JP2021117284A - Voice recognition cock - Google Patents

Abstract

To provide a voice recognition cock which can improve a voice recognition rate by suitably attenuating or removing noise sound without using a directional microphone.SOLUTION: A voice recognition cock 1A includes: a cock unit 50 for performing water spouting and water stop and adjusting a temperature and a flow rate of water; a voice input unit 10A to which voice is inputted; and a control unit 30 for controlling operation of the cock unit 50 on the basis of voice information from the voice input unit 10A. The voice input unit 10A includes a first microphone 11 and a second microphone 12, which are two omnidirectional microphones. A voice recognition unit 2 formed of the voice input unit 10A and the control unit 30 includes a controller 2A including: a noise attenuation removal part 15A for attenuating or removing noise sound on the basis of a phase difference of corresponding sounds in the sounds from the first microphone 11 and the second microphone 12; and a voice recognition part 31A for recognizing voice by using voice information from which noise sound is attenuated or removed.SELECTED DRAWING: Figure 6

Description

The present invention relates to a voice recognition faucet.

In a mixing faucet used in a kitchen, a washroom, etc., Patent Document 1 describes a voice recognition type that can recognize a voice instruction issued by a user using one microphone and adjust the flow rate and temperature of water. Mixture faucets are disclosed. With the above configuration, the user can use the mixed faucet cleanly and rationally without manually operating the faucet lever.

Further, Patent Document 2 describes a voice input microphone for inputting a sound including a noise sound such as a running water sound near the faucet, and a directivity provided near the faucet for inputting a noise sound (running water sound near the faucet). A voice recognition faucet having two microphones, a sex microphone, is disclosed. With the above configuration, it is possible to suppress a decrease in the voice recognition rate by subtracting the noise sound input to the directional microphone from the voice input to the voice input microphone.

Japanese Unexamined Patent Publication No. 60-14677 Japanese Unexamined Patent Publication No. 3-24383

In Patent Document 1, since only one microphone does not have a special noise sound removing means, the voice recognition rate may decrease.

In Patent Document 2, a directional microphone for removing noise is added to the voice input microphone to suppress a decrease in the voice recognition rate. However, the directional microphone has a complicated structure for collecting sound in the microphone.

The present invention has been devised in view of these points, and is a voice recognition faucet capable of appropriately attenuating or removing noise sound and further improving the voice recognition rate without using a directional microphone. I will provide a.

In order to solve the above problems, the voice recognition faucet of the present invention takes the following means.

That is, the voice recognition faucet of the present invention is a faucet unit that performs at least one of spouting and stopping, adjusting the flow rate of discharged water, and adjusting the temperature of discharged water, and a voice from a user. It is a voice recognition faucet having a voice input unit into which is input and a control unit that controls the operation of the faucet unit based on the voice information input from the voice input unit. The voice input unit has two omnidirectional microphones, a first microphone and a second microphone, which are arranged at predetermined intervals. The voice recognition unit composed of the voice input unit and the control unit is included in each sound included in the first voice information input from the first microphone and in the second voice information input from the second microphone. Based on the phase difference between each sound and the corresponding sound, the noise attenuation removing unit that attenuates or removes the noise sound contained in the voice information and the voice information from which the noise sound is attenuated or removed It is provided with a control device having a voice recognition unit for recognizing a voice from a user by using the voice recognition unit.

According to the above configuration, the noise sound included in the voice information can be attenuated or removed based on the phase difference between the corresponding sounds input from the two microphones. Therefore, the voice recognition rate can be further improved by appropriately attenuating or removing noise sound without using a directional microphone.

Further, the voice recognition faucet of the present invention may be further configured as follows. The noise attenuation removing unit attenuates or removes sounds having substantially the same phase of the corresponding sounds as noise sounds. The voice input unit is arranged near the faucet to which the water discharged from the faucet unit is output. In the first microphone and the second microphone, a virtual plane orthogonal to the virtual straight line passes through the midpoint of the virtual straight line having the first microphone and the second microphone at both ends, and passes through the mouth of the user standing in front of the faucet. It is arranged so as to pass through the water repelling position where the water discharged from the faucet repels or the vicinity of the water repelling position.

According to the above configuration, the noise sound generated from the water splash position included in the first audio information input from the first microphone and the noise sound included in the second audio information input from the second microphone. The phases are almost the same. Further, the voice generated from the user's mouth included in the first voice information and the voice included in the second voice information cause a relatively phase difference. Therefore, the noise sound is appropriately attenuated or removed, and the voice recognition rate can be further improved.

Further, the voice recognition faucet of the present invention may be further configured as follows. The first microphone and the second microphone are arranged so that the virtual straight line extends substantially in the vertical direction, and the upper end of the virtual straight line is closer to the user than the lower end of the virtual straight line in the vertical direction toward the user. It is arranged so as to incline at a predetermined angle with respect to.

According to the above configuration, a difference is generated depending on the distance from the user's mouth to each microphone, so that the phase difference is more likely to occur. Therefore, the voice recognition rate can be further improved.

It is a perspective view explaining the example which applied the voice recognition faucet of this invention to the faucet of the sink of the sink of a home. It is a front view of the voice recognition faucet shown in FIG. 1 as seen from the II direction. It is a right side view of the voice recognition faucet shown in FIG. 1 as seen from the direction III. It is a top view of the voice recognition faucet shown in FIG. 1 as seen from the IV direction. It is a right side view which shows the positional relationship between a voice recognition faucet and a user. It is a block diagram explaining the structure of the voice recognition faucet of 1st Embodiment. In the first embodiment, it is the flowchart explaining the example of the processing procedure of the processing (overall processing) of a control device. In the first embodiment, it is a flowchart explaining the details of the process SN100 (input signal acquisition process) in the flowchart shown in FIG. 7. In the first embodiment, it is a flowchart explaining the details of the process SN200 (noise attenuation removal process) in the flowchart shown in FIG. 7. In the first embodiment, it is a flowchart explaining the details of the process SS100 (initialization process) in the flowchart shown in FIG. 7. In the first embodiment, it is a flowchart explaining the detail of the process SA200 (input signal processing) in the flowchart shown in FIG. 7. In the first embodiment, it is a flowchart explaining the details of the process SA400 (the output process of the control signal corresponding to the recognized voice) in the flowchart shown in FIG. 7. In the first embodiment, it is a flowchart explaining the details of the process SA500 (the output process of the control signal according to the temperature) in the flowchart shown in FIG. 7. It is a block diagram explaining the structure of the voice recognition faucet of 2nd Embodiment. In the second embodiment, it is the flowchart explaining the example of the processing procedure of the processing (overall processing) of a control device.

<Overall configuration and arrangement of voice recognition faucet 1 (Fig. 1-5)>
Hereinafter, embodiments for carrying out the present invention will be described with reference to FIGS. 1-15. In the following description, when each direction such as front-back, up-down, left-right, etc. is shown, it means each direction shown in each figure.

First, the overall configuration and arrangement of the voice recognition faucet 1 of the present invention will be described (see FIGS. 1-5). As shown in FIG. 1, the voice recognition faucet 1 of the present invention is configured as a hot water mixing faucet attached to a household sink 90.

As shown in FIG. 1, the voice recognition faucet 1 includes a faucet unit 50 and a faucet unit that perform three operations of spouting and stopping water, adjusting the flow rate of discharged water, and adjusting the temperature of discharged water. A faucet 92 that discharges the water sent from the 50 to the sink 91, a voice recognition unit 2 that controls the operation of the faucet unit 50 by recognizing the voice of the user U standing in front of the faucet 92, and a speaker. 70 and. As shown in FIG. 1-5, the faucet unit 50 is arranged below the faucet 92 and in the sink 90. The faucet unit 50 is controlled by the voice recognition unit 2 to mix the inflowing water (tap water) and hot water (hot water from the water heater) at a predetermined ratio, and discharges the mixed hot water to the faucet 92. The speaker 70 outputs a notification voice based on a control signal from the voice recognition unit 2 (control unit 30).

The faucet 92 is attached to the rear of the sink 91 and is provided so that it can rotate in the horizontal direction. The rotation of the faucet 92 causes the faucet 92A of the faucet 92 to move in an arc with respect to the sink 91. That is, the faucet 92 can change the water discharge position with respect to the sink 91. As shown in FIGS. 1 and 4, the water is discharged onto the water splash position 93 of the sink 91. When water is discharged to the water splash position 93, the water splash sound generated from the water splash position 93 corresponds to the "noise sound" of the present invention.

The voice recognition unit 2 is provided in the vicinity of the faucet 92, and is a voice input unit 10 into which the voice from the user U is input, and the faucet unit 50 based on the voice information input from the voice input unit 10. It has a control unit 30 that controls the operation.

As shown in FIGS. 2 and 3, the audio input unit 10 has a first microphone 11, a second microphone 12, a discharge LED 13, a temperature LED 14, and a first microphone 11 and a second microphone 12 at both ends. It has a virtual straight line 19 and a virtual plane 20 that passes through the midpoint 19A of the virtual straight line 19 and is orthogonal to the virtual straight line 19. The discharge LED 13 and the temperature LED 14 output light such as color (red, green, orange, etc.) and lighting / blinking based on the control signal from the control unit 30.

The first microphone 11 and the second microphone 12 are omnidirectional microphones, and are arranged at intervals L from each other. As shown in FIG. 3, the first microphone 11 and the second microphone 12 are arranged so that the faucet 92A substantially overlaps the above-mentioned water splash position 93 on the virtual plane 20. Further, the speaker 70 described above is also arranged so as to substantially overlap the virtual plane 20. The user of the first microphone 11 and the second microphone 12 so that the virtual straight line 19 extends substantially in the vertical direction as shown in FIG. 2 and has an angle θ with respect to the vertical direction as shown in FIGS. 3 and 5. Arranged so as to incline toward U. Further, the first microphone 11 is arranged so as to be closer to the user U than the second microphone 12. That is, the first microphone 11 and the second microphone 12 are in the vertical direction toward the user U so that the upper end 19B of the virtual straight line 19 is closer to the user U than the lower end 19C of the virtual straight line 19. It is arranged so as to incline with respect to a predetermined angle θ.

The position of the mouth of the user U is assumed to be in the space A shown in FIG. The virtual plane 20 is set so as not to pass through this space A. Therefore, the first microphone 11 and the second microphone 12 have a faucet having a virtual plane 20 orthogonal to the virtual straight line 19 through the midpoint 19A of the virtual straight line 19 having the first microphone 11 and the second microphone 12 at both ends. It is arranged so as to pass near the water splash position 93 or the water splash position 93 where the water discharged from the microphone 92A does not pass through the mouth of the user U standing in front of the 92A.

In the examples shown in FIGS. 3 and 5, the first microphone 11 and the second microphone 12 are arranged so that the virtual plane 20 overlaps the water splash position 93 where the faucet 92 is used most frequently. That is, as shown in FIGS. 3 and 5, the virtual plane 20 is set to pass through the water splash position 93 when the faucet 92A faces the user U directly in front of the user U. In this way, even if the faucet 92 is rotated by the operation of the user U and the water splash position 93 is moved, the virtual plane 20 is set to pass in the vicinity of the water splash position 93.

Due to the above arrangement of the first microphone 11 and the second microphone 12, the distances from the water splash position 93 to the first microphone 11 and the second microphone 12 are substantially equal to each other. As a result, the water splash sound generated from the water splash position 93 is input to the first microphone 11 and the second microphone 12 so that the phases are substantially the same. That is, the phases of the water splash sound included in the first voice information input from the first microphone 11 and the water splash sound included in the second voice information input from the second microphone 12 are substantially the same.

Further, due to the above arrangement, the distances from the mouth of the user U to the first microphone 11 and the second microphone 12 are relatively different. As a result, the voice emitted from the mouth of the user U is input to the first microphone 11 and the second microphone 12 so as to cause a phase difference. That is, a phase difference occurs between the voice included in the first voice information input from the first microphone 11 and the voice included in the second voice information input from the second microphone 12.

As described above, the voice recognition unit 2 is provided with the first microphone 11 and the second microphone 12, so that the phase difference between the corresponding sounds included in the two voice information input from the microphones 11 and 12 is provided. Can be detected. By arranging the first microphone 11 and the second microphone 12 at the above-mentioned appropriate positions, the phases of the water splash sounds (noise sounds) generated from the water splash positions 93 are substantially the same. As a result, the voice recognition unit 2 can attenuate or remove sounds having substantially the same phase as noise sounds. In this way, the voice recognition unit 2 can recognize the voice from the user U by using the voice information in which the noise sound is attenuated or removed.

Further, as shown in FIG. 5, by arranging the first microphone 11 so as to be closer to the user U than the second microphone 12, the voice of the user U included in the second voice information is the first voice. The phase is delayed compared to the voice of the user U included in the voice information. The voice recognition unit 2 can correctly recognize the voice of the user U standing in front of the faucet 92 by detecting which voice information includes the phase of the voice being delayed.

That is, for example, as shown in FIG. 5, it is assumed that a third party U2 standing on the opposite side of the user U with the voice recognition unit 2 sandwiched the voice recognition unit 2 inputs the voice. In this case, the voice recognition unit 2 detects that the phase of the first voice information from the first microphone 11 is behind the phase of the second voice information from the second microphone 12. As a result, the voice recognition unit 2 can recognize that the third party U2 is a user standing on the opposite side of the user U. In this way, the voice recognition unit 2 can prevent the voice from the third party U2 from being recognized.

<First Embodiment (Fig. 6-13)>
Hereinafter, the voice recognition faucet 1A of the first embodiment will be described with reference to FIGS. 6 to 13. In the voice recognition faucet 1A of the first embodiment, the voice input unit 10A attenuates or removes noise sounds based on the phase difference between the corresponding sounds.

<Configuration of voice recognition faucet 1A (Fig. 6)>
First, the configuration of the voice recognition faucet 1A is shown in FIG. The voice recognition faucet 1A includes a control device 2A (voice recognition unit 2) including a voice input unit 10A and a control unit 30, and a faucet unit 50.

The faucet unit 50 includes a mixing valve 51, a temperature motor 51M, an on-off valve 52, a flow rate adjusting valve 53, a flow rate motor 53M, a temperature sensor 54, and a flow rate sensor 55.

A pipe for water (tap water) and a pipe for hot water (hot water from a water heater) are connected to the mixing valve 51, and hot water in which water and hot water are mixed at a predetermined ratio is discharged toward the on-off valve 52. The predetermined ratio (mixing ratio) of the mixing valve 51 is adjusted by the temperature motor 51M controlled by the control signal from the control unit 30.

The on-off valve 52 is controlled to an open state (fully open) or a closed state (fully closed) by a control signal from the control unit 30. When the on-off valve 52 is controlled to be in the open state, the hot water flowing in from the mixing valve 51 flows out toward the flow rate adjusting valve 53.

The flow rate adjusting valve 53 adjusts the flow rate of the hot water flowing in from the on-off valve 52 and causes the flow rate to flow out toward the faucet 92A (see FIG. 1-5) of the faucet 92. The flow rate by the flow rate adjusting valve 53 is adjusted by the flow rate motor 53M controlled by the control signal from the control unit 30.

The temperature sensor 54 outputs a detection signal according to the temperature of the hot water discharged from the mixing valve 51 to the control unit 30. The flow rate sensor 55 outputs a detection signal according to the flow rate of the hot water discharged from the on-off valve 52 to the control unit 30.

The control unit 30 includes a control CPU 31, a storage device 32 such as a Flash ROM, a RAM 33, a timer 34, and a communication circuit 35. The control CPU 31 has a voice recognition unit 31A that recognizes voice information input from the voice input unit 10A. The control CPU 31 detects the temperature of the hot water discharged from the mixing valve 51 based on the detection signal from the temperature sensor 54, and the flow rate of the hot water discharged from the on-off valve 52 based on the detection signal from the flow rate sensor 55. Is detected. The control CPU 31 outputs a control signal for controlling the output of the discharge LED 13 and the temperature LED 14 based on the detection signal, and the control CPU 31 outputs a control signal for controlling the temperature motor 51M, the on-off valve 52, and the flow rate motor 53M. do.

The communication circuit 35 outputs a control signal for controlling the output of the speaker 70 based on the detection signal. For example, a control signal is output to the speaker 70 by a wireless signal such as Bluetooth (registered trademark).

The speaker 70 outputs the operating state of the voice recognition faucet 1A by voice based on a wireless signal such as Bluetooth (registered trademark) output from the communication circuit 35. The voice from the speaker 70 is not recognized because the speaker 70 is provided behind the voice input unit 10A like the third party U2 described above. Further, the sound produced by the speaker 70 is attenuated or removed in the same manner as the water splash sound by providing the speaker 70 on the virtual plane 20. The speaker 70 may be omitted.

The voice input unit 10A further includes a voice input CPU 15, a storage device 16 such as a Flash ROM, a RAM 17, and a timer 18 in addition to the configuration of the voice input unit 10 described above. The voice input CPU 15 has a noise attenuation removing unit 15A that attenuates or removes noise. The details of the noise attenuation removing unit 15A will be described later.

As described below, the control CPU 31 controls the operation of the faucet unit 50 by using a voice pattern selected from a plurality of voice patterns set in advance in the storage device 32. The plurality of voice patterns correspond to water discharge and water stoppage, flow rate adjustment, temperature adjustment, and the like, respectively.

<Overall processing in the processing procedure of the control device 2A (FIG. 7)>
Next, an example of the processing procedure of the entire processing of the voice input CPU 15 and the control CPU 31 (control device 2A) will be described with reference to the flowchart shown in FIG. First, the voice input CPU 15 will be described. When the voice input CPU 15 is started, the process proceeds to step S010.

In step S010, the voice input CPU 15 executes the process SN100 (input signal capture process) and proceeds to step S020. The details of the processing SN100 (input signal acquisition processing) will be described later.

In step S020, the voice input CPU 15 executes the process SN200 (noise attenuation removal process) to proceed to step S030. The details of the processing SN200 (noise attenuation removal processing) will be described later.

In step S030, the voice input CPU 15 outputs the voice information whose noise sound is attenuated or removed by the processing SN 200 to the control CPU 31, and returns the processing to step S010.

Next, the control CPU 31 will be described. When the control CPU 31 is started, the process proceeds to step S110.

In step S110, the control CPU 31 executes the process SS100 (initialization process) to proceed to step S120. The details of the processing SS100 (initialization processing) will be described later.

In step S120, the control CPU 31 executes processing SA200 (input signal processing) and proceeds to step S130. The details of the processing SA200 (input signal processing) will be described later.

In step S130, the control CPU 31 performs a process of capturing the voice information output in step S030 of the voice input CPU 15, and proceeds to step S140.

In step S140, the control CPU 31 recognizes the voice of the voice information captured in the voice recognition process, and proceeds to the process in step S150.

The control CPU 31 executing the process of step S140 corresponds to the voice recognition unit 31A that recognizes the voice from the user U by using the voice information from which the noise sound is attenuated or removed.

In step S150, the control CPU 31 executes the process SA400 (output processing of the control signal according to the recognized voice), and proceeds to the process in step S160.

In step S160, the control CPU 31 executes the process SA500 (output process of the control signal according to the temperature) and returns the process to step S120. The details of the processing SA500 (output processing of the control signal according to the temperature) will be described later.

<Details of processing SN100 (input signal acquisition processing) (Fig. 8)>
Next, the details of the processing SN100 (input signal acquisition processing) will be described with reference to FIG. When the voice input CPU 15 proceeds to step S010 of the flowchart shown in FIG. 7, the voice input CPU 15 proceeds to step SN110 of the processing SN100 shown in FIG.

In step SN110, the voice input CPU 15 creates the first voice information based on the input signal from the first microphone 11, and creates the second voice information based on the input signal from the second microphone 12. Further, the voice input CPU 15 returns the process to step S020 shown in FIG.

<Details of processing SN200 (noise attenuation removal processing) (Fig. 9)>
Next, the details of the processing SN200 (noise attenuation removing processing) will be described with reference to FIG. When the voice input CPU 15 proceeds to step S020 of the flowchart shown in FIG. 7, the voice input CPU 15 proceeds to step SN210 of the process SN200 shown in FIG.

In step SN210, the voice input CPU 15 removes (or attenuates) as noise sound a sound in which the corresponding sounds of each sound included in the first voice information and each sound included in the second voice information have substantially the same phase. )do. It should be noted that extracting sounds having a phase difference between the corresponding sounds of a predetermined amount or more is also included in "attenuating or removing sounds having substantially the same phase difference between the corresponding sounds as noise sounds". Further, the voice input CPU 15 returns the process to step S030 shown in FIG.

The voice input CPU 15 executing the process of step SN210 of the processing SN200 has each sound included in the first voice information input from the first microphone 11 and the second voice information input from the second microphone 12. Corresponds to the noise attenuation removing unit 15A that attenuates or removes the noise sound included in the voice information based on the phase difference between each sound included in and the corresponding sound.

<Details of processing SS100 (initialization processing) (FIG. 10)>
Next, the details of the processing SS100 (initialization processing) will be described with reference to FIG. When the control CPU 31 proceeds to step S110 of the flowchart shown in FIG. 7, the control CPU 31 proceeds to step SS110 of the process SS100 shown in FIG.

In step SS110, the control CPU 31 drives the flow rate motor 53M to the preset flow rate reference rotation position, and drives the temperature motor 51M to the preset temperature reference rotation position. Further, the control CPU 31 drives the on-off valve 52 to the closed state, and outputs water from the discharge LED 13 (for example, lighting in green). Further, the control CPU 31 returns the process to step S120 shown in FIG. The flow rate reference rotation position and the temperature reference rotation position are appropriately set.

<Details of processing SA200 (input signal processing) (FIG. 11)>
Next, the details of the processing SA200 (input signal processing) will be described with reference to FIG. When the control CPU 31 proceeds to step S120 of the flowchart shown in FIG. 7, the control CPU 31 proceeds to step SA210 of the process SA200 shown in FIG.

In step SA210, the control CPU 31 obtains and stores the flow rate of hot water flowing into the flow rate adjusting valve 53 based on the detection signal from the flow rate sensor 55, and discharges it from the mixing valve 51 based on the detection signal from the temperature sensor 54. Find and memorize the temperature of hot water. Further, the control CPU 31 returns the process to step S130 shown in FIG. When the on-off valve 52 is in the closed state, 0 (zero) is detected for the flow rate, and the temperature of the hot water accumulated around the temperature sensor 54 is detected for the temperature.

<Details of processing SA400 (output processing of control signal according to recognized voice) (FIG. 12)>
Next, the details of the processing SA400 (output processing of the control signal according to the recognized voice) will be described with reference to FIG. When the control CPU 31 proceeds to step S150 of the flowchart shown in FIG. 7, the control CPU 31 proceeds to step SA410 of the process SA400 shown in FIG.

In step SA410, the control CPU 31 determines whether or not the voice corresponding to "water discharge" (for example, "output", "water discharge", etc.) is recognized. If it is recognized (Yes), the process proceeds to step SA415, and if it is not recognized (No), the process proceeds to step SA420.

In step SA415, the control CPU 31 maintains the operating position of the flow rate motor 53M (does nothing), maintains the operating position of the temperature motor 51M (does nothing), and drives the on-off valve 52 to the open state. .. Further, the control CPU 31 outputs water for water discharge from the discharge LED 13 (for example, lighting in red), outputs water for water discharge from the speaker 70 (for example, notifies that “water has been discharged”), and ends the process. The process returns to step S160 shown in 7.

In step SA420, the control CPU 31 determines whether or not the voice corresponding to "water stop" (for example, "stop", "water stop", etc.) is recognized. If it is recognized (Yes), the process proceeds to step SA425, and if it is not recognized (No), the process proceeds to step SA430.

In step SA425, the control CPU 31 maintains the operating position of the flow rate motor 53M (does nothing), maintains the operating position of the temperature motor 51M (does nothing), and drives the on-off valve 52 to the closed state. .. Further, the control CPU 31 outputs water stoppage from the discharge LED 13 (for example, lighting in green), outputs water stoppage from the speaker 70 (for example, notifies that "water has stopped"), and ends the process. Then, the process is returned to step S160 shown in FIG.

In step SA430, the control CPU 31 determines whether or not the voice corresponding to the "flow rate increase" (for example, "increase", "many", etc.) is recognized. If it is recognized (Yes), the process proceeds to step SA435, and if it is not recognized (No), the process proceeds to step SA440.

In step SA435, the control CPU 31 drives the flow rate motor 53M to the increasing side by a predetermined amount, maintains the operating position of the temperature motor 51M (does nothing), and maintains the on-off valve 52 (does nothing). Further, the control CPU 31 outputs an output for increasing the flow rate from the speaker 70 (for example, notifying that the flow rate has been increased), ends the process, and returns the process to step S160 shown in FIG. 7.

In step SA440, the control CPU 31 determines whether or not the voice corresponding to the "flow rate reduction" (for example, "reduce", "less", etc.) is recognized. If it is recognized (Yes), the process proceeds to step SA445, and if it is not recognized (No), the process proceeds to step SA450.

In step SA445, the control CPU 31 drives the flow rate motor 53M to the decreasing side by a predetermined amount, maintains the operating position of the temperature motor 51M (does nothing), and maintains the on-off valve 52 (does nothing). Further, the control CPU 31 outputs a flow rate reduction output from the speaker 70 (for example, notifies that the flow rate has been reduced), ends the process, and returns the process to step S160 shown in FIG. 7.

In step SA450, the control CPU 31 determines whether or not the voice corresponding to "heating" (for example, "raising", "hot", etc.) is recognized. If it is recognized (Yes), the process proceeds to step SA455, and if it is not recognized (No), the process proceeds to step SA460.

In step SA455, the control CPU 31 maintains the operating position of the flow rate motor 53M (does nothing), drives the temperature motor 51M to the temperature rise side by a predetermined amount, and maintains the on-off valve 52 (does nothing). Further, the control CPU 31 outputs a temperature rise output from the speaker 70 (for example, notifies that the temperature has been raised), ends the process, and returns the process to step S160 shown in FIG. 7.

In step SA460, the control CPU 31 determines whether or not the voice corresponding to the "lowering temperature" (for example, "lowering", "cold", etc.) is recognized. If it is recognized (Yes), the process proceeds to step SA465, and if it is not recognized (No), the process is returned to step S160 shown in FIG.

In step SA465, the control CPU 31 maintains the operating position of the flow rate motor 53M (does nothing), drives the temperature motor 51M to the temperature lowering side by a predetermined amount, and maintains the on-off valve 52 (does nothing). Further, the control CPU 31 outputs a temperature lowering output from the speaker 70 (for example, notifies that the temperature has been lowered), ends the process, and returns the process to step S160 shown in FIG. 7.

<Details of processing SA500 (output processing of control signal according to temperature) (FIG. 13)>
Next, the details of the processing SA500 (output processing of the control signal according to the temperature) will be described with reference to FIG. When the control CPU 31 proceeds to step S160 of the flowchart shown in FIG. 7, the control CPU 31 proceeds to step SA510 of the process SA500 shown in FIG.

In step SA510, the control CPU 31 determines whether or not the temperature of the hot water is, for example, less than 30 ° C. based on the detection signal from the temperature sensor 54. The control CPU 31 proceeds to step SA515 when the temperature is less than 30 ° C. (Yes), and proceeds to step SA520 when the temperature is 30 ° C. or higher (No).

In step SA515, the control CPU 31 outputs a “cold” output (for example, lit in blue) from the temperature LED 14, and returns the process to step S120 shown in FIG.

In step SA520, the control CPU 31 determines whether or not the temperature of the hot water is, for example, less than 45 ° C. based on the detection signal from the temperature sensor 54. The control CPU 31 proceeds to step SA525 when the temperature is less than 45 ° C. (Yes), and proceeds to step SA530 when the temperature is 45 ° C. or higher (No).

In step SA525, the control CPU 31 outputs an “appropriate temperature” output (for example, lit in yellow) from the temperature LED 14, and returns the process to step S120 shown in FIG.

In step SA530, the control CPU 31 outputs “hot” from the temperature LED 14 (for example, lit in red), and returns the process to step S120 shown in FIG. 7.

In the first embodiment described above, the noise sound can be appropriately attenuated or removed without using a directional microphone, and the voice recognition rate can be further improved.

<Second embodiment (Fig. 14-15)>
Hereinafter, the voice recognition faucet 1B of the second embodiment will be described with reference to FIGS. 14-15. The voice recognition faucet 1B of the second embodiment uses the control unit 30A to attenuate or eliminate noise sounds based on the phase difference between the corresponding sounds with respect to the voice recognition faucet 1A of the first embodiment. conduct.

<Configuration of voice recognition faucet 1B (Fig. 14)>
First, the configuration of the voice recognition faucet 1B is shown in FIG. The voice recognition faucet 1B is different from the voice recognition faucet 1A in that it has a control device 2B (voice recognition unit 2) including the above-mentioned voice input unit 10 and a control unit 30A.

The control unit 30A further includes an inverting circuit 36, a non-inverting circuit 37, and an adder 38 in addition to the configuration of the control unit 30 described above. The inverting circuit 36 is connected to the second microphone 12, and the non-inverting circuit 37 is connected to the first microphone 11. The adder 38 adds the first voice information and the second voice information and outputs them to the control CPU 31. With the above configuration, the control unit 30A inverts the phase of the second voice information input from the second microphone 12. Further, the control unit 30A adds the first voice information and the phase-inverted second voice information.

As described above, the control unit 30A can cancel and attenuate the sounds contained in the first voice information and the second voice information whose phases are substantially the same. That is, the control unit 30A attenuates the water splash sound (noise sound) generated from the water splash position 93 included in the voice information. The voice recognition unit 31A of the control unit 30A recognizes the voice from the user U based on the voice information in which the water splash sound (noise sound) is attenuated. The noise sound canceling structure by the inverting circuit 36, the non-inverting circuit 37, and the adder 38 corresponds to the noise attenuation removing unit 15A that attenuates or removes sounds having substantially the same phase of the corresponding sounds as noise sounds.

<Overall processing in the processing procedure of the control device 2B (FIG. 15)>
Next, an example of the processing procedure of the entire processing of the control device 2B is shown in FIG. The flowchart of FIG. 15 is the same as the flowchart of the control CPU 31 of the first embodiment. In step S130, the control CPU 31 performs a voice information acquisition process in which the first voice information and the phase-inverted second voice information are added together.

In the second embodiment described above, the noise sound can be appropriately attenuated or removed without using a directional microphone, and the voice recognition rate can be further improved.

<Summary>
Summarizing the above, the voice recognition faucet 1 of the present embodiment has the following configuration. That is, the voice from the user (U) and the faucet unit (50) that performs at least one of the operations of spouting and stopping water, adjusting the flow rate of the discharged water, and adjusting the temperature of the discharged water are input. It has a voice input unit (10, 10A) and a control unit (30, 30A) that controls the operation of the faucet unit (50) based on the voice information input from the voice input unit (10, 10A). It is a voice recognition faucet (1). The voice input unit (10, 10A) has a first microphone (11) and a second microphone (12), which are two omnidirectional microphones arranged at a predetermined interval (L). The voice recognition unit (2) composed of the voice input unit (10, 10A) and the control unit (30) includes each sound included in the first voice information input from the first microphone (11) and each sound. Based on the phase difference between each sound included in the second voice information input from the second microphone (12) and the corresponding sound, the noise sound contained in the voice information is attenuated or removed. A control device (2A, 2B) having a noise attenuation removing unit (15A) and a voice recognition unit (31A) that recognizes a voice from a user (U) using voice information from which noise sound is attenuated or removed. It has.

With such a configuration, noise sounds included in the voice information can be attenuated or removed based on the phase difference of each sound input from the two microphones (11, 12), respectively. Therefore, the voice recognition rate can be further improved by appropriately attenuating or removing noise sound without using a directional microphone.

Further, the noise attenuation removing unit (15A) attenuates or removes sounds having substantially the same phase of the corresponding sounds as noise sounds. The voice input unit (10, 10A) is arranged in the vicinity of the faucet (92A) from which the water discharged from the faucet unit (50) is output. The first microphone (11) and the second microphone (12) pass through the midpoint (19A) of the virtual straight line (19) having the first microphone (11) and the second microphone (12) at both ends. The water splash position (93) in which the virtual plane (20) orthogonal to (19) repels the water discharged from the microphone (92A) without passing through the mouth of the user (U) standing in front of the microphone (92A). Alternatively, it is arranged so as to pass in the vicinity of the water splash position (93).

With such a configuration, the noise sound generated from the water splash position (93) included in the first voice information input from the first microphone (11) and the noise sound input from the second microphone (12). The phase of the noise sound included in the second voice information is substantially the same. Further, the voice generated from the mouth of the user (U) included in the first voice information and the voice included in the second voice information cause a relatively phase difference. Therefore, the voice recognition rate can be further improved by appropriately attenuating or removing noise sound without using a directional microphone.

Further, the first microphone (11) and the second microphone (12) are arranged so that the virtual straight line (19) extends substantially in the vertical direction, and the upper end (19B) of the virtual straight line (19) is the virtual straight line. It is arranged so as to be inclined at a predetermined angle (θ) with respect to the vertical direction toward the user (U) so as to be closer to the user (U) than the lower end (19C) of (19).

With such a configuration, a difference is generated depending on the respective distances from the mouth of the user (U) to each microphone (11, 12), so that a phase difference is more likely to occur. Therefore, the voice recognition rate can be further improved.

<Other Embodiments>
The voice recognition faucets 1A and 1B of the present invention are not limited to the configuration, structure, shape, appearance and the like described in the present embodiment, and various changes, additions and deletions can be made without changing the gist of the present invention. Is. For example, in the description of the present embodiment, the faucet unit 50 has described an example in which it is possible to discharge and stop water, adjust the flow rate of discharged water, and adjust the temperature of discharged water. It suffices if at least one operation of adjusting the flow rate of the discharged water and adjusting the temperature of the discharged water can be performed.

In the description of the present embodiment, an example in which water discharge and water stoppage, flow rate increase and flow rate decrease, temperature rise and temperature decrease can be controlled by recognizing the voice of the user has been described, but water discharge and water stoppage and flow rate have been described. It may be configured to control at least one of increase and decrease in flow rate and increase and decrease in temperature.

The voice recognition faucet described in the present embodiment is not limited to the faucet of the sink in the home, and can be applied to various faucets such as the faucet of a public facility.

1, 1A, 1B Voice recognition faucet 2 Voice recognition unit 2A, 2B Control device 10, 10A Voice input unit 11 1st microphone 12 2nd microphone 13 Discharge LED
14 temperature LED
15 Voice input CPU
15A Noise Attenuation Remover 16 Storage Device 17 RAM
18 Timer 19 Virtual straight line 19A Midpoint 19B Upper end 19C Lower end 20 Virtual plane 30, 30A Control unit 31 Control CPU
31A Voice recognition unit 32 Storage device 33 RAM
34 Timer 35 Communication circuit 36 Reversing circuit 37 Non-reversing circuit 38 Adder 50 Faucet unit 51 Mixing valve 51M Temperature motor 52 On-off valve 53 Flow control valve 53M Flow motor 54 Temperature sensor 55 Flow sensor 70 Speaker 90 Sink 91 Sink 92 Faucet 92A Faucet 93 Water splash position U User U2 Third party L Interval θ Angle A Space

Claims (3)

A faucet unit that performs at least one of spouting and stopping, adjusting the flow rate of discharged water, and adjusting the temperature of discharged water.
A voice input unit that inputs voice from the user, and
A control unit that controls the operation of the faucet unit based on voice information input from the voice input unit, and
Is a voice recognition faucet with
The voice input unit has two omnidirectional microphones, a first microphone and a second microphone, which are arranged at predetermined intervals.
The voice recognition unit composed of the voice input unit and the control unit is
The phases of the corresponding sounds of each sound included in the first voice information input from the first microphone and each sound included in the second voice information input from the second microphone. A noise attenuation removing unit that attenuates or removes noise sounds contained in the voice information based on the difference.
A voice recognition unit that recognizes the voice from the user by using the voice information from which the noise sound is attenuated or removed.
Equipped with a control device,
Voice recognition faucet. The voice recognition faucet according to claim 1.
The noise attenuation removing unit attenuates or removes sounds having substantially the same phase of the corresponding sounds as the noise sounds.
The voice input unit is arranged in the vicinity of a faucet to which water discharged from the faucet unit is output.
The first microphone and the second microphone are
A virtual plane orthogonal to the virtual straight line passing through the midpoint of the virtual straight line having the first microphone and the second microphone at both ends does not pass through the mouth of the user standing in front of the faucet, but from the faucet. It is arranged so as to pass through the water splash position where the discharged water repels or the vicinity of the water splash position.
Voice recognition faucet. The voice recognition faucet according to claim 2.
The first microphone and the second microphone are
The virtual straight line is arranged so as to extend substantially in the vertical direction, and is predetermined with respect to the vertical direction toward the user so that the upper end of the virtual straight line is closer to the user than the lower end of the virtual straight line. Arranged to tilt at an angle,
Voice recognition faucet.

Images