Abstract: A computer-implemented method is provided for generating a plurality of templates. The method includes obtaining, by a processor device, a Recurrent Neural Network Language Model (RNNLM) trained using a first set of text data. The method further includes adapting, by the processor device, the RNNLM using a second set of text data by adding a new node corresponding to a class in both an input layer and an output layer of the RNNLM, the class being obtained from the second set of text data. The method also includes generating, by the processor device, the plurality of templates using the adapted RNNLM.

Abstract: An apparatus, method, and computer program product for adapting an acoustic model to a specific environment are defined. An adapted model obtained by adapting an original model to the specific environment using adaptation data, the original model being trained using training data and being used to calculate probabilities of context-dependent phones given an acoustic feature. Adapted probabilities obtained by adapting original probabilities using the training data and the adaptation data, the original probabilities being trained using the training data and being prior probabilities of context-dependent phones. An adapted acoustic model obtained from the adapted model and the adapted probabilities.

Abstract: The present disclosure provides an energy management system capable of improving energy efficiency. The energy management system includes: a fuel cell configured to supply energy used in a facility; a first hydrogen supply unit configured to supply hydrogen to the fuel cell by causing a power generation apparatus that uses renewable energy to perform water electrolysis; a second hydrogen supply unit configured to supply hydrogen to the fuel cell by reforming natural gas supplied via a pipeline; and a control unit configured to determine a ratio between hydrogen supplied from the first hydrogen supply unit to the fuel cell and hydrogen supplied from the second hydrogen supply unit to the fuel cell. The control unit determines the ratio in accordance with a percentage of heat energy and energy other than the heat energy with respect to the energy used in the facility.

Abstract: In a piezoelectric device, electrode layers are spaced apart from each other in the direction of the normal thereto. A first piezoelectric layer is interposed between two electrode layers of electrode layers in the direction of the normal. A second piezoelectric layer is provided on an opposite side of the first piezoelectric layer from a base portion. The second piezoelectric layer is interposed between two electrode layers of the electrode layers in the direction of the normal. The half-width of a rocking curve measured by X-ray diffraction for a lattice plane of the first piezoelectric layer substantially parallel to a first main surface is smaller than a half-width for the second piezoelectric layer. The piezoelectric constant of a material defining the first piezoelectric layer is smaller than the piezoelectric constant of a material defining the second piezoelectric layer.

Abstract: An apparatus, method, and computer program product for adapting an acoustic model to a specific environment are defined. An adapted model obtained by adapting an original model to the specific environment using adaptation data, the original model being trained using training data and being used to calculate probabilities of context-dependent phones given an acoustic feature. Adapted probabilities obtained by adapting original probabilities using the training data and the adaptation data, the original probabilities being trained using the training data and being prior probabilities of context-dependent phones. An adapted acoustic model obtained from the adapted model and the adapted probabilities.

Abstract: A technique for data augmentation for speech data is disclosed. Original speech data including a sequence of feature frames is obtained. A partially prolonged copy of the original speech data is generated by inserting one or more new frames into the sequence of the feature frames. The partially prolonged copy is output as augmented speech data for training an acoustic model for training an acoustic model.

Abstract: An airport according to the present disclosure is an airport where a vehicle is provided. The vehicle includes external supply means for supplying power to outside, and the airport includes power receiving equipment capable of receiving power from the vehicle via the external supply means. The present disclosure provides an airport capable of receiving power from a vehicle provided in the airport in the event of a power failure due to a disaster.

Abstract: A semiconductor film, including: an assembly of semiconductor quantum dots containing a metal atom; and a ligand that is coordinated to the semiconductor quantum dots and that is represented by the following Formula (A): wherein, in Formula (A), X1 represents NH, S, or O; each of X2 and X3 independently represents NH2, SH, or OH; and each of n and m independently represents an integer from 1 to 3.

Abstract: Fusion of neural networks is performed by obtaining a first neural network and a second neural network. The first and the second neural networks are the result of a parent neural network subjected to different training. A similarity score is calculated of a first component of the first neural network and a corresponding second component of the second neural network. An interpolation weight is determined for the first and the second components by using the similarity score. A neural network parameter of the first component is updated based on the interpolation weight and a corresponding neural network parameter of the second component to obtain a fused neural network.

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 computer-implemented method, computer program product, and apparatus are provided. The method includes generating a plurality of sequences of small unit tokens from a first language model that is trained with a small unit corpus including the small unit tokens, the small unit corpus having been derived by tokenization with a small unit. The method further includes tokenizing the plurality of sequences of small unit tokens by a large unit that is larger than the small unit, to create a derived large unit corpus including derived large unit tokens.

Abstract: A method for producing a patch including a support layer, and an adhesive agent layer formed on the support layer and including sodium diacetate, a pressure-sensitive adhesive base agent, and asenapine and/or a pharmaceutically acceptable salt thereof. The sodium diacetate is generated from sodium acetate in the presence of the asenapine and/or salt thereof, a content of the asenapine and/or salt thereof in terms of free asenapine in the adhesive agent layer is in range of 3.0 to 20 mg, and when a content of the asenapine and/or salt thereof in terms of free asenapine in the adhesive agent layer is 6.4 mg and the patch is in contact with skin for 24 hours, Cmax of free asenapine is in range of 0.5 to 6.0 ng/mL and tmax of free asenapine is in range of 8 to 28 hr.

Abstract: A method, computer system, and a computer program product for generating a plurality of voice data having a particular speaking style is provided. The present invention may include preparing a plurality of original voice data corresponding to at least one word or at least one phrase is prepared. The present invention may also include attenuating a low frequency component and a high frequency component in the prepared plurality of original voice data. The present invention may then include reducing power at a beginning and an end of the prepared plurality of original voice data. The present invention may further include storing a plurality of resultant voice data obtained after the attenuating and the reducing.

Abstract: A fuel injection valve includes a needle valve that controls communication between a high pressure chamber and an injection hole, a follower valve provided inside a control chamber controlled by fuel pressure inside an intermediate chamber, and an open-close valve that controls communication between a first passage and a low pressure passage and communication between a second passage and the low pressure passage. The fuel injection valve is configured to control the gradient of the fuel injection rate from the injection hole with an improved configuration.

Abstract: A technique for detecting a signal tone in an audio signal is disclosed. A determination is made as to whether a peak modulation frequency in the audio signal is in a specific range or not to obtain a determination result. A measure regarding a modulation spectrum of the audio signal is calculated. The measure is calculated based on at least components of the modulation spectrum above a specific limit of modulation frequency. By using the determination result and the measure regarding the modulation spectrum, a judgement is done as to whether the audio signal contains a signal tone or not.

Abstract: A computer-implemented method is provided for generating a plurality of templates. The method includes obtaining, by a processor device, a Recurrent Neural Network Language Model (RNNLM) trained using a first set of text data. The method further includes adapting, by the processor device, the RNNLM using a second set of text data by adding a new node corresponding to a class in both an input layer and an output layer of the RNNLM, the class being obtained from the second set of text data. The method also includes generating, by the processor device, the plurality of templates using the adapted RNNLM.

Abstract: Methods and systems for information retrieval include analyzing audio data to produce word hypotheses. Displaying the word hypotheses in motion at different respective speeds at once across a graphical display. Information is retrieved in accordance with one or more selected terms from the displayed word hypotheses.

Abstract: Methods and systems for information retrieval include analyzing audio data to produce one or more word hypotheses, each word hypothesis having an associated confidence value. The one or more word hypotheses are displayed in motion across a graphical display. Information retrieval is performed in accordance with one or more selected terms from the displayed word hypotheses.

Abstract: A patch for administering asenapine includes a support layer, and an adhesive agent layer formed on the support layer and including an adhesive base agent and asenapine and/or a pharmaceutically acceptable salt thereof. The adhesive base agent has a content in a range of 10 to 90% by mass in the adhesive agent layer and includes a natural rubber, polyisobutylene, an alkyl vinyl ether(co)polymer, polyisoprene, polybutadiene, a styrene-butadiene copolymer, a styrene-isoprene copolymer, a styrene-isoprene-styrene block copolymer, or a combination thereof. When a content of the asenapine and/or pharmaceutically acceptable salt thereof in terms of free asenapine in the adhesive agent layer is 3.4 mg, an AUC2-120 for a period starting from the time when the patch is brought into contact with a skin for 24 hours is 27,000 pg·hr/mL or more, and an AUC2-120 of an asenapine metabolite is 20% or less of the AUC2-120 of the free asenapine.

Abstract: A technique for detecting a music segment in an audio signal is disclosed. A time window is set for each section in an audio signal. A maximum and a statistic of the audio signal within the time window are calculated. A density index is computed for the section using the maximum and the statistic. The density index is a measure of the statistic relative to the maximum. The section is estimated as a music segment based, at least in part, on a condition with respect to the density index.