Abstract: A computer-implemented method and an apparatus are provided. The method includes obtaining, by a processor, a frequency spectrum of an audio signal data. The method further includes extracting, by the processor, periodic indications from the frequency spectrum. The method also includes inputting, by the processor, the periodic indications and components of the frequency spectrum into a neural network. The method additionally includes estimating, by the processor, sound identification information from the neural network.

Abstract: A computer-implemented method and an apparatus are provided. The method includes obtaining, by a processor, a frequency spectrum of an audio signal data. The method further includes extracting, by the processor, periodic indications from the frequency spectrum. The method also includes inputting, by the processor, the periodic indications and components of the frequency spectrum into a neural network. The method additionally includes estimating, by the processor, sound identification information from the neural network.

Abstract: There are provided a localized surface plasmon resonance sensing chip in which a linewidth of an absorption spectrum originating from localized plasmon resonance is narrow and with which a peak wavelength shift of an optical spectrum accompanying a change in refractive index of a surface can be accurately measured, and a localized surface plasmon resonance sensing system using this sensing chip. A sensing chip 10 includes a base 14 having a flat-plate shape, a plurality of protruding portions 16, and a metal layer 18 covering each front surface of the plurality of protruding portions 16. The protruding portions 16 each have a shape like a semi-oblate spheroid which is one of three-dimensional parts obtained by dividing an oblate spheroid in half along an equatorial plane and are arranged such that a divided surface 16a of the semi-oblate spheroid faces a front surface 14a of the base 14.

Abstract: A via model generation method includes: acquiring via arrangement information including a hole diameter of a via formed in a board including wiring layers, clearance distance between a ground conductor formed in one of the wiring layers and the via, and ground via distance between the via and a ground via coupled to the ground conductor; acquiring, by a computer, board information including a relative dielectric constant of the board; calculating a capacitance component of the via by a first electromagnetic field analysis with use of the hole diameter of the via, the clearance distance, and the relative dielectric constant of the board; calculating an inductance component of the via by a second electromagnetic field analysis with use of the hole diameter of the via, the ground via distance, and the relative dielectric constant of the board; and generating a via model including the capacitance component and the inductance component.

Abstract: A method for transferring acoustic knowledge of a trained acoustic model (AM) to a neural network (NN) includes reading, into memory, the NN and the AM, the AM being trained with target domain data, and a set of training data including a set of phoneme data, the set of training data being data obtained from a domain different from a target domain for the target domain data, inputting training data from the set of training data into the AM, calculating one or more posterior probabilities of context-dependent states corresponding to phonemes in a phoneme class of a phoneme to which each frame in the training data belongs, and generating a posterior probability vector from the one or more posterior probabilities, as a soft label for the NN, and inputting the training data into the NN and updating the NN, using the soft label.

Abstract: A case structure to accommodate a driving apparatus including a first motor and a second motor includes a first case, a second case, a first joint portion, an intermediate case, a positioning portion, and a first end portion of a second rotor or a second rotary shaft of the second motor. A stator of the first motor is to be attached to the first case. The second case is joined to the first case. The first joint portion is provided by joining a first end surface of the first case and an end surface of the second case together. The intermediate case is disposed on an inner diameter side of the first joint portion and attached to a stator of the second motor and to the first case. The intermediate case is positioned at the positioning portion with respect to the second case.

Abstract: Methods, systems, and computer programs are provided for training a front-end neural network (“front-end NN”) and a back-end neural network (“back-end NN”). The method includes: combining the back-end NN with the front-end NN so that an output layer of the front-end NN is also an input layer of the back-end NN to form a joint layer to thereby generate a combined NN; and training the combined NN for a speech recognition with a set of utterances as training data, a plurality of specific units in the joint layer being dropped during the training and the plurality of the specific units corresponding to one or more common frequency bands. The front-end NN may be configured to estimate clean frequency filter bank features from noisy input features; or, to estimate clean frequency filter bank features from noisy frequency filter bank input features in the same feature space.

Abstract: A hybrid vehicle driving system includes: a generator; a motor; a case which accommodates the generator and the motor; and a power control unit for controlling the generator and the motor, the generator and the motor being disposed side by side on a same axis within the case. The power control unit is mounted on the case by connecting a unit-side generator connector and a unit-side motor connector which are provided on a bottom surface of the power control unit with a case-side generator connector and a case-side motor connector which are disposed on the case, directly and respectively. The case is fixed to a vehicle framework member via a mount member, and a fixing point where the case and the mount member are fixed together is disposed near the case-side generator connector and the case-side motor connector.

Abstract: Methods and systems are provided for separating a target speech from a plurality of other speeches having different directions of arrival. One of the methods includes obtaining speech signals from speech input devices disposed apart in predetermined distances from one another, calculating a direction of arrival of target speeches and directions of arrival of other speeches other than the target speeches for each of at least one pair of speech input devices, calculating an aliasing metric, wherein the aliasing metric indicates which frequency band of speeches is susceptible to spatial aliasing, enhancing speech signals arrived from the direction of arrival of the target speech signals, based on the speech signals and the direction of arrival of the target speeches, to generate the enhanced speech signals, reading a probability model, and inputting the enhanced speech signals and the aliasing metric to the probability model to output target speeches.

Abstract: A birefringence measurement device includes a light flux generator for generating light flux, a light flux irradiator for irradiating a measurement target with the light flux in a predetermined polarization state, an imaging optical system for forming an image from light flux transmitted through the measurement target, a polarization/diffraction grating positioned within the imaging optical system, an image pickup for generating a light-dark signal related to brightness of the image, and an output for outputting information regarding a phase difference for the light flux. The phase difference resulting from the transmission through the measurement target is determined on the basis of the light-dark signal. The image pickup generates the light-dark signal for the image based on at least one beam of diffracted light from among a plurality of beams of diffracted light produced by the grating. A two-dimensional distribution of birefringence is obtained in real time without a rotating mechanism.

Abstract: A method, for testing words defined in a pronunciation lexicon used in an automatic speech recognition (ASR) system, is provided. The method includes: obtaining test sentences which can be accepted by a language model used in the ASR system. The test sentences cover words defined in the pronunciation lexicon. The method further includes obtaining variations of speech data corresponding to each test sentence, and obtaining a plurality of texts by recognizing the variations of speech data, or a plurality of texts generated by recognizing the variation of speech data. The method also includes constructing a word graph, using the plurality of texts, for each test sentence, where each word in the word graph corresponds to each word defined in the pronunciation lexicon; and determining whether or not all or parts of words in a test sentence are present in a path of the word graph derived from the test sentence.

Abstract: Methods and systems are provided for separating a target speech from a plurality of other speeches having different directions of arrival. One of the methods includes obtaining speech signals from speech input devices disposed apart in predetermined distances from one another, calculating a direction of arrival of target speeches and directions of arrival of other speeches other than the target speeches for each of at least one pair of speech input devices, calculating an aliasing metric, wherein the aliasing metric indicates which frequency band of speeches is susceptible to spatial aliasing, enhancing speech signals arrived from the direction of arrival of the target speech signals, based on the speech signals and the direction of arrival of the target speeches, to generate the enhanced speech signals, reading a probability model, and inputting the enhanced speech signals and the aliasing metric to the probability model to output target speeches.

Abstract: A method for learning a neural network having a plurality of filters for extracting local features performed by a computing device is disclosed. The computing device calculates a plurality of projection parameter sets by analyzing one or more training data. The plurality of the projection parameter sets define a projection of each training data into a new space and each projection parameter set has a same size as the filters in the neural network. At least part of the plurality of the projection parameter sets is set as initial parameters of at least part of the plurality of the filters in the neural network for training.

Abstract: A method, for testing words defined in a pronunciation lexicon used in an automatic speech recognition (ASR) system, is provided. The method includes: obtaining test sentences which can be accepted by a language model used in the ASR system. The test sentences cover words defined in the pronunciation lexicon. The method further includes obtaining variations of speech data corresponding to each test sentence, and obtaining a plurality of texts by recognizing the variations of speech data, or a plurality of texts generated by recognizing the variation of speech data. The method also includes constructing a word graph, using the plurality of texts, for each test sentence, where each word in the word graph corresponds to each word defined in the pronunciation lexicon; and determining whether or not all or parts of words in a test sentence are present in a path of the word graph derived from the test sentence.

Abstract: It is possible to provide a new information recording/reproduction method and a device which can realize a small-size large-capacity memory having a characteristic equivalent to or higher than a hologram memory. The optical information recording/reproduction device includes: recording light generator (51) which generates a recording light (55) in a polarization state having two mutually orthogonal polarization components with a phase difference at an arbitrary polarization base; reproduction light generator (61) which generates a reproduction light (65) in a polarization state having only a single polarization component at a arbitrary polarization basis; recording medium (71) in which optical information is recorded by recording light (55) and the recorded optical information is reproduced by reproduction light; and optical information detector (polarimeter 81) which retrieves information light (72) after being applied to recording medium (71) and detects the light as optical information.

Abstract: There are provided a localized surface plasmon resonance sensing chip in which a linewidth of an absorption spectrum originating from localized plasmon resonance is narrow and with which a peak wavelength shift of an optical spectrum accompanying a change in refractive index of a surface can be accurately measured, and a localized surface plasmon resonance sensing system using this sensing chip. A sensing chip 10 includes a base 14 having a flat-plate shape, a plurality of protruding portions 16, and a metal layer 18 covering each front surface of the plurality of protruding portions 16. The protruding portions 16 each have a shape like a semi-oblate spheroid which is one of three-dimensional parts obtained by dividing an oblate spheroid in half along an equatorial plane and are arranged such that a divided surface 16a of the semi-oblate spheroid faces a front surface 14a of the base 14.

Abstract: A method, a system, and a computer program product are provided for discriminatively training a feature-space transform. The method includes performing feature-space discriminative training (f-DT) on an initialized feature-space transform, using manually transcribed data, to obtain a pre-stage trained feature-space transform. The method further includes performing f-DT on the pre-stage trained feature-space transform as a newly initialized feature-space transform, using automatically transcribed data, to obtain a main-stage trained feature-space transform. The method additionally includes performing f-DT on the main-stage trained feature-space transform as a newly initialized feature-space transform, using manually transcribed data, to obtain a post-stage trained feature-space transform.

Abstract: An acquirer acquires, for the on-the path categories situated on the path from the topmost category of a hierarchical structure comprising categories into which products or serves are classified to each of a category of interest and the categories immediately below the category of interest, the frequencies of the names of the on-the-path categories and a keyword co-occurring in a search query given to a search device. An identifier identifies the category of interest as a category candidate immediately above a category of which the name is given by the keyword when the frequencies acquired for the on-the-path categories satisfy a candidate condition associated by the search device.

Abstract: Methods and systems are provided for separating a target speech from a plurality of other speeches having different directions of arrival. One of the methods includes obtaining speech signals from speech input devices disposed apart in predetermined distances from one another, calculating a direction of arrival of target speeches and directions of arrival of other speeches other than the target speeches for each of at least one pair of speech input devices, calculating an aliasing metric, wherein the aliasing metric indicates which frequency band of speeches is susceptible to spatial aliasing, enhancing speech signals arrived from the direction of arrival of the target speech signals, based on the speech signals and the direction of arrival of the target speeches, to generate the enhanced speech signals, reading a probability model, and inputting the enhanced speech signals and the aliasing metric to the probability model to output target speeches.

Abstract: A method, a system, and a computer program product detect a clipping event in audio signals. The method includes digitalizing audio signals having limited frequency bands, at a sampling frequency which is greater than two times as large as the maximum frequency component of the audio signal; and detecting a clipping event of the audio signals, based on magnitudes of spectrum in a bandwidth which is greater than or equal to the limited frequency band. The sampling frequency may be greater than or equal to three times as large as the maximum frequency component of the audio signal. The detection of a clipping event may include determining, for each frame, whether or not a sum or average of the magnitudes of spectrum at the bandwidth which is greater than or equal to the limited frequency band is larger than a predetermined threshold.