Abstract: A learning method includes the following processes. A shuffling process acquires learning data arranged in a time series and rearranges the learning data in an order different from the order of the time series. A learning process trains an acoustic model using the learning data rearranged through the shuffling process.

Abstract: Execution speed of a thread is dynamically restored while reducing influence on processing accuracy of the whole system. A thread synchronization device (10) achieves synchronization among N threads (1-1, . . . , 1-N) to perform parallel processing by dividing time-series data into a plurality of pieces of data. Environment variables which achieve a trade-off between processing accuracy and execution speed are individually set at the threads (1-1, . . . , 1-N). An execution speed calculation unit (2) calculates execution speed of each of the threads. An environment variable update unit (3) updates the environment variables in accordance with the execution speed of the threads.

Abstract: A learning device includes a learning unit learning, with a first feature value having a first feature and given a first value label, a second feature value having a second feature and given a second value label and a third feature value having a feature between the first feature and the second feature and given a value label having a value between the first value label and the second value label as teacher data, a model for estimating which of the first feature and the second feature an input feature value sequence has.

Abstract: Recognition results are acquired with high responsiveness without being affected by a network communication state. A speech recognition control device (1) acquires recognition results from a speech recognition device (2) with which it communicates through a network (3) and a speech recognition unit (13). A communication state measuring unit (11) measures a communication state of the network (3). A speech recognition requesting unit (12) transmits a request for a speech recognition process to each of the speech recognition device (2) and the speech recognition unit (13) with a timeout time set in accordance with an immediately prior communication state of the network (3). A recognition result output unit (14) outputs a recognition result based on a recognition result received from one or recognition results received from both of the speech recognition device (2) and the speech recognition unit (13).

Abstract: An identification model learning device capable of improving an identification model for a particular speech vocal sound is provided. An identification model learning device includes: an identification model learning unit configured to learn, based on learning data including a feature sequence in a frame unit of a speech and a binary label indicating whether the speech is a particular speech, an identification model including an input layer that accepts the feature sequence in the frame unit as an input and outputs an output result to an intermediate layer, one or more intermediate layers that accept an output result of the input layer or an immediately previous intermediate layer as an input and output a processing result, an integration layer that accepts an output result of a final intermediate layer as an input and outputs a processing result in a speech unit, and an output layer that outputs the label from the output of the integration layer.

Abstract: A model training device includes: a feature amount extraction unit 2 configured to extract a feature amount that corresponds to each of segments into which a first information sequence is divided by a predetermined unit; a second model calculation unit 3 configured to calculate an output probability distribution of second information when the extracted feature amounts are input to a second model; and a model update unit 4 configured to perform at least one of update of the first model based on the output probability distribution of first information calculated by the first model calculation unit and a correct unit number that corresponds to the acoustic feature amounts, and update of the second model based on the output probability distribution of second information calculated by the second model calculation unit and a correct unit number that corresponds to the first information sequence.

Abstract: Provided is a technology of learning an acoustic model with a certain degree of accuracy of sound recognition within a short calculation period.

Abstract: An acoustic model learning apparatus includes a parameter updating part configured to update a parameter of a second acoustic model on the basis of a first loss for a feature amount for training, based on output probability distribution of the second acoustic model which is a neural network acoustic model to be trained, and a second loss for a feature amount for training, based on an intermediate feature amount of a first acoustic model which is a trained neural network acoustic model and an intermediate feature amount of the second acoustic model.

Abstract: A model learning technique is provided to add a word or character at lower cost than the conventional art. A model learning apparatus includes: a storage section 32 in which a neural network model for voice recognition is stored; an addition section 33 that adds a unit corresponding to a word or character to be added, to the output layer of the neural network model read from the storage section 32; a model calculation section 30 that calculates an output probability distribution of an output from the output layer when a feature amount corresponding to the word or character is input to the neural network model where the unit corresponding to the word or character is added to the output layer; and a model update section 31 that updates the parameter of the output layer of the neural network model based on a correct unit number corresponding to the feature amount and the calculated output probability distribution.

Abstract: A model learning apparatus includes: a model calculation unit that calculates output probability distribution, which is an output from an output layer obtained when each feature amount corresponding to each task j?1, . . . , J?1 is inputted into a neural network model, where a main task is a task J and sub-tasks are tasks 1, . . . , J?1; and a multi-task type model update unit that updates a parameter of the neural network model so as to minimize a value of a loss function for the each task j?1, . . . , J?1, the value being calculated based on a correct unit number, which corresponds to each feature amount corresponding to the each task j?1, . . . , J?1, and the output probability distribution, which is calculated and corresponds to the each task j?1, . . .

Abstract: There is provided a neural network learning apparatus capable of adjusting an amount of reduction in a model size. A group parameter generating part grouping model parameters of a neural network model into arbitrarily defined groups and generating group parameters indicating features of the groups, a regularization term calculating part calculating a regularization term on an assumption that distribution of the group parameters is according to distribution defined by hyper parameters which are parameters defining distribution features, and a model updating part calculating a loss function from correct labels in teacher data, output probability distribution obtained by inputting feature values corresponding to the correct labels in the teacher data to the neural network model, and a regularization term, and updating the neural network model in a manner that a value of the loss function is decreased are included.

Abstract: The present invention relates to a production process for a solder electrode, including: a step (1) of forming a coating film of a photosensitive resin composition on a substrate having an electrode pad; a step (2) of forming resist having an opening in a region corresponding to the electrode pad by selectively exposing the coating film to light and further developing the film; and a step (3) of filling the opening with molten solder, in which the photosensitive resin composition contains at least a benzoxazole precursor. According to the production process for the solder electrode of the present invention, development of cracks on a resist surface can be prevented, and solder filling capability can be improved, even when the resist receives high heat during solder filling as in an IMS method, and therefore the solder electrode adapted for the purpose can be appropriately produced.

Abstract: A pattern-forming method includes forming a silicon-containing film on a substrate, the silicon-containing film having a mass ratio of silicon atoms to carbon atoms of 2 to 12. A shape transfer target layer is formed on the silicon-containing film. A fine pattern is transferred to the shape transfer target layer using a stamper that has a fine pattern to form a resist pattern. The silicon-containing film and the substrate are dry-etched using the resist pattern as a mask to form a pattern on the substrate in nanoimprint lithography. According to another aspect of the invention, a silicon-containing film includes silicon atoms and carbon atoms. A mass ratio of silicon atoms to carbon atoms is 2 to 12. The silicon-containing film is used for a pattern-forming method employed in nanoimprint lithography.

Abstract: A method of forming a photoresist pattern includes providing a photoresist film on a substrate. An upper layer film is provided on the photoresist film using an upper layer film-forming composition. Radiation is applied to the upper layer film and the photoresist film through a mask having a given pattern via an immersion medium. The upper layer film and the photoresist film are developed using a developer to form a photoresist pattern. The upper layer film-forming composition includes a resin soluble in the developer and a solvent component. The solvent component includes a first solvent, a second solvent shown by a general formula (2), and a third solvent shown by a general formula (3). The first solvent is diethylene glycol monoethyl ether acetate, ethylene glycol monobutyl ether acetate, diethylene glycol diethyl ether, ?-butyrolactone, methyl propylene diglycol, methyl propylene triglycol or a mixture thereof.

Abstract: An upper layer film-forming composition includes a resin and a solvent component. The resin is soluble in a developer. The solvent component includes first solvent which has a boiling point of 180 to 280° C. at 101.3 kPa and a vapor pressure of 0.001 to 0.1 kPa at 20° C. The upper layer film-forming composition is used to form an upper layer film on a photoresist film.

Abstract: A pattern-forming method includes forming a silicon-containing film on a substrate, the silicon-containing film having a mass ratio of silicon atoms to carbon atoms of 2 to 12. A shape transfer target layer is formed on the silicon-containing film. A fine pattern is transferred to the shape transfer target layer using a stamper that has a fine pattern to form a resist pattern. The silicon-containing film and the substrate are dry-etched using the resist pattern as a mask to form a pattern on the substrate in nanoimprint lithography. According to another aspect of the invention, a silicon-containing film includes silicon atoms and carbon atoms. A mass ratio of silicon atoms to carbon atoms is 2 to 12. The silicon-containing film is used for a pattern-forming method employed in nanoimprint lithography.

Abstract: A resist pattern coating agent includes a hydroxyl group-containing resin, a solvent, and at least two compounds including at least two groups shown by a following formula (1), compounds including a group shown by a following formula (2), and compounds including a group shown by a following formula (4).

Abstract: The object of the invention is to provide a curate liquid composition excelling in storage stability and curability and capable of forming a coat (film) which excels in antistatic properties, hardness, scratch resistance, and transparency on the surface of various substrates, a cured film of the composition, and an anti static laminate. This object is achieved by providing a curate liquid composition comprising the following components (A), (B), (C), and (D): (A) particles comprising an oxide of at least one element selected from the group consisting of indium, antimony, zinc, and tin as a major component, (B) a compound having two or more polymerizable unsaturated groups in the molecule, (C) a silicon-containing surfactant, and (D) a solvent.

Abstract: A photocurable composition comprising the following components (A) to (D): (A) at least one of the (meth)acrylates having the structures shown by the formulas (1) and (2), wherein R1 represents a hydrogen atom or a halogen atom excluding a fluorine atom, R2 is a hydrogen atom, a halogen atom excluding a fluorine atom, Ph-C(CH3)2—, Ph-, or an alkyl group having 1-20 carbon atoms, and R3 represents —CH2—, —S—, or —C(CH3)2—; (B) a (meth)acrylate having three or more functional groups, excluding the (meth)acrylates of the component (A); (C) a radical photoinitiator; and (D) a polycarbonate polyol having a hydroxyl value of 10-100; wherein 5-50 wt % of the total acrylic components in the composition are methacrylate compounds. A photocurable composition produces a cured product possessing a high refractive index, excelling in heat resistance, showing only a small amount of warping, and being particularly useful as an optical part such as a prism lens sheet.

Abstract: The present invention relates to a process for producing an optical multilayer film filter comprising the steps of forming a resin layer on a substrate; forming a multilayer film on the resin layer; and detaching the multilayer film from an interface with the resin layer.