JPH01191839A - Speech recognizing camera - Google Patents

Abstract

PURPOSE:To facilitate the voice registration by a simple constitution by constituting the title camera so that the voice registration can be executed, when the operating switch of the camera is operated in a registration mode. CONSTITUTION:At the time of registering a voice, an operating switch whose operation by a voice is desired, among the operating switches is turned on in a state that a mode switch is turned ON, and a voice is inputted from a microphone 1. In a speech recognizing circuit 3, a signal is outputted to an SO terminal of a microcomputer 4 and the microcomputer 4 is set to an inoperable state thereby, and based on signals from the switch 16 and the selected operating switch, the inputted voice is registered as an instruction voice for executing the same operation as the operation of a camera which is started by this operating switch. Subsequently, when the switch 16 is turned OFF, the camera becomes a recognition mode, a start signal is outputted to the SO terminal of the microcomputer 4 from the circuit 3 and the microcomputer 4 is started. In such a way, the microcomputer 4 is operated by both the output of the circuit 3 and the outputs of the switches 12-15.

Description

DETAILED DESCRIPTION OF THE INVENTION (Field of Industrial Application) The present invention relates to a voice recognition camera operated by voice input.

(Prior art) With the advancement of voice recognition technology, voice recognition cameras are being developed in which when a pre-registered voice or keyword (command voice) is input, the camera recognizes the voice and performs a predetermined action. ing. If the camera is activated by voice, the user can release the shutter by simply saying, for example, ``release,'' and there is no need to worry about ``shake,'' and the camera can be operated remotely.

Conventionally, as a method for registering voice commands in this type of camera, a method has been considered in which the recognition circuit system is put into a registration mode and registration is performed according to an order determined by the circuit system. For example, if multiple switches are provided, a command voice (for example, "
``Release'') is registered, and a command voice (for example, ``SELF'') for pressing the second switch to operate the self-timer is registered.

Furthermore, a method has also been considered in which the function to be operated is displayed on the display means and the function is registered accordingly.

However, according to this conventional method, the user must know the correspondence between each input switch and each camera operation, and it is very troublesome to register the sound. Registration errors are likely to occur, such as pressing the input switch for self-timer operation without realizing it. Furthermore, similar troubles occur when changing the command voice.

Furthermore, the registration method using display means requires display v7&fI that is easy to understand, and the apparatus becomes complicated.

(Objective and Structure of the Invention) The present invention has been made in view of the above points, and an object of the present invention is to enable easy registration of command voices with a simple configuration.

In order to achieve this object, the present invention is configured such that when a camera operation switch is operated in the registration mode, a command voice to perform the same camera operation as that started by the operation switch is registered. .

(Embodiment) FIG. 1 is a block diagram showing a circuit configuration of an embodiment of a voice recognition camera according to the present invention. 3 is an amplifier that amplifies the input voice signal; 3 is a voice recognition circuit that determines whether the input voice signal matches the registered command voice and outputs a 2-bit signal corresponding to the voice when the input voice signal matches the registered command voice; 4 is a microcomputer that controls each part of the camera according to the output signal from the voice recognition circuit 3; 5 is a photometry circuit that measures the brightness of the subject using a photodiode 6; and 7 is a circuit that turns on and off the magnet 8 according to the brightness of the subject. A shutter control circuit 9 controls the shutter speed, an AF circuit 9 detects the focal point of the photographic lens and moves the photographic lens to the focal point, and a motor drive circuit 10 drives the film feeding motor 11.

Next, to explain the camera operation switches, 12.13
are S I, which are turned on by the release button, respectively.
It is an S2 switch, and when you press the release button down one step lightly, the 81 switch 12 turns on, and when you press it down even further, both the S switch 12 and the S2 switch 13 turn on. In the photographing sequence of the camera, when the SI switch 12 is turned on, photometry and distance measurement are performed in that order, and when the S2 switch 13 is turned on, lens driving, shutter driving, and film winding are performed. 14 is a self-timer switch that operates a self-timer, and 15 is a rewind switch that is operated when rewinding the film. One of the terminals of the operation switches 12 to 15 described above is grounded, and the other terminal is connected to the input terminals 1o to I3 of the microcomputer 4 and the voice recognition circuit 3 via a diode.

Reference numeral 16 denotes a mode switch for switching between recognition mode and registration mode, one end of which is connected to the voice recognition circuit 3. When the mode switch 16 is on, it is a registration mode, and when it is off, it is a recognition mode.

Next, the operation of the embodiment will be explained.

When registering a voice, the mode switch 16 is kept on, the operation switch among the operation switches 12 to 15 that is desired to be operated by voice is turned on, and the voice is inputted from the microphone 1. In the voice recognition circuit 3, a signal is output to the SO terminal of the microcomputer 4 to put the microcomputer 4 into an inactive state, and based on the signals from the mode switch 16 and the selected operation switch, the input voice or the selected operation switch is output. It is registered as a command voice to perform an operation similar to the camera operation started by . Operation switch 12 is shown in the table below.
Input terminal ■ of the speech recognition circuit 3 when each of ~15 is turned on. An example of the signal level of -I3 and the command voice is shown.

For example, press the release button lightly and press S, switch 1.
2, input "focus lock" from the microphone L, press the release button even deeper, turn on the S2 switch 13, input "release", and then similarly turn on the self-timer switch 14 and enter "self". , turn on the rewind switch 15' and input "rewind". As a result, each voice is registered as a command voice that is equally useful as the corresponding operation switch.

Next, the operation in recognition mode will be explained.

When the mode switch 16 is turned off, the camera enters the recognition mode, and the voice recognition circuit 3 outputs an activation signal to the SO terminal of the microcomputer 4, thereby placing the microcomputer 4 in an activated state. As a result, the microcomputer 4 can be operated by either the output from the voice recognition circuit 3 or the output from the operation switches 12 to 15.

Now, to explain using the flowchart in FIG. 2, when a voice is input (F-1), the voice recognition circuit 3 determines whether the input voice matches the command voice (F-2).
, if they match, send the corresponding signal to the microcontroller 4. ,
An example of this signal output to the D1 terminal (F-3) is shown at the right end of the table above. For example, when "focus lock" is recognized, the input terminal of microcomputer 4 is activated. , D, to “0” rO
J signal is output.

The microcomputer 4 operates the camera according to the input voice based on the output signal from the voice recognition circuit 3 (F-4). In other words, photometry can be performed by voice input of "Focus Lock".
Distance measurement is performed, and the ``release'' button drives the lens, shutter, and winds the film. Also, if there is a voice input of "self", the self-timer is activated, and if there is a voice input of "rewind", rewinding of the film will start.

As described above, according to the present invention, voice registration is performed by operating the operation switch of the camera, so registration is extremely simple, and registration errors are therefore less likely to occur. It is also easy to change the command voice. Furthermore, since the camera operation switch is also used as an input switch for registration, it is possible to construct a close-up camera at low cost without adding any new parts.

By the way, the speech recognition circuit in the above embodiment is, for example, a speech recognition IC based on so-called specific speaker speech recognition that registers a spectrum analysis pattern of input speech of a specific speaker.
is used. However, the present invention can be applied regardless of the type of voice recognition system, and if a voice recognition camera is developed in the near future that performs linguistic analysis of input voice and understands the meaning of the voice to operate the camera. , it goes without saying that this method can also be applied to such cameras.

(Effects of the Invention) As explained above, according to the present invention, since the configuration is such that voice registration is performed when the camera operation switch is operated in the registration mode, voice registration can be easily performed with an extremely simple configuration. I can do it.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing a circuit configuration of an embodiment of a voice recognition camera according to the present invention, and FIG. 2 is a flowchart illustrating the operation of the embodiment in recognition mode. 1...Microphone, 3...Voice recognition circuit, 12...S
1 switch, l3-S2 switch, 14... Self-timer switch, 15... Rewind switch, 16.
・・Mode switch

Claims (2)

[Claims] (1) A voice recognition camera that operates based on the input of voice commands has a registration mode and a recognition mode, and when a camera operation switch is operated in the registration mode, the same camera operation as that started by the operation switch is performed. 1. A voice recognition camera characterized by being provided with voice recognition means for accepting registration of voice commands for performing. (2) The voice recognition camera according to claim 1, wherein the voice registration by the voice recognition means is voice registration for specific speaker recognition.