that is, the recognition data is given to the analysis means 2. Analysis means 2
Analyzes the recognition data and determines whether there is a contradiction or error in the data type or the data. Then, the analysis result is provided to the dialog control means 3 together with the recognition data.
The dialogue control means 3 determines the content to be interacted with the operator who has input the voice data, based on the recognition data and the analysis result. The contents to be interacted with are, for example, when there is an inconsistency or an error in the input voice, a voice for prompting re-input or requesting correction of the input is determined. In addition, for ambiguous input data, a voice for asking an ambiguous point is determined. Then, the determined contents are given to the speech synthesis means 4.

The voice synthesizing means 4 converts a character string expressing voice into actual voice and outputs it as synthesized voice. Therefore, the operator does not need to look at the display or the like to receive the output data, and can confirm the data contents not by visual sense but by hearing. The operator who has heard the synthesized voice output from the voice synthesis means 4 inputs a voice corresponding to the synthesized voice again to the apparatus.

[0013]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 2 is a block diagram showing the configuration of the portable audio data input / output terminal device according to one embodiment of the present invention. The terminal device 10 includes a voice recognition unit 11 for recognizing an input voice, a CPU 12 for processing a recognition result recognized by the voice recognition unit 11,
ROM 13 storing the operation program and the dictionary of
R as a memory used when the CPU 12 performs processing
An AM 14, a voice synthesizing unit 15 for converting output data into a synthesized voice, and a battery 16 for supplying a driving power supply for the input / output terminal device 10 are provided. Further, the portable audio data input / output terminal device 10 is provided with a headset having a speaker 17 and a microphone 18 as a detachable external device. The voice recognition unit 11 converts an analog voice signal input from the microphone 18 into a digital signal and recognizes voice data. Further, the portable audio data input / output terminal device 10 includes a wireless unit 20. The CPU 12 is capable of wirelessly communicating with a host computer 21 disposed at a predetermined place via the wireless unit 20. The host computer 21 performs an analysis process and a dialogue control process, as described later. Normally, the host computer 21 has a large-capacity storage device, so that data necessary for the audio data input / output system may be mainly stored in the large-capacity storage device of the host computer 21. When data is needed in the audio data input / output terminal device 10, the data in the host computer 21 may be read and stored in the RAM 14. Therefore, the capacity of the RAM 14 in the audio data input / output terminal device 10 can be reduced, and the configuration of the terminal device 10 can be reduced in size. The CPU 12 controls the portable audio data input / output terminal device 10 based on analysis processing and dialog control processing performed by the host computer 21 while exchanging data with the host computer 21 via the wireless unit 20. .

In the analysis process, the type of the recognized voice data provided from the voice recognition unit 11 is analyzed, and it is determined whether or not the content has an inconsistency or an error. In the dialogue control processing, character string data expressing the synthesized speech given to the speech synthesis unit 15 is determined.

The voice synthesizer 15 converts the character string data sent from the CPU 12 into an analog signal which is a synthesized voice, and outputs the analog signal to the speaker 17. FIG. 3 is a flowchart illustrating an example of processing performed by the CPU 12 and the host computer 21 in FIG. In the following description, for the processing performed by the cooperation of the CPU 12 and the host computer 21, the control operation of this system will be specifically described as the processing of the CPU 12 for convenience of description. Next, a description will be given along the flow of FIG. 3 with reference to FIG. The following description will be made on the case where the portable voice data input / output terminal device 10 is owned by a worker of an electric power company and a test is performed to check whether a transformer provided on a telephone pole is normally operating. The case of using the result input work will be described as an example.

When an operation switch (not shown) of the portable audio data input / output terminal device 10 is turned on and the operation is started, character string data representing an audio to be synthesized is supplied from the CPU 12 to the audio synthesis unit 15. Then, the speech synthesis unit 15 generates a synthesized speech. Then, the sound is output from the speaker 17 of the headset (step S1). For example, a synthesized voice "Please input the investigated device number" is output.

The CPU 12 determines whether or not there is recognition data from the speech recognition unit 11 (step S2). If there is no recognition data within a predetermined time, the speech synthesis unit 15
Again, character string data representing the voice to be synthesized is given,
The same synthesized voice is output from the voice synthesizer 15. This is repeated while there is no recognition data, and the state of waiting for recognition data is continued.

The operator inputs data by voice using the microphone 18 in accordance with the synthesized voice output from the speaker 17. For example, "Transformer C of telephone pole K1
Enter the number of the inspected part, such as "3". The voice data input from the microphone 18 is transmitted to the voice recognition unit 1
1 and converted from an analog audio signal to a digital signal, and the contents of the audio data are recognized. The recognized data is sent to the CPU 12
Sent to

If it is determined in step S2 that there is recognition data, the recognition data is sent to the voice synthesizing unit 15 (step S3), and the voice synthesizing unit 15 generates a synthesized voice. (Step S4). Therefore, the operator can confirm the voice data input by the user from the microphone 18 by the synthesized voice output from the voice synthesizer 15 via the speaker 17. Then, at the time of this confirmation, if the synthesized voice matches the voice data input by the user,
The operator inputs “yes” to the microphone 18. On the other hand, if the voice input by the user is different from the output synthesized voice, it means that the input voice has not been correctly recognized in the voice recognition unit 11, and thus “No” is input.

The entered "yes" or "no"
The voice is recognized by the voice recognition unit 11 and given to the CPU 12.
The CPU 12 checks whether the recognition data is "yes" (step S5). As a result, if it is confirmed that the answer is “Yes”, the input data previously input (step S
Is analyzed (step S2).
6).

On the other hand, if the recognition data is not "Yes", an inquiry voice is determined (step S1).
0). For example, "Please enter data again"
Is determined. This is converted into a synthesized voice by the voice synthesis unit 15 and output from the speaker 17. In response, the operator inputs voice data again.

Data analysis by the CPU 12 (step S
After 6), it is determined whether or not the data is of an appropriate type, and whether or not the data has inconsistency or error (step S).
7). If the data is appropriate, the data is adopted (step S8). The adopted data is stored in the RAM 14. Then, in order to specify the data to be input next by the operator, character string data representing the content of the instruction is determined by the CPU 12 (step S9). Then, the data is given to the voice synthesizing unit 15, converted into a synthesized voice, and output from the speaker 17 (step S1). For example, this synthesized voice is "Please input whether there is a failure"
And so on. The operator operates the microphone 1 according to the instruction.
Next, the next data will be input using 8.

If it is determined in step S7 that the input data is not appropriate, the CPU 12 determines the inquiry data for the dialog (step S10). For example, "Please enter data again." Or "Data entered now is inconsistent with data entered earlier."
Enter the correct data again. And the like are determined. Then, the inquiry data is converted into a synthesized voice by the voice synthesizer 15 and output from the speaker 17 (step S1).

If the data employed in step S8 is, for example, inquiry data from the operator, "What is the current instruction?", The next data determined in step S9 is the operator's It will be the data that answers the inquiry from. As described above, according to this embodiment, the operator and the portable voice data input / output terminal device 10 can exchange data interactively and can input data interactively, so that correct data can be accurately input. Can be entered. In particular, even an operator who is unfamiliar with data input can easily perform correct data input.

In the above embodiment, a portable voice data input / output terminal device for a worker working on a telephone pole, for example, is taken as an example. The input / output device suitable for various uses can be obtained simply by changing In the above-described embodiment, the portable audio data input / output terminal device has been described as an example. However, the present invention can be applied to a non-portable audio data input / output device.

In addition, the present invention can be variously modified in accordance with the configuration described in the claims.

[0027]

Since the present invention is configured as described above, data input is performed interactively between the operator and the device, and when the meaning is not understood, it can be confirmed. You can enter data. Further, the operator can input data correctly without having to use his / her hand for data input and without checking input data on a display or the like. Therefore, the efficiency of the data input operation can be improved.

[Brief description of the drawings]

FIG. 1 is a diagram for explaining the operation of the present invention.

FIG. 2 is a configuration block diagram of a portable audio data input / output terminal device according to an embodiment of the present invention.

FIG. 3 is a flowchart illustrating an operation of the audio data input / output terminal device shown in FIG. 2;

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Voice recognition means 2 Analysis means 3 Dialogue control means 4 Voice synthesis means 10 Portable data input / output terminal device 11 Voice recognition unit 12 CPU 15 Voice synthesis unit 20 Radio unit 21 Host computer

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G10L 15/22 G10L 3/00 551P 571T

Claims (1)

[Claims] An audio data input / output system including an audio data input / output portable terminal device and a host computer, wherein the audio data input / output portable terminal device has means for outputting an instruction voice, and responds to the output of the instruction voice. Voice recognition means for recognizing input voice data, means for outputting given data as synthesized voice, and wireless means for performing wireless communication with a host computer. Analyzing means for analyzing the type of voice data recognized by the voice recognizing means provided via the wireless means, and based on the analysis result of the analyzing means, the input data is appropriate, and the data responding to the instruction voice In the case of, the data is adopted and the input data is appropriate, but when it is the inquiry data from the operator, As the data to be output, data that responds to the inquiry from the operator is determined. When it is determined that the input data is not appropriate, the inquiry data for the dialog is determined as the data to be output, and the determined data is An audio data input / output system, further comprising: a dialogue control unit for giving the audio data input / output to the portable terminal device via the wireless unit.