Abstract: Provided is a speech processing apparatus including a word string estimation unit that estimates a word string equivalent to input speech among word strings included in dictionary data, and a calculation unit that calculates, for an element part constituting the word string estimated by the word string estimation unit, a certainty factor in which a content of the element part is equivalent to a content of a corresponding part in the input speech.

Abstract: There is provided a speech processing apparatus to improve the flexibility of processing regarding speech recognition, the speech processing apparatus including: a determination unit configured to determine how to deal with a recognition result of speech data obtained by a first speech recognizer on a basis of a comparison between a certainty factor of the recognition result of the speech data obtained by the first speech recognizer and a threshold; and a threshold setting unit configured to set dynamically the threshold. The method further comprises using three operation modes where third, second and first modes comprise of three, two and one recognizers respectively, and the threshold in the third mode is lower than the second mode and higher than the first mode.

Abstract: [Object] To obtain a more precise certainty factor for an estimated word string. [Solution] A speech processing apparatus including: a word string estimation unit configured to estimate a word string equivalent to input speech among word strings included in dictionary data; and a calculation unit configured to calculate, for an element part constituting the word string estimated by the word string estimation unit, a certainty factor in which a content of the element part is equivalent to a content of a corresponding part in the input speech.

Abstract: There is provided a speech processing apparatus to improve the flexibility of processing regarding speech recognition, the speech processing apparatus including: a determination unit configured to determine how to deal with a recognition result of speech data obtained by a first speech recognizer on a basis of a comparison between a certainty factor of the recognition result of the speech data obtained by the first speech recognizer and a threshold; and a threshold setting unit configured to set dynamically the threshold.

Abstract: A mechanical noise suppression apparatus includes: a framing section adapted to divide an input signal into frames of a predetermined time length; a Fourier transform section adapted to transform framed signals obtained by the framing section into a frequency spectrum of a frequency domain; a mechanical noise reduction section adapted to correct the frequency spectrum of the input signal obtained by the Fourier transform section based on frequency spectrum information of mechanical noise to suppress the mechanical noise; an inverse Fourier transform section adapted to return the frequency spectrum corrected by the mechanical noise reduction section into framed signals of a time domain; and a frame synthesis section adapted to carry out frame synthesis of the framed signals of frames obtained by the inverse Fourier transform section to obtain an output signal in which the mechanical noise is suppressed.

Abstract: A signal processing device includes a sound collecting unit configured to collect sound, a covering detecting unit configured to detect a covered state of the sound collecting unit on the basis of a resonance frequency and a magnitude of a component of the resonance frequency in a frequency characteristic of an acoustic signal obtained through sound collection performed by the sound collecting unit, and an apparatus control determining unit configured to determine a type of control to be performed on a target apparatus in accordance with the covered state of the sound collecting unit detected by the covering detecting unit.

Abstract: A mechanical noise suppression apparatus includes: a framing section adapted to divide an input signal into frames of a predetermined time length; a Fourier transform section adapted to transform framed signals obtained by the framing section into a frequency spectrum of a frequency domain; a mechanical noise reduction section adapted to correct the frequency spectrum of the input signal obtained by the Fourier transform section based on frequency spectrum information of mechanical noise to suppress the mechanical noise; an inverse Fourier transform section adapted to return the frequency spectrum corrected by the mechanical noise reduction section into framed signals of a time domain; and a frame synthesis section adapted to carry out frame synthesis of the framed signals of frames obtained by the inverse Fourier transform section to obtain an output signal in which the mechanical noise is suppressed.

Abstract: The emotion is to be added to the synthesized speech as the prosodic feature of the language is maintained. In a speech synthesis device 200, a language processor 201 generates a string of pronunciation marks from the text, and a prosodic data generating unit 202 creates prosodic data, expressing the time duration, pitch, sound volume or the like parameters of phonemes, based on the string of pronunciation marks. A constraint information generating unit 203 is fed with the prosodic data and with the string of pronunciation marks to generate the constraint information which limits the changes in the parameters to add the so generated constraint information to the prosodic data. A emotion filter 204, fed with the prosodic data, to which has been added the constraint information, changes the parameters of the prosodic data, within the constraint, responsive to the feeling state information, imparted to it.

Abstract: The emotion is to be added to the synthesized speech as the prosodic feature of the language is maintained. In a speech synthesis device 200, a language processor 201 generates a string of pronunciation marks from the text, and a prosodic data generating unit 202 creates prosodic data, expressing the time duration, pitch, sound volume or the like parameters of phonemes, based on the string of pronunciation marks. A constraint information generating unit 203 is fed with the prosodic data and with the string of pronunciation marks to generate the constraint information which limits the changes in the parameters to add the so generated constraint information to the prosodic data. A emotion filter 204, fed with the prosodic data, to which has been added the constraint information, changes the parameters of the prosodic data, within the constraint, responsive to the feeling state information, imparted to it.

Abstract: A camera which uses a film cartridge having a magnetic recording part for each frame portion thereof and writes magnetic information in the magnetic recording part of each frame, in rewinding the film after completion of photographing on all frames, is arranged to effectively prevent information from being recorded again at the time of rewinding the film for any frame having magnetic information already recorded in a case where the film cartridge loaded into the camera contains a film in which part of frames have been already exposed. In the camera, when a film cartridge having some of film frames already exposed is loaded, the camera stores the position of a leading unexposed frame and to permit recording of magnetic information up to the leading unexposed frame in performing the recording action at the time of film rewinding.

Abstract: An apparatus such as a camera which makes it possible to start using a film at a position of an unused frame comprises a detecting device which detects a position of an unused frame of a film, and a control device which executes a control operation so that the film can start to be used at the position of the unused frame in accordance with a detection result by the detecting device, the control device making a determination as to a state of noise which acts on the detecting device and varying the control operation in accordance with a result of the determination.

Abstract: A camera comprises discrimination means for discriminating whether an image stabilizing function is active or not and control means responsive to the discrimination by the discrimination means that the image stabilizing function is active for changing a shutter speed for an image blur warning or inhibiting the image blur warning.

Abstract: An image processing apparatus for visual axis detection in which a frame transfer type CCD is used as an area sensor for converting an incident eyeball image into an electrical signal. Use of the frame transfer type LCD will widen the light receiving area on the surface of the CCD and enhance the numerical aperture, as to well as greatly enhance the probability of detection of Purkinje's image and enhance the sensitivity to the infrared range to thereby make the Purkinje's image detectable by a smaller quantity of illumination.

Abstract: An image stabilizing device for a camera includes an image stabilizing means for preventing an image blur of the camera and a control means for changing a function of the image stabilizing means in accordance with a photometry or focus mode of the camera.

Abstract: This invention concerns with an electronic flash unit in which, as two capacitors of large and small capacitances are charged, even when a trigger operation is actuated before the capacitor of large capacitance is fully charged, it is made possible with the help of the charge from the capacitor of small capacitance to fire the flash tube. Particularly in application of the invention to the above-described type of electronic flash unit, as the battery for use in charging the capacitors also serves to drive another load for a time which can fall in coincidence with the period of charging the capacitors, when the driving of the load is started, the charging of the capacitor of large capacitance is inhibited while the charging of the capacitor of small capacitance is permitted to go on, thereby it being made possible to carry out the driving of the load with high reliability so that the correct flash exposure is made while still maintaining the quickness of snap shots.

Abstract: In a system for setting the aperture in a camera for flash photography, a minimum aperture is computed in response to parameters such as distance to an object, stroboscopic guide number and film sensitivity. In one embodiment, a predetermined aperture value is preestablished in the system and the computed minimum aperture is compared therewith. Where the computed minimum aperture is below such predetermined aperture value, such computed minimum aperture is used in flash photography. On the other hand, when the computed minimum aperture is above such predetermined aperture value, an aperture larger than the predetermined minimum aperture value is used in flash photography. Other embodiments for flash aperture setting are also set forth.

Abstract: An apparatus for determining the amount of flash having a first light receiving element for measuring light with respect to a first region (central region) of the frame, a second light receiving element for measuring light with respect to a second region (marginal region). The apparatus determines the amount of flash in accordance with the ratio of the outputs per unit area of the first and second light receiving elements.

Abstract: A camera system capable of performing flash photography is arranged to perform pre-flashing to detect beforehand the quantity of flash light to be obtained by main flashing. The system makes a display to show whether the flash light quantity thus detected assures an adequate exposure.