Abstract: Provided is a model learning technology to learn a model in consideration of a difference in label assignment accuracy between experts and non-experts.

Abstract: In one embodiment, an electron beam inspection apparatus includes an optical system irradiating a substrate with primary electron beams, a beam separator separating, from the primary electron beams, secondary electron beams emitted as a result of irradiating the substrate with the primary electron beams, a detector detecting the secondary electron beams separated, a movable stage on which the substrate is placed, a support base supporting the substrate on the stage, and an applying unit applying a first voltage to the substrate. The support base includes a plurality of support pins that support the substrate from below. The support pins each include a columnar insulator and a metal film disposed in the insulator. A second voltage is applied to the metal film.

Abstract: The present invention provides emotion recognition technology that achieves high emotion recognition accuracy for all speakers.

Abstract: A multi-electron beam inspection apparatus includes first sample hold circuits, each configured to include a capacitor and a switch arranged for each of electrodes of each of a plurality of multipoles, and to hold, using the capacitor and the switch, a potential to be applied to the each of the electrodes, power sources configured to apply potentials to the plurality of first sample hold circuits, a control circuit configured to control the plurality of first sample hold circuits such that the plurality of potentials having been applied to the plurality of first sample hold circuits are held, in synchronization with swinging back of the collective beam deflection by the objective deflector, by a plurality of second sample hold circuits selected from the plurality of first sample hold circuits, and a detector configured to detect multiple secondary electron beams emitted because the substrate is irradiated with the multiple primary electron beams.

Abstract: A recognition apparatus includes a classification unit that estimates a non-linguistic and para-linguistic information label to be imparted by an n-th listener from an acoustic feature amount of speech data to be recognized using an n-th classification model, and an integration unit that integrates estimation results of the non-linguistic and para-linguistic information labels for N listeners and obtains non-linguistic and para-linguistic information estimation results as a recognition apparatus for the speech data to be recognized, and the n-th classification model is a classification model trained using training speech data and a non-linguistic and para-linguistic information label imparted to the training speech data by the n-th listener as training data.

Abstract: Provided is a cosmetic comprising nano bubble-liquid and cosmetic ingredients. The cosmetic according to the present invention comprises nano bubble-liquid and cosmetic ingredients, in which the nano bubble-liquid is liquid in a nano bubble state comprising a liquid medium and bubbles, the bubbles having a diameter of 5 nm to 500 nm.

Abstract: A learning apparatus includes: a speaker vector learning unit configured to learn a speaker vector extraction parameter ? based on one or more items of learning speech voice data in a speaker vector voice database; a non-speaker-individuality sound model learning unit configured to create a probability distribution model using a frequency component of one or more items of non-speaker-individuality sound data in a non-speaker-individuality sound database and calculate an internal parameter of the probability distribution model; and an age level estimation model learning unit configured to extract a speaker vector from voice data in an age level estimation model-learning voice database using the speaker vector extraction parameter ?, calculate a non-speaker-individuality sound likelihood vector from voice data in the age level estimation model-learning voice database using the internal parameters ? and ?, and learn, with input of the speaker vector and the non-speaker-individuality sound likelihood vector, a pa

Abstract: Estimation accuracies of a conversation satisfaction and a speech satisfaction are improved. A learning data storage unit (10) stores learning data including a conversation voice containing a conversation including a plurality of speeches, a correct answer value of a conversation satisfaction for the conversation, and a correct answer value of a speech satisfaction for each speech included in the conversation.

Abstract: With correct emotion classes selected as correct values of an emotion of an utterer of a first utterance from among a plurality of emotion classes C1, . . . , CK by listeners who have listened to the first utterance, as an input, the numbers of times ni that emotion classes Ci have been selected as the correct emotion classes are obtained, and rates of the numbers of times nk to a sum total of the numbers of times n1, . . . , nK or smoothed values of the rates are obtained as correct emotion soft labels tk(s) corresponding to the first utterance.

Abstract: A conveyance route switching mechanism and a paper sheet handling apparatus that includes the conveyance route switching mechanism include a driving source, a gate, a first gear, and an internal gear. The driving source includes a driving shaft. The gate includes a gate shaft, and a blade that is provided on the gate shaft, and switches conveyance routes of paper sheets. The first gear is provided on the gate shaft. The internal gear meshes with the first gear. According to rotation of the driving shaft, the gate shaft rotates on an axis of the gate shaft, and revolves with the driving shaft as a rotation center while the first gear meshes with the internal gear.

Abstract: In a centering mechanism and a paper sheet handling apparatus including the centering mechanism, a centering unit conveys a paper sheet in a pinched state, and centers a position of the paper sheet in a width direction orthogonal to a conveyance direction of the paper sheet by inclining with respect to the conveyance direction. In addition, the paper sheet is delivered to a downstream side conveyance unit from the centering unit in a state in which the centering unit pinches the paper sheet, and the downstream side conveyance unit conveys the paper sheet while pinching the paper sheet at pinch pressure stronger than pinch pressure at which the centering unit pinches the paper sheet.

Abstract: A paper sheet handling apparatus includes: a first facing section and a second facing section that are disposed to face each other across an insertion/take-out space; a partition section that is disposed between the first and second facing sections so as to be capable of moving in a facing direction in which the first and second facing sections face each other, forms, within the insertion/take-out space, an insertion space between the partition section and the first facing section, and forms, within the insertion/take-out space, a take-out space between the partition section and the second facing section. The partition section includes a movable member provided at a leading end portion of the partition section on an insertion/take-out port side and capable of moving toward each of the first facing section and the second facing section.

Abstract: A paper sheet handling apparatus includes: a first facing section and a second facing section which are arranged so as to face each other in a facing direction with an insertion space interposed therebetween; and a conveyance section that conveys a paper sheet. The first facing section includes a first shutter that openably closes a first opening portion, and is disposed so as to be movable, in the facing direction, to an insertion position at a time when the paper sheet is inserted and a conveyance position at a time when the paper sheet is conveyed. The first facing section and the conveyance section include first shutter opening/closing units which open the first opening portion by meshing with each other to open the first shutter when the first facing section moves from the insertion position to the conveyance position.

Abstract: A paper sheet handling apparatus includes a support member that is disposed so as to face a taking-out port in a taking-out space in which a paper sheet is taken out from the taking-out port, and supports a lower end of the paper sheet. The support member moves toward the taking-out port at a time when the paper sheet is taken out.

Abstract: State-of-satisfaction change pattern models each including a set of transition weights in state sequences of the states of satisfaction are obtained for predetermined change patterns of the states of satisfaction, and a state-of-satisfaction estimation model for obtaining the posteriori probability of the utterance feature amount given the state of satisfaction of an utterer is obtained by using the utterance-for-learning feature amount and a correct value of the state of satisfaction of an utterer who gave an utterance for learning corresponding to the utterance-for-learning feature amount. By using the input utterance feature amount and the state-of-satisfaction change pattern models and the state-of-satisfaction estimation model, an estimated value of the state of satisfaction of an utterer who gave an utterance corresponding to the input utterance feature amount is obtained.

Abstract: A multiple secondary electron beam alignment method includes scanning a plurality of first detection elements of a multi-detector, which are arrayed in a grid, with multiple secondary electron beams emitted from a surface of a target object on a stage, detecting a plurality of beams including a corner beam located at a corner in the multiple secondary electron beams by the multi-detector, calculating a positional relationship between the plurality of beams including the corner beam and a plurality of second detection elements, which have detected the plurality of beams including the corner beam, in the plurality of first detection elements, calculating, based on the positional relationship, a shift amount for aligning the plurality of first detection elements with the multiple secondary electron beams, and moving, using the shift amount, the multi-detector relatively to the multiple secondary electron beams.

Abstract: An urgency level estimation technique of estimating an urgency level of a speaker for free uttered speech, which does not require a specific word, is provided. An urgency level estimation apparatus includes a feature amount extracting part configured to extract a feature amount of an utterance from uttered speech, and an urgency level estimating part configured to estimate an urgency level of a speaker of the uttered speech from the feature amount based on a relationship between a feature amount extracted from uttered speech and an urgency level of a speaker of the uttered speech, the relationship being determined in advance, and the feature amount includes at least one of a feature indicating speaking speed of the uttered speech, a feature indicating voice pitch of the uttered speech and a feature indicating a power level of the uttered speech.

Abstract: An impression estimation technique without the need of voice recognition is provided. An impression estimation device includes an estimation unit configured to estimate an impression of a voice signal s by defining p1<p2 and using a first feature amount obtained based on a first analysis time length p1 for the voice signal s and a second feature amount obtained based on a second analysis time length p2 for the voice signal s. A learning device includes a learning unit configured to learn an estimation model which estimates the impression of the voice signal by defining p1<p2 and using a first feature amount for learning obtained based on the first analysis time length p1 for a voice signal for learning sL, a second feature amount for learning obtained based on the second analysis time length p2 for the voice signal for learning sL, and an impression label imparted to the voice signal for learning sL.

Abstract: A conduction inspection method for a multipole aberration corrector according to one aspect of the present invention includes applying, in a state where a predetermined potential has been applied to each shield electrode, an inspection charged particle beam to pass through a first opening, a second opening, and a third opening, using a multipole aberration corrector which includes an upper-stage substrate where the first opening is formed and a shield electrode is arranged around the first opening, a middle-stage substrate where the second opening is formed, a plurality of control electrodes are disposed to be opposite each other across the second opening, and a plurality of wirings are arranged to be individually connected to one of the plurality of control electrodes which are different from each other, and a lower-stage substrate where the third opening is formed and a shield electrode is arranged around the third opening, and which corrects aberration of a correction charged particle beam passing through

Abstract: An electron gun according to one aspect of the present invention includes an emission source configured to emit an electron beam, an aperture array substrate, where a plurality of passage holes are formed, configured to form multiple beams by letting portions of the electron beam individually pass through the plurality of passage holes, and a first electrode, where a first opening through which the electron beam can pass is formed, configured to include an opposing plane which is located at a side of the emission source with respect to the aperture array substrate and facing a surface of the aperture array substrate and whose outer diameter is smaller than an outer diameter of the aperture array substrate, the first electrode configured to be applied with a first control potential.