JP2000235216A - Voice operable camera - Google Patents

Abstract

PROBLEM TO BE SOLVED: To make possible surely executing operation required by a user even when a partial phrase showing a command is omitted when the same command is repeated. SOLUTION: This camera is a voice operable camera recognizing a voice command constituted of plural phrases generated from a camera operator and executing the prescribed operation answering to the voice command. At this time, a DSP(digital signal processor) 31 incorporated in a voice command recognition unit 29 is provided with a function recognizing the phrases constituting the voice command, a function storing the recognized phases and a function detecting that the partial phrases constituting the voice command is omitted and complementing the omitted phrases with the stored phrases, and a CPU 17 being the means controlling the camera operation is provided with a function temporarily changing the function of e.g. a release switch 35 according to the command from the DSP 31.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a camera capable of recognizing a voice command pronounced by a user and executing a predetermined operation corresponding to the command.

[0002]

2. Description of the Related Art A voice control camera for controlling a camera by voice has been conventionally proposed, and a specific function of the camera is executed by issuing a voice control command assigned to the function. It has become.

As an example of such technical means, Japanese Patent Application Laid-Open No. 64-56428 discloses a control mechanism for controlling the function of a camera, a voice input means for inputting a voice, and a voice for recognizing the input voice. A recognition unit, and a control unit that controls a function of the camera based on the control content corresponding to the recognition result. When operating the camera, a voice corresponding to a desired operation is input via the voice input unit. In addition, a description is given of a camera control method based on sound, in which the input sound is recognized by the sound recognition means, and the control unit controls the function of the camera based on the control content corresponding to the recognition result.

In such a conventional voice control camera, the camera has a voice recognition function, and the camera function can be freely operated based on the voice of the camera user.

[0005]

By the way, when operating the camera with a voice command, if the shutter speed (hereinafter referred to as Tv value) indicating the shutter speed is to be increased by three steps, for example, "Tv value increase", "Tv value" You have to say "value up" and "Tv value up". However, when the user says “Tv value”, the parameter to be operated is T
The value is fixed at v value, and “T” is used until a parameter to be operated next (for example, “aperture value” (hereinafter, referred to as Av value))
Obviously, "up" following "v-value" is the word associated with the Tv value. Thus, the above instruction:
It is desirable that the terms “Tv value up”, “up”, and “up” have equivalent meanings. However, the above-mentioned conventional voice control camera does not show a method for dealing with a case where some of the words constituting the command are omitted.

[0006] If the meaning of a word can be determined even if a part of the word is clearly omitted from the flow of the words before and after, the camera user operates the camera by omitting the word and using only a few words. I want to tell you.

The present invention has been made in view of the above circumstances, and in the case where the same command is repeated, even if a part of a word indicating the command is omitted, an operation desired by the user is surely executed. It is an object of the present invention to provide a camera capable of voice operation.

[0008]

In order to achieve the above object, a first invention is a camera capable of recognizing voice data and performing a predetermined setting operation based on the recognized voice data. A recognition means for preliminarily storing the voice of the specific speaker as a table, recognizing the input voice by comparing the input voice with the table and recognizing the input voice, and converting the voice data into voice data; First analysis means for associating one of the operation members, second analysis means for associating the voice data with one of the directions in which the operation member is operated, and outputs of the first and second analysis means, respectively. Storage means for updating and storing one by one, and means for defining the operation member and the operation direction of the operation member based on the information stored in the storage means, and activating the camera according to the information. Preparation Those were.

According to a second aspect of the present invention, in the camera capable of voice operation according to the first aspect, when data cannot be obtained from the first analyzing means, the stored data stored in the storing means is replaced with The data is processed as data not obtained by the first analysis means.

[0010] Further, a third invention is the camera capable of voice operation according to the first invention, wherein the means for temporarily changing the function of a specific operation member according to the output of the first analysis means is provided. It is further characterized by being provided.

[0011]

Embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a configuration of a camera capable of voice operation according to an embodiment of the present invention.

In FIG. 1, the photographing lenses are group 1, group 2,
It comprises three lens groups 11, 12, and 13 of three groups. By changing the position of the second lens group 12, the focal length of the taking lens can be changed. The second group lens group 12 is driven by a zoom motor 14. The rotational movement of the zoom motor 14 is controlled by the zoom drive
2 on the optical axis. The zoom motor 14 is supplied with power from a zoom motor drive circuit 16. In addition, control of the entire camera system (including shooting operation control)
CPU (Central Processing Uni
The zoom motor drive circuit 16 is controlled by t) 17. In addition to the function of controlling the operation of the camera, the CPU 17 temporarily switches a specific operation member, for example, a shooting operation start function which is a function of the release switch 35, to another function (a zoom function, a shutter speed variable function, or an aperture value variable function). Etc.).

By changing the position of the third lens group 13, the object can be focused.
The third group 13 is driven by a focus motor 18. The rotational movement of the focus motor 18 is converted by the focus drive mechanism 19 into movement of the third lens group 13 on the optical axis. The focus motor 18 is supplied with power from a focus drive circuit 20. The focus motor drive circuit 20 is controlled by the CPU 17. Shooting lens 20
An image sensor 21 typified by a CCD or the like is arranged on the focal plane of. The image sensor 21 is controlled by an image processing circuit 22. The image processing circuit 22 captures image data from the image sensor 21 and stores it in the image memory 23 based on a command from the CPU 17. The display circuit 24 is a circuit for displaying image data. The user can confirm the subject image based on the image data displayed by the display circuit 24. The distance measuring circuit 25 is a circuit for measuring a distance to a subject, and is a light projecting element (L) that projects a light speed for photometry toward the subject.
(For example, ED) (not shown) and a light receiving element (not shown) for receiving the speed of light reflected from the subject. The focus motor drive circuit 20 controls the focus motor 18 based on the drive control signal output by the CPU 17 according to the subject distance detected by the distance measurement circuit 25, thereby moving the focus third lens group 13 to the in-focus position. Can be done. The aperture 26 for controlling the light amount of the taking lens is
It is driven by a step motor 27. CPU17
Controls the step motor 27 by the step motor drive circuit 28.

The voice command recognition unit 29 recognizes voice commands pronounced by the camera user, and
To output a command indicating the operation of the camera. The command is transferred to the CPU 17 through the communication line 34. The voice command recognition unit 29 includes a voice memory 30 as a lookup table and a DSP (Di
Gital Signal Processor) 31, an audio input circuit 32, and a microphone 33.

The DSP 31 forms a function of recognizing the words constituting the voice command together with the voice memory 30, and also has a function of storing the recognized words and a function of detecting that some of the words constituting the voice command have been omitted. In addition, the CPU 17 has a function of complementing the abbreviated words with the stored words. Even if a part of the voice command is omitted, the CPU 17 sends a predetermined command to the camera based on the complemented command from the DSP 31. Operation is performed. Or D
The SP 31 associates a recognition unit that recognizes an input voice and converts the voice data into voice data, and associates the voice data with one of a plurality of camera operation members (or camera operation parts) using transfer data 1 (see FIG. 2). Analysis means for associating the voice data with one of the directions in which the operation member (or operation part) is operated (operated) using transfer data 2 (see FIG. 2); A storage means for updating and storing one output of each of the second analysis means by using a register in the DSP, and the operation member (or the operation part) and the operation member (or the operation member) based on the information stored in the storage means. Or means for defining an operation direction of the operating member (or the operating part), and the CPU 17 controls the camera in accordance with the determined operation member (or operating part) and information on the operating direction of the operating member (or the operating part). Thereby to perform a predetermined operation.

The voice command that the user pronounces is the microphone 3
3 converts the signal into an electric signal, and the DSP
Output to 31. The audio input circuit 32 includes an amplifier and an A / D
A converter for amplifying an electric signal from the microphone 33;
The signal is converted into a digital signal using a / D converter. DSP
At 31, the digital signal is collated with the user's voice information stored as a table in the voice memory 30. Then, a command (command code that can be determined by the CPU 17) for causing a predetermined operation to be performed based on the collation result is output to the CP.
Output to U17.

A communication method between the DSP 31 and the CPU 17 will be described with reference to FIG. The communication line 34 includes four signal lines RQ, EN, DT, and CK. The signal flow (←) indicates that the DSP 31 outputs a signal and the CPU 17 receives the signal. The signal flow (→) indicates that the CPU 17 outputs a signal and the DSP 31 receives the signal.

Communication is performed as follows. DSP31
Changes the voltage level of the signal line RQ from high (High) to low (Low), and requests the CPU 17 to permit the command transfer operation. When detecting this change of the signal line RQ, the CPU 17 changes the signal line EN from high to low and permits the command transfer operation.
When the DSP 31 detects this change of the signal line EN, it outputs a clock signal to the signal line CK and synchronizes with the clock signal to form two-byte data (one-byte transfer data 1 and 2) on the signal line DT. Output the command to be executed.
When receiving the 2-byte command data, the CPU 17 changes the signal line EN from low (Low) to high (High) to notify the DSP 3 that the reception of the command has been completed.
Tell 1 The DSP 31 returns the signal line RQ to high in response to the change of the signal line EN. Table 1 shows DSP3
1 to the CPU 17 (the transfer data 1,
3 shows the correspondence between 2) and the operation of the CPU 17.
In the table, HEX represents hexadecimal.

[0019]

[Table 1] The release switch (hereinafter, release SW) 35 is a switch composed of two SWs (1RSW and 2RSW). When the user presses the release SW 35 lightly (half-press), only the 1RSW is turned on. Release SW3
When 5 is pushed in (deeply pushed), 2RSW is turned on together with 1RSW. The release SW 35 is a switch that is operated when the user wants the camera to perform an exposure operation, that is, starts a shooting operation. In the camera system of the present invention, the function of the release SW 35 as a switch for instructing an exposure operation can be used as a switch when the function is changed by a voice command and another function is executed. This will be described later.

FIGS. 3 and 4 are flowcharts showing the operation of the DSP 31. 3 and 4 are originally one drawing, but are divided into two for the sake of description.

In step S200, the process waits until the user inputs a voice by voice command. When the user utters a voice command to the camera, the voice input circuit 32
The audio signal output from the microphone 33 is converted into a digital signal and output to the DSP 31 as audio data. In step S201, the DSP 31 inputs the audio data. S202
Then, the voice data is compared with the words stored in the voice memory 30 to recognize the voice command pronounced by the user. A voice command for instructing the operation of the camera is basically composed of two words. In S203, it is determined whether the first word constituting the voice command is “exposure”. The voice command instructing the exposure operation is only the first word. If the first word is "exposure", the process proceeds to S204. In S204, the CP
Two bytes of predetermined data are output to U17. This is indicated by # 1 in Table 1. Communication format. If the first word is not "exposure", the process moves from S203 to S210. When the first word is "release SW", the process goes to S211 and
If not, proceed to S220. In S211, it is determined whether the second word is "ZOOM". If it is “ZOOM”, the flow shifts to S212, and the predetermined data indicated by # 2 in Table 1 is transferred to the CPU 17. CPU 1 that has received this data
In step S211 the release SW 35 functions as a SW (switch) for changing the focal length of the photographing lens. If "ZOOM" is not set, the flow advances to step S213. In S213, it is determined whether the second word is “Tv value”.
If the value is “Tv value”, the process proceeds to S214, and the predetermined data indicated by # 3 in Table 1 is transferred to the CPU 17. Upon receiving this data, the CPU 17 causes the release SW 35 to function as a SW for setting the shutter time (corresponding to the charge integration time of the image sensor 21).

If it is not "Tv value" in S213, the process proceeds to S215. In S215, it is determined whether the second word is “Av value”. If "Av value", the process proceeds to S216, and Table 1
Is transferred to the CPU 17. Upon receiving this data, the CPU 17 releases the release SW3
5 functions as a switch for setting the aperture value.

When the process proceeds from S210 to S220, it is determined whether the first word is "ZOOM". S for "ZOOM"
The process proceeds to 221; otherwise, the process proceeds to S230. S
At 221, it is determined whether the second word is “Up”. "U
If "p", the flow shifts to S222, and the predetermined data indicated by # 5 in Table 1 is transferred to the CPU 17. Upon receiving this data, the CPU 17 sets the focal length of the taking lens to wide (Wid).
e) Change a predetermined amount from the Tele side to the Tele side. Upon completion of the data transfer, the flow shifts to S245. In S245, the first word is stored in a register inside the DSP 31. The DSP
The register in 31 functions as storage means for storing words indicating operation members (or operation parts). The reason for storing is that the first word may be omitted when the user gives an operation instruction to the camera by a voice command. If the first word is omitted, the word stored in this register will be substituted. [Note that # 5 in Table 1
In order to transfer to the CPU 17 the predetermined data (including the second word “Up”, which is a word indicating the direction in which the operating member or the part is operated), the second word is also temporarily stored. Needless to say, it is necessary to store the data in another register inside the DSP 31. ] "Up" in S221
If not, the process proceeds to S223. In S223, it is determined whether the second word is “Down”. If it is "Down", the flow shifts to S224, where predetermined data indicated by # 6 in Table 1 is transferred to the CPU 17. CP that input this data
U17 changes the focal length of the photographing lens by a predetermined amount from the tele side to the wide side. When the data transfer is completed, the first word “ZOOM” is sent to the DSP in S245.
31 is stored in a register. In S220, the first word is "Z
If you move to S230 instead of "OM", the first word will be "Tv
Value ”. If "Tv value", the process proceeds to S231; otherwise, the process proceeds to S240. In S231, it is determined whether the second word is "Up". S23 if "Up"
2 and the predetermined data shown in # 7 of Table 1 is transferred to the CPU.
Transfer to 17. Upon receiving this data, the CPU 17
Change the shutter speed to +1 step to the high speed side. After the operation of S232 is completed, the process proceeds to S245 and the first word “Tv” is added to the DSP 31.
To the register inside. If it is not "Up" in S231, the flow shifts to S233. When the process proceeds to S233, the second word “Do
wn ”. If it is "Down", the flow shifts to S234, and the data shown in # 8 of Table 1 is transferred to the CPU 17. When receiving this data, the CPU 17 changes the shutter speed by one stage to a lower speed side. After the operation of S234 ends, the process moves to S245 to store the first word “Tv value” in a register in the DSP 31. In S230, the first word is “Tv
If you go to S240 instead of “Value”, the first word will be “Av value”
Is determined. If "Av value", the process proceeds to S241,
Otherwise, shift to S250. In S241, it is determined whether the second word is “Up”. S242 if "Up"
Then, the data indicated by # 9 in Table 1 is transferred to the CPU 17. When receiving the data, the CPU 17 changes the aperture value by one step. When the process of S242 is completed, the process moves to S245 to store the first word “Av value” in the DSP 31. If the process proceeds to S243 instead of "Up" in S241, it is determined whether the second word is "Down". "Down"
If so, the flow shifts to S244, where data indicated by # 10 in Table 1 is output to the CPU 17. CPU that input this data
A step 17 changes the aperture value by one step. After the process of S244, the process proceeds to S245 to store the first word “Av value” in the DSP 31. In S240, the first word is “Av value”
Therefore, when the process proceeds from S240 to S250, it is determined whether the first word is “Up”. If "Up", the process proceeds to S251. When the first word is “Up”, it indicates that the user has omitted the word that should be pronounced as the first word.
In this case, the first word included in the voice command already pronounced by the user without omission is required.

In S251, the first word stored in the register inside the DSP 31 is read. This word is the one stored in S245. In S252, it is determined whether the stored first word is "ZOOM". "ZOOM"
Then, it means that the user has omitted "ZOOMUp" as "Up". If it is "ZOOM", the data indicated by # 5 in Table 1 is transferred to the CPU 17 in S253.
Then, the process proceeds to S200 to input the next voice command. When shifting from S252 to S254, it is determined whether the stored word is a “Tv value”. “Tv value” means that “Tv value Up” is abbreviated as “Up”. If "Tv value", the data indicated by # 7 in Table 1 is transferred to the CPU 17 in S255. S254 to S256
When the process proceeds to, it is determined whether the stored word is “Av value”. “Av value” means that a command that should be originally called “Av value Up” is abbreviated as “Up”.
If "Av value", the data indicated by # 9 in Table 1 is transferred to the CPU 17 in S257.

If the first word is not "Up" in S250,
The process shifts from S250 to S260 to determine whether the first word is “Down”. If the first word is “Down”, it means that part of the voice command has been omitted. The abbreviated words are already included in the pronounced voice command.
The words already pronounced are stored in a register which is a part of the storage means of the DSP 31 in S245. If the first word is not "Down" in S260, the process proceeds to S261.

In S261, the omitted first word stored in the register inside the DSP 31 is read. In S262, it is determined whether the stored word is "ZOOM". If "ZOOM", the user is "ZOOM Dow
n "is abbreviated as" Down ". "ZO
If "OM", the data indicated by # 6 in Table 1 is transferred to the CPU 17 in S263. Then, the process proceeds to S200 to input the next voice command. When the process proceeds from S262 to S264, it is determined whether the stored first word is a “Tv value”. If "Tv value", "Tv value Down"
Is abbreviated as “Down”. "Tv value"
If so, in S265, the data indicated by # 8 in Table 1 is transferred to the CPU 17. When the process proceeds from S264 to S266, it is determined whether the stored first word is “Av value”. “Av value” means that the command that should be originally called “Av value Down” is abbreviated as “Down”. If "Av value", the data indicated by # 10 in Table 1 is transferred to the CPU 17 in S267.

FIG. 5 is a flowchart showing the operation of the CPU 17. As described above, when detecting the voice command, the DSP 31 outputs 2-byte data corresponding to the command to the CPU 17. This data is received at S100. When data from the DSP 31 has been input, the process proceeds from S101 to S110, and when there is no data from the DSP 31, the process proceeds from S101 to S102. S110
Then, a branch operation according to communication data from the DSP 31 is performed. If the first byte of the data transferred from the DSP 31 is 10 [HEX], the flow shifts to S111, where DS
The second byte of the data transferred from P31 is the CPU 17
Is stored in the SW function register inside. The SW function register functions as a means for temporarily changing the function of the release switch 35, which is a specific operation member, in response to a command from the DSP 31. By the operation of the SW function register in the CPU, the release SW 35 can be used for functions other than the originally determined function. This will be described later.

When the setting of the SW function register in the CPU 17 is completed, the process shifts to S100 to receive the next command.

The data from the DSP 31 is 2001 [HE
X], the flow shifts to S112. In step S112, the zoom motor 14 is controlled to change the focal length of the taking lens by a predetermined amount toward the long focal length. The data from the DSP 31 is 2002 [H
[EX], the process proceeds to S113. In S113, the focal length of the taking lens is changed by a predetermined amount toward the short focal length. If the data from the DSP 31 is b001 [HEX], the process proceeds to S114. In S114, the shutter speed is changed to the one-step high-speed side.
If the data from the DSP 31 is 4001 [HEX], S
Move to 115. In S115, the aperture setting value is changed by one step in the direction of narrowing down. The data from the DSP 31 is b00
If it is 2 [HEX], the flow shifts to S116. In S116, the shutter speed is changed to the one-step lower speed side. If the data from the DSP 31 is 4002 [HEX], the flow shifts to S117. S
At 117, the aperture setting is changed by one step toward the open side. DS
If the data from P31 is 8080 [HEX], S118
Move to.

In step S118, distance information from the distance measuring circuit 25 to the subject is input. The focus motor 18 is controlled based on the distance information to form a subject image on the image sensor 21. In S119, the step motor 27 is controlled based on the set aperture value. Then, the image sensor 21 is controlled based on the set shutter time to capture image data.

If there is no voice command input in S101, S10
Move to 2. When the process proceeds to step S102, the operation switch
, The state of the release SW 35 is input. If there is no change in the release SW 35, the process proceeds from S103 to S100, and if a change in the switch is detected, the process proceeds from S103 to S10.
Move to 4. In S104, a branch operation according to the set value of the SW function register in the CPU 17 is performed. CPU1
If the value of the SW function register in 7 is 00 [HEX], S
120, if 20 [HEX], go to S130, b0 [HE
X], the flow branches to S140, and if it is 40 [HEX], the flow branches to S150. By the function of the SW function register in the CPU 17, the release SW 35 has a function other than the original function. The reason for providing such a function will be described below.

In a conventional camera system, a large number of switches (SW) were required to instruct a complicated operation or to determine parameters and conditions necessary for photographing. However, the operation becomes complicated when the number of SWs increases,
This makes the camera hard to use for the user. Also, in reducing the size of the camera, a large number of SWs is an obstacle.
Therefore, it is important to be able to set many functions with one SW in order to solve these problems. When the function of the SW is set, if the setting can be performed without using the SW, the operability is further improved. For example, for a user who can use only one hand, the number of SWs that can be operated while holding the camera is very limited. However, if the limited functions of the operable SW can be changed to various functions by voice commands, the user's merit becomes difficult to measure. In the present embodiment, the release SW 35 is configured so that various functions can be set by voice commands. However, such a configuration is possible for all operation switches existing in the camera, and the release SW 35 is only one representative. When the SW function register in the CPU 17 is 00 [HEX], the release SW 35 functions as an original function. In S120, 1RSW is on (ON)
Determine whether you are. When 1RSW is on, S
At 121, a focus adjustment operation is performed. After the end of the focus adjustment operation, the state of the 2RSW is determined in S122. When the 2RSW is on, a shooting operation is performed in S123.

In S104, the SW function register sets 20 [HE].
X], the flow shifts to S130. In S130, it is determined whether only 1RSW is ON. When the switch is on, the process proceeds to step S131, and from the tele side, the width is wide.
The focal length is changed by a predetermined amount to the side. Then, the flow shifts to S144, where the SW function register is initialized. The register value is
00 [HEX], and the release SW 35 has the original function. Then, control goes to a step S100. When the SW function register is 20 [HEX] and both the 1RSW and the 2RSW are on (ON), the process goes from S132 to S133 to change the focal length from the wide side to the tele side. Then, the flow shifts to S144, where the register value is 0.
Initialized to 0 [HEX]. That is, if the SW function register is 20 [HEX], the release SW 35 is
The function is changed to the M operation switch.

In S104, the SW function register sets b0 [HE
X], the flow shifts to S140. In S140, it is determined whether only 1RSW is on (ON). When the switch is on, the Tv value is changed by one step to the high speed side in S141.
Then, the flow shifts to initialization of the register in S144. 1RSW
When both and 2RSW are on (ON), S142
Then, the flow shifts to S143. In S143, the Tv value is changed by one stage to the lower speed side. Then, the flow shifts to register initialization in S144. That is, if the SW function register is b0 [HEX], the function of the release SW 35 is changed to a Tv value change SW.

In S104, the SW function register sets 40 [HE].
X], the flow shifts to S150. In S150, it is determined whether only 1RSW is ON. If the switch is on, the process shifts to S151 to change the Av value by one step. Then, the flow shifts to register initialization in S144. 1RSW and 2
When both of the RSWs are on (ON), the process proceeds from S152 to S153. In S153, the Av value is changed by one step. Then, the flow shifts to register initialization in S144. That is, if the SW function register is 40 [HEX], the function of the release SW 35 is changed to the Av value change SW.

In the above embodiment, a camera system capable of performing an electronic photographing operation is assumed, but the present invention is also applicable to a camera system using a silver halide film. In addition, the technology described in the present invention can be effectively used in electronic devices that can perform voice operations regardless of the camera system.

Furthermore, the voice command in the present embodiment is composed of two words, a first word and a second word (ie, a word indicating an operation member or an operation portion, and an operation member (operation).
Word indicating the direction in which the command is performed), but the technology of the present invention is also effective for voice commands composed of more words (words).

[Supplementary Notes] (1) A camera capable of recognizing a voice command composed of a plurality of words generated by a camera operator and executing a predetermined operation corresponding to the voice command. Recognizing means for recognizing words constituting the language, storing means for storing the words recognized by the recognizing means, and detecting that a part of the words constituting the voice command is omitted, and storing the words in the storing means. Means capable of supplementing words abbreviated with words.

(2) A first word indicating an operation part or a shooting condition pronounced by the camera operator and a second word indicating a change in the operation direction or the shooting condition of the operation part pronounced by the camera operator. A camera operable by voice to perform a predetermined operation, comprising: recognition means for recognizing a first word and a second word; storage means for storing a word recognized by the recognition means; 1. When the second word is recognized, operation instruction data is generated based on these two words. When the recognition means recognizes only the second word, the second word and the storage means are generated. Means for generating operation instruction data based on the first word stored in the camera.

Therefore, according to the invention of the supplementary note (1), there is a recognition means for recognizing the words constituting the voice command pronounced by the user. Then, there is means for storing the recognized words. When the user omits a part of the voice command, the stored words are treated as the user's abbreviated words to compose the voice command intended by the user. Then, a predetermined operation can be performed based on the voice command.

[0041]

As described above, according to the present invention, when the same command is repeatedly executed, the operation desired by the user can be performed even if a part of the voice command is omitted.
This can reduce the complexity of the user perceiving the same word many times.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a camera capable of voice operation according to an embodiment of the present invention.

FIG. 2 is a timing chart illustrating a communication method between a DSP and a CPU in the embodiment of FIG.

FIG. 3 is a flowchart showing the operation of the DSP in the embodiment of FIG. 1;

FIG. 4 is a flowchart showing the operation of the DSP in the embodiment of FIG. 1;

FIG. 5 is a flowchart showing the operation of the CPU in the embodiment of FIG. 1;

[Explanation of symbols]

14 zoom motor 17 CPU (means for operating the camera, control means, means for temporarily changing the function of a specific operation member) 18 focus motor 22 image processing circuit 29 voice command recognition unit (voice command) 30 ... Voice memory 31 ... DSP (recognition means, first and second analysis means, storage means) 32 ... Voice input circuit 33 ... Microphone 35 ... Release switch (specific operation member)

Claims (3)

[Claims] 1. A camera capable of recognizing voice data and performing a predetermined setting operation based on the recognized voice data, the camera having a voice of a specific speaker in advance as a table, Recognizing means for recognizing the input voice by recognizing the voice with the table and converting the input voice into voice data; first analyzing means for associating the voice data with one of a plurality of camera operating members; Second analysis means for associating one of the directions in which the operating member is operated; storage means for updating and storing one output of each of the first and second analysis means; and information stored in the storage means. A camera capable of voice operation, comprising: means for defining the operation member and the operation direction of the operation member, and activating the camera in accordance with the information. 2. When no data is obtained from the first analysis means, the stored data stored in the storage means is processed as data not obtained by the first analysis means. The camera of claim 1, wherein the camera is operable by voice. 3. The camera according to claim 1, further comprising means for temporarily changing a function of a specific operation member according to an output of said first analysis means. .