Speech recognition device and computer-readable storage medium

Abstract

This speech recognition device comprises: a speech acceptance unit for accepting speech information representing one command among a plurality of commands; a speech recognition unit for performing speech recognition of the one command on the basis of the speech information accepted by the speech acceptance unit and for computing a reliability score for the recognition result of the one command; a condition storage unit for storing a plurality of conditions used in determining whether to execute a verification process for a recognition result, in association with a plurality of respective commands; a determination unit for determining whether to execute a verification process on the basis of one condition among a plurality of conditions stored in the condition storage unit and the reliability score computed by the speech recognition unit; and an output unit for outputting the recognition result without executing the verification process in a case where the determination unit determined to not execute the verification process.

Description

[Technical Field]

[0001] The present disclosure relates to a speech recognition device and a computer-readable storage medium. [Background technology]

[0002] There is known a speech recognition device that recognizes spoken speech, converts it into text, and calculates the reliability of the converted text. In such a speech recognition device, a confirmation step is executed to ask the user to confirm the converted text depending on the calculated reliability (for example, Patent Document 1). In other words, when the reliability is low, the speech recognition device asks the user to confirm whether the converted text is correct, and when the reliability is high, the confirmation step is omitted. This reduces the number of user operations on the speech recognition device, thereby improving the convenience of the speech recognition device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-233305 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in conventional speech recognition devices, whether or not to perform the confirmation process is determined regardless of the importance of the content of the information converted to text by speech recognition. Therefore, for example, even if the content of the information converted to text is not important, the confirmation process may be performed. Therefore, there is a need for further improvement in the user convenience of speech recognition devices.

[0005] An object of the present disclosure is to provide a voice recognition device with improved convenience. [Means for solving the problem]

[0006] The voice recognition device includes a voice receiving unit that receives voice information indicating one of a plurality of commands; a voice recognition unit that performs voice recognition of the one command based on the voice information received by the voice receiving unit and calculates the reliability of the recognition result of the one command; a condition storage unit that stores a plurality of conditions used to determine whether or not to execute a confirmation process of the recognition result, each corresponding to a plurality of commands; a judgment unit that judges whether or not to execute the confirmation process based on one of the plurality of conditions stored in the condition storage unit and the reliability calculated by the voice recognition unit; and an output unit that outputs the recognition result without executing the confirmation process when the judgment unit judges not to execute the confirmation process.

[0007] A computer-readable storage medium stores instructions that cause a computer to receive voice information indicating one of a plurality of commands, perform voice recognition of the one command based on the received voice information and calculate the reliability of the recognition result of the one command, determine whether to perform the confirmation step based on one of a plurality of conditions stored in correspondence with each of the plurality of commands and used to determine whether to perform a confirmation step of the recognition result and the calculated reliability, and output the recognition result without performing the confirmation step if it is determined not to perform the confirmation step. [Effects of the Invention]

[0008] According to one aspect of the present disclosure, it is possible to provide a voice recognition device with improved convenience. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 2 is a block diagram showing an example of a hardware configuration of a machine tool. [Figure 2] FIG. 2 is a block diagram showing an example of functions of a voice recognition device. [Figure 3] FIG. 2 is a block diagram showing an example of the functions of a voice recognition unit. [Figure 4] 3A and 3B are diagrams illustrating an example of commands and conditions stored in a condition storage unit. [Figure 5] FIG. 10 is a diagram showing an example of a confirmation screen displayed in a confirmation step. [Figure 6] 10 is a flowchart illustrating an example of processing executed in a preparation stage. [Figure 7] 10 is a flowchart illustrating an example of a process executed in an operation stage. [Figure 8] FIG. 1 is a block diagram showing an example of functions of a voice recognition device including an update unit. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, according to an embodiment of the present disclosure, Voice recognition device The following description will be given with reference to the drawings. Note that not all combinations of features described in the following embodiments are necessarily required to solve the problems. In addition, more detailed description than necessary may be omitted. Furthermore, the following description of the embodiments and the drawings are provided to enable those skilled in the art to fully understand the present disclosure, and are not intended to limit the scope of the claims.

[0011] A speech recognition device is a device that performs speech recognition. Speech recognition is a process of converting spoken speech into text. The concept of speech recognition may also include converting spoken speech into information that a computer can understand.

[0012] The speech recognition device is implemented in, for example, a numerical control device that controls industrial machinery. The speech recognition device may also be implemented in a server, a personal computer (PC), or a portable tablet that is connected to the numerical control device via a wired or wireless connection.

[0013] The industrial machines include machine tools, injection molding machines, wire electric discharge machines, and industrial robots. The machine tools are, for example, lathes, machining centers, drilling centers, and multi-tasking machines. In the following, an embodiment will be described in which the voice recognition device is implemented in a numerical control device that controls the machine tools.

[0014] FIG. 1 is a block diagram showing an example of the hardware configuration of a machine tool equipped with a numerical control device.

[0015] The machine tool 1 includes a numerical control device 2, an input / output device 3, a servo amplifier 4, a servo motor 5, a spindle amplifier 6, a spindle motor 7, an auxiliary device 8, and a microphone 9.

[0016] The numerical control device 2 is a device that controls the entire machine tool 1. The numerical control device 2 includes a hardware processor 201, a bus 202, a ROM (Read Only Memory) 203, a RAM (Random Access Memory) 204, and a non-volatile memory 205.

[0017] The hardware processor 201 is a processor that controls the entire numerical control device 2 in accordance with a system program. The hardware processor 201 reads the system program stored in the ROM 203 via the bus 202 and performs various processes based on the system program. The hardware processor 201 controls the servo motor 5 and the spindle motor 7 based on the machining program. The hardware processor 201 is, for example, a CPU (Central Processing Unit) or an electronic circuit.

[0018] The hardware processor 201 analyzes the machining program and outputs control commands to the servo motor 5 and the spindle motor 7, for example, for each control period.

[0019] The bus 202 is a communication path that connects the various pieces of hardware within the numerical control device 2. The various pieces of hardware within the numerical control device 2 exchange data via the bus 202.

[0020] The ROM 203 is a storage device that stores a system program for controlling the entire numerical control device 2. The ROM 203 may also store a voice recognition program. The ROM 203 is a computer-readable storage medium.

[0021] The RAM 204 is a storage device that temporarily stores various data and functions as a work area for the hardware processor 201 to process various data.

[0022] The nonvolatile memory 205 is a storage device that retains data even when the machine tool 1 is turned off and no power is supplied to the numerical control device 2. The nonvolatile memory 205 stores, for example, machining programs and various parameters. The nonvolatile memory 205 is a computer-readable storage medium. The nonvolatile memory 205 is configured, for example, by a battery-backed memory or an SSD (Solid State Drive).

[0023] The numerical control device 2 further includes a first interface 206 , an axis control circuit 207 , a spindle control circuit 208 , a PLC (Programmable Logic Controller) 209 , an I / O unit 210 , and a second interface 211 .

[0024] The first interface 206 is an interface that connects the bus 202 and the input / output device 3. The first interface 206 sends various data processed by the hardware processor 201 to the input / output device 3, for example.

[0025] The input / output device 3 is a device that receives and displays various data via the first interface 206. The input / output device 3 also accepts input of various data and sends the data to, for example, the hardware processor 201 via the first interface 206.

[0026] The input / output device 3 is, for example, a touch panel. When the input / output device 3 is a touch panel, the input / output device 3 is, for example, a capacitive touch panel. Note that the touch panel is not limited to a capacitive touch panel and may be a touch panel of another type. The input / output device 3 is installed in an operation panel (not shown) in which the numerical control device 2 is housed.

[0027] The axis control circuit 207 is a circuit that controls the servo motor 5. The axis control circuit 207 receives a control command from the hardware processor 201 and outputs a command to drive the servo motor 5 to the servo amplifier 4. The axis control circuit 207 sends, for example, a torque command to control the torque of the servo motor 5 to the servo amplifier 4.

[0028] The servo amplifier 4 receives a command from the axis control circuit 207 and supplies a current to the servo motor 5 .

[0029] The servo motor 5 is driven by receiving a current supply from the servo amplifier 4. The servo motor 5 is connected to, for example, a ball screw that drives a tool post. When the servo motor 5 is driven, structures of the machine tool 1, such as the tool post, move in the directions of the control axes. The servo motor 5 has a built-in encoder (not shown) that detects the position and feed rate of the control axis. Position feedback information and speed feedback information indicating the position and feed rate of the control axis, respectively, detected by the encoder are fed back to the axis control circuit 207. In this way, the axis control circuit 207 performs feedback control of the control axis.

[0030] The spindle control circuit 208 is a circuit for controlling the spindle motor 7. The spindle control circuit 208 receives a control command from the hardware processor 201 and sends a command to the spindle amplifier 6 to drive the spindle motor 7. The spindle control circuit 208 sends, for example, a spindle speed command to the spindle amplifier 6 to control the rotation speed of the spindle motor 7.

[0031] The spindle amplifier 6 receives a command from the spindle control circuit 208 and supplies a current to the spindle motor 7 .

[0032] The spindle motor 7 is driven by receiving a current supplied from the spindle amplifier 6. The spindle motor 7 is connected to the main shaft and rotates the main shaft.

[0033] The PLC 209 is a device that executes a ladder program to control the auxiliary device 8. The PLC 209 sends commands to the auxiliary device 8 via an I / O unit 210.

[0034] The I / O unit 210 is an interface that connects the PLC 209 and the auxiliary device 8. The I / O unit 210 sends a command received from the PLC 209 to the auxiliary device 8.

[0035] The auxiliary device 8 is a device that is installed in the machine tool 1 and performs auxiliary operations in the machine tool 1. The auxiliary device 8 operates based on commands received from the I / O unit 210. The auxiliary device 8 may also be a device that is installed in the periphery of the machine tool 1. The auxiliary device 8 is, for example, a tool changer, a cutting fluid injection device, or an opening / closing door drive device.

[0036] The second interface 211 is an interface that connects the bus 202 and the microphone 9. The second interface 211 sends, for example, audio information output from the microphone 9 to the hardware processor 201.

[0037] The microphone 9 is an acoustic device that captures sound and converts it into audio information. Here, the audio information is an electrical signal. The microphone 9 sends the audio information to the hardware processor 201 via the second interface 211.

[0038] Next, the function of the voice recognition device 20 will be described.

[0039] 2 is a block diagram showing an example of the functions of the voice recognition device 20 implemented in the numerical control device 2. The voice recognition device 20 includes a voice receiving unit 21, a voice recognition unit 22, a condition storage unit 23, a judgment unit 24, a confirmation execution unit 25, and an output unit 26.

[0040] The voice receiving unit 21, the voice recognition unit 22, the determination unit 24, the confirmation execution unit 25, and the output unit 26 are realized, for example, by the hardware processor 201 performing arithmetic processing using the system program and the voice recognition program stored in the ROM 203, and various data stored in the nonvolatile memory 205. The condition storage unit 23 is realized by storing various data in the RAM 204 or the nonvolatile memory 205.

[0041] The voice receiving unit 21 receives voice information of a voice uttered by a user. The voice uttered by the user includes, for example, a command for the numerical control device 2. The user utters, for example, a voice indicating one command out of a plurality of commands. In other words, the voice receiving unit 21 receives voice information indicating one command out of a plurality of commands.

[0042] The voice receiving unit 21 receives input of voice information from, for example, the microphone 9. The voice information is, for example, an analog signal representing a voice uttered by a speaker. The voice information may also be a digital signal converted from the analog signal representing the voice.

[0043] The voice recognition unit 22 performs voice recognition of a command based on the voice information received by the voice receiving unit 21, and calculates the reliability of the recognition result of the command. In other words, the voice recognition unit 22 recognizes what kind of command the voice information is. Here, the function of the voice recognition unit 22 will be described in detail.

[0044] 3 is a block diagram showing an example of the functions of the speech recognition unit 22. The speech recognition unit 22 includes an acoustic model storage unit 221, a dictionary storage unit 222, a recognition processing unit 223, and a grammar storage unit 224.

[0045] The acoustic model storage unit 221 stores an acoustic model for identifying phonemes contained in speech information. The acoustic model is used to extract features from the waveform of speech uttered by a speaker and identify the phonemes. The features include, for example, the strength of the speech and frequency characteristics.

[0046] The acoustic model is generated, for example, by machine learning using speech information of a speech uttered by a speaker as training data. The acoustic model storage unit 221 may store a plurality of acoustic models corresponding to each language.

[0047] The dictionary storage unit 222 stores a dictionary. The dictionary includes, for example, commands used when various operations or settings are performed on the numerical control device 2. The dictionary may also include technical terms used when various operations or settings are performed on the numerical control device 2.

[0048] The recognition processing unit 223 determines the sequence of phonemes indicated by the speech information using an acoustic model. For example, when a voice corresponding to "external interface" in Japanese is uttered, the recognition processing unit 223 determines the Japanese phoneme sequence "gaibuiNtafe:su" corresponding to "external interface." The recognition processing unit 223 also determines a character string and a word sequence that match the phoneme sequence using a dictionary stored in the dictionary storage unit 222. For example, the recognition processing unit 223 determines that the phoneme sequence "gaibuiNtafe:su" matches the character string corresponding to "external interface" in Japanese.

[0049] The grammar storage unit 224 stores grammar models that define the rules for constructing sentences. A grammar model indicates the probability of a word appearing in speech information. In other words, a grammar model indicates the probability that a certain word appears after another word. A grammar model is used to evaluate whether a string of characters or a sequence of words is appropriate for a language. A grammar model is also called a language model.

[0050] The recognition processing unit 223 uses a dictionary and a grammar model to recognize the speech information so that the speech information becomes a character string and a word sequence appropriate for the language. That is, the recognition processing unit 223 obtains candidates for an appropriate character string and word sequence from the speech information. In other words, the recognition processing unit 223 recognizes commands by performing speech recognition.

[0051] The recognition processing unit 223 also calculates the reliability of the obtained candidates. The reliability is a measure of how reliable the obtained character string and word sequence are. The reliability is calculated in the range of 0.0 to 1.0. A small reliability value means that many other candidates similar to the character string and word sequence have been obtained. On the other hand, a large reliability value means that there are no or few other candidates similar to the character string and word sequence. For example, the N-best method is used to calculate the reliability.

[0052] The condition storage unit 23 stores a plurality of conditions used to determine whether or not to execute a confirmation process of the recognition result, each corresponding to a plurality of commands. The confirmation process is a process in which the user approves or rejects the recognition result depending on whether the recognition result of the voice information is correct. The condition is, for example, a threshold value. When the condition is a threshold value, the condition storage unit 23 stores a plurality of threshold values ​​corresponding to each of the plurality of commands.

[0053] 4 is a diagram showing an example of commands and conditions stored in the condition storage unit 23. The condition storage unit 23 stores, for example, a transition command, a setting command, a drive command, and an approval command.

[0054] The transition command is a command that transitions the display screen. The transition command includes a home screen command and a network screen command. The home screen command is a command that transitions the display screen to the home screen. The network screen command is a command that transitions the display screen to the network screen.

[0055] The setting command is a command for setting a mode. The setting commands include an automatic mode command and a manual mode command. The automatic mode command is a command for setting the operation mode of the numerical control device 2 to the automatic mode. The manual mode command is a command for setting the operation mode of the numerical control device 2 to the manual mode.

[0056] The drive command is a command for driving at least one of the spindle and each controlled axis. The drive command includes a start command and a stop command. The start command is a command for starting the drive of at least one of the spindle and each controlled axis. The stop command is a command for stopping the drive of at least one of the spindle and each controlled axis.

[0057] The approval command is a command for approving or denying confirmation items on the confirmation screen. The confirmation screen is a screen that displays confirmation items on a display screen. Approval commands include a yes command and a no command. The yes command is a command for approving confirmation items. The no command is a command for denying confirmation items.

[0058] The condition storage unit 23 stores a plurality of conditions corresponding to these commands. The conditions stored in the condition storage unit 23 are, for example, threshold values ​​that are compared with the reliability of the recognition result calculated by the voice recognition unit 22.

[0059] For example, the condition storage unit 23 stores 0.6 as the condition corresponding to a transition command. The condition storage unit 23 also stores 0.7 as the condition corresponding to a setting command. The condition storage unit 23 also stores 0.8 as the condition corresponding to a drive command. The condition storage unit 23 also stores 0.9 as the condition corresponding to an approval command.

[0060] The determination unit 24 determines whether or not to execute the confirmation process based on one of the multiple conditions stored in the condition storage unit 23 and the reliability calculated by the voice recognition unit 22. For example, when the voice information is recognized as a transition command, the determination unit 24 compares the reliability calculated by the voice recognition unit 22 with the condition "0.6" stored in association with the transition command and determines whether or not to execute the confirmation process.

[0061] The judgment unit 24 judges not to execute the confirmation process when the reliability calculated by the voice recognition unit 22 is 0.6 or more, and judges to execute the confirmation process when the reliability calculated by the voice recognition unit 22 is less than 0.6.

[0062] Similarly, if the command recognized by the voice recognition unit 22 is a setting command and the calculated reliability is 0.7 or more, the judgment unit 24 judges not to execute the confirmation process. On the other hand, if the command recognized by the voice recognition unit 22 is a setting command and the calculated reliability is less than 0.7, the judgment unit 24 judges to execute the confirmation process.

[0063] Similarly, if the command recognized by the voice recognition unit 22 is a drive command and the calculated reliability is 0.8 or more, the judgment unit 24 judges not to execute the confirmation process. On the other hand, if the command recognized by the voice recognition unit 22 is a drive command and the calculated reliability is less than 0.8, the judgment unit 24 judges to execute the confirmation process.

[0064] Similarly, if the command recognized by the voice recognition unit 22 is an approval command and the calculated reliability is 0.9 or more, the judgment unit 24 judges not to execute the confirmation process. On the other hand, if the command recognized by the voice recognition unit 22 is an approval command and the calculated reliability is less than 0.9, the judgment unit 24 judges to execute the confirmation process.

[0065] When the determining unit 24 determines that the confirmation step should be performed, the confirmation executing unit 25 executes the confirmation step.

[0066] FIG. 5 is a diagram showing an example of a confirmation screen displayed in the confirmation step. FIG. 5 shows an example of the confirmation screen when the voice recognition unit 22 recognizes that the voice information indicates the "home screen." When the confirmation screen is displayed, the user inputs approval information. Approval information is information indicating approval or denial of the recognition result. For example, the user utters a voice "yes" indicating approval, or a voice "no" indicating denial. These voices are input as approval information.

[0067] In the confirmation process, the voice receiving unit 21 receives approval information indicating approval or rejection of the recognition result of the voice information. The voice recognition unit 22 performs voice recognition of the approval information received by the voice receiving unit 21 and calculates the reliability of the recognition result of the approval information. In other words, the voice recognition unit 22 recognizes the approval information as "yes" or "no" and calculates the reliability of this recognition result. Note that the approval information may be the same as the approval command stored in the condition storage unit 23.

[0068] The determination unit 24 determines whether to output the recognition result of the voice information recognized before the confirmation step, based on the conditions stored in association with the approval command stored in the condition storage unit 23 and the reliability of the approval information calculated by the voice recognition unit 22. In other words, the determination unit 24 determines whether to output the recognition result of the command uttered by the user, depending on whether the recognition result of the approval information and the reliability of the approval information satisfy the conditions.

[0069] For example, if the approval information recognized by the voice recognition unit 22 is "yes" and the calculated reliability of the approval information is 0.9 or more, the determination unit 24 determines to output the recognition result of the command uttered by the user. In this case, the user has confirmed that the recognition result of the command recognized by the voice recognition unit 22 is correct.

[0070] Furthermore, if the approval information recognized by the voice recognition unit 22 is "No" and the calculated reliability of the approval information is 0.9 or more, the judgment unit 24 judges not to output the recognition result of the voice information recognized before the confirmation step. In this case, the user has confirmed that the recognition result of the command recognized by the voice recognition unit 22 is incorrect.

[0071] Furthermore, if the approval information recognized by the voice recognition unit 22 is "yes" or "no" and the calculated reliability of the approval information is less than 0.9, the judgment unit 24 determines not to output the recognition result. In these cases, it means that it is not clear enough to be reliably certain whether the recognition result of the approval information is correct or incorrect.

[0072] When the determination unit 24 determines that the command recognition result should be output, the output unit 26 outputs the recognition result. The output unit 26 outputs the recognition result to, for example, a control unit (not shown) of the numerical control device 2. This enables the control unit to execute the command indicated by the recognition result. The output unit 26 may also display the command indicated by the recognition result on the display screen of the input / output device 3.

[0073] If the determination unit 24 determines not to output the recognition result, the voice recognition unit 22 may again receive voice information indicating a command. This allows the voice recognition device 20 to perform voice recognition of a command again even if the voice recognition device 20 fails to recognize the command once.

[0074] Next, a description will be given of the flow of processing executed in the voice recognition device 20. The voice recognition device 20 performs processing in a preparation stage and processing in an operation stage.

[0075] 6 is a flowchart showing an example of processing executed in a preparation stage of the speech recognition device 20. In the preparation stage, first, a grammar model, a dictionary, and an acoustic model generated in response to a plurality of commands are implemented in the speech recognition device 20 (step SA1). That is, the acoustic model storage unit 221 stores the acoustic model. Also, the dictionary storage unit 222 stores the dictionary. Also, the grammar storage unit 224 stores the grammar model. Note that the commands are designed according to, for example, the machine tool 1, the factory where the machine tool 1 is installed, the workers, etc.

[0076] Next, a plurality of conditions used to determine whether or not to execute the confirmation process are implemented in the voice recognition device 20 (step SA2). That is, the condition storage unit 23 stores the plurality of conditions used to determine whether or not to execute the confirmation process in association with the plurality of commands, respectively. This completes the preparatory process.

[0077] Next, the process in the operation stage will be described.

[0078] 7 is a flowchart showing an example of processing executed in the operation stage of the voice recognition device 20. In the operation stage, first, the voice receiving unit 21 receives voice information indicating one command out of a plurality of commands (step SB1).

[0079] Next, the voice recognition unit 22 performs voice recognition of the one command and calculates the reliability of the recognition result of the one command (step SB2).

[0080] Next, the decision unit 24 decides whether or not to execute a confirmation step (step SB3).

[0081] If the decision unit 24 decides not to execute the confirmation step (No in step SB3), the output unit 26 outputs the recognition result (step SB4), and the process ends.

[0082] If the determination unit 24 determines that the confirmation step should be executed (Yes in step SB3), the confirmation execution unit 25 executes the confirmation step. In the confirmation step, the confirmation execution unit 25 displays the recognition result on the display screen (step SB5). Next, the voice acceptance unit 21 accepts the approval information (step SB6).

[0083] If the approval information indicates "Yes" and the reliability of the approval information satisfies the condition (Yes in step SB7), the output unit 26 outputs the recognition result (step SB4), and the process ends.

[0084] If the approval information indicates "Yes" and the reliability of the approval information does not satisfy the condition, or if the approval information indicates "No" (No in step SB7), the voice accepting unit 21 accepts voice information again.

[0085] As described above, the voice recognition device 20 includes a voice receiving unit 21 that receives voice information indicating one command out of a plurality of commands; a voice recognition unit 22 that performs voice recognition of the one command based on the voice information received by the voice receiving unit 21 and calculates the reliability of the recognition result of the one command; a condition storage unit 23 that stores a plurality of conditions used to determine whether or not to execute a confirmation process of the recognition result, each corresponding to a plurality of commands; a judgment unit 24 that judges whether or not to execute the confirmation process based on one of the plurality of conditions stored in the condition storage unit 23 and the reliability calculated by the voice recognition unit 22; and an output unit 26 that outputs the recognition result without executing the confirmation process when the judgment unit 24 determines not to execute the confirmation process.

[0086] Therefore, the voice recognition device 20 can improve user convenience. Specifically, the number of confirmation steps is reduced depending on the reliability of the command recognition result. In other words, the number of operations the user has to perform on the voice recognition device 20 is reduced.

[0087] The voice recognition device 20 may further include an update unit that updates the conditions stored in the condition storage unit 23.

[0088] Fig. 8 is a block diagram showing an example of the functions of the speech recognition device 20 equipped with an update unit. Here, functions different from the functions of the speech recognition device 20 described using Fig. 2 will be described, and a description of the same functions as those of the speech recognition device 20 in Fig. 2 will be omitted.

[0089] The update unit 27 updates one condition corresponding to one command based on the approval information received by the voice reception unit 21 in the confirmation step.

[0090] For example, even if the reliability of the recognition result of the setting command is "0.65," which is lower than the condition "0.7" stored corresponding to the setting command, if approval information indicating "yes" is input in the confirmation process, the recognition result of the setting command by the voice recognition unit 22 is correct. In other words, no problem occurs even if the value of the condition stored corresponding to the setting command is changed to "0.6," which is lower than the calculated reliability. Therefore, when approval information indicating approval is received by the voice receiving unit 21 in the confirmation process, the update unit 27 can change the value of the condition stored corresponding to the setting command to a smaller value. By updating the condition by the update unit 27, the confirmation process can be omitted the next time the voice recognition unit 22 recognizes the setting command. In each update, the update unit 27 decreases the value of the condition by, for example, a predetermined value.

[0091] The update unit 27 may further update one of the conditions based on the acceptance history of the approval information. The acceptance history of the approval information is a record of past acceptance of approval information indicating approval or denial by the voice acceptance unit 21 in the confirmation process.

[0092] For example, if the reception history records multiple inputs of approval information indicating approval in the process of confirming the recognition result of the drive command, the update unit 27 can update the conditions stored corresponding to the drive command. Specifically, the update unit 27 can update the conditions stored corresponding to the drive command so as to decrease the value indicated by the conditions.

[0093] The update unit 27 may further update one condition based on system information. The system information is, for example, time information that the voice recognition device 20 has as system information. For example, during the day, it is highly likely that a manager, such as a factory manager, is at work. In other words, it is highly likely that a person who can be responsible for changing the conditions stored in the condition storage unit 23 is at work. Therefore, for example, it is possible to configure the update unit 27 to change the conditions stored in the condition storage unit 23 between 9:00 a.m. and 5:00 p.m.

[0094] In the above-described embodiment, the voice receiving unit 21 receives approval information indicating approval or denial as voice information in the confirmation process. However, the approval information may be received by an operation on the display screen of the input / output device 3 in the confirmation process.

[0095] The present disclosure is not limited to the above-described embodiments, and can be appropriately modified without departing from the spirit and scope of the present disclosure. In the present disclosure, any of the components of the embodiments can be modified or omitted. [Explanation of symbols]

[0096] 1 Machine tools 2. Numerical control device 20 Voice recognition device 21 Voice Reception Section 22 Voice Recognition Unit 221 Acoustic Model Storage Unit 222 Dictionary storage unit 223 Recognition processing section 224 Grammar memory section 23 Condition memory section 24 Judgment Department 25 Verification Execution Department 26 Output section 27 Update section 201 Hardware Processor 202 Bus 203 ROM 204 RAM 205 Non-volatile memory 206 First Interface 207 Axis Control Circuit 208 Spindle control circuit 209 PLC 210 I / O units 211 Second Interface 3 Input / Output Devices 4 Servo amplifiers 5 Servo motors 6 Spindle amplifier 7 Spindle motor 8 Auxiliary equipment 9 Microphone

Claims

1. a voice receiving unit that receives voice information indicating one command among the plurality of commands; a voice recognition unit that performs voice recognition of the one command based on the voice information received by the voice receiving unit and calculates the reliability of the recognition result of the one command; a condition storage unit that stores a plurality of conditions used to determine whether or not to execute the step of confirming the recognition result, in association with the plurality of commands; a determination unit that determines whether to execute the confirmation step based on one of the plurality of conditions stored in the condition storage unit and the reliability calculated by the speech recognition unit; and an output unit that outputs the recognition result without executing the confirmation process when the determination unit determines not to execute the confirmation process; an update unit that updates the one condition corresponding to the one command based on approval information indicating approval or rejection of the recognition result, which is received by the voice receiving unit in the confirmation step; the one condition is a threshold value, A voice recognition device in which, when the voice receiving unit receives the approval information indicating approval in the confirmation process, the update unit changes the threshold value corresponding to the one command based on time information.

2. Receiving voice information indicating one command among a plurality of commands; performing voice recognition of the one command based on the received voice information and calculating a reliability of the recognition result of the one command; determining whether to execute the confirmation step based on one of a plurality of conditions used for determining whether to execute a confirmation step of the recognition result, the conditions being stored in association with each of the plurality of commands, and the calculated reliability; outputting the recognition result without executing the confirmation process when it is determined that the confirmation process should not be executed; updating the one condition corresponding to the one command based on approval information indicating approval or rejection of the recognition result received in the confirmation step; moreover, the one condition is a threshold value, When the confirmation step receives the approval information indicating approval, the threshold value corresponding to the one command can be changed based on time information; A computer-readable storage medium that stores instructions for causing a computer to execute the above.

Images