Abstract: The accuracy of unsupervised anomalous sound detection is improved. An anomalous sound generation unit 12 generates a pseudo-anomalous sound by associating a sound obtained from a predetermined device with a probability distribution followed by a sound obtained from a desired device group. A threshold value setting unit 13 sets a threshold value so that all anomaly scores calculated from the pseudo-anomalous sound are determined to be anomalous. A parameter update unit 14 uses an obtained normal sound and an obtained anomalous sound, or a threshold value and a value based on the obtained anomalous sound, to update a parameter so to reliably determine an anomalous sound as anomalous and minimize the probability of determining a normal sound as anomalous.

Abstract: An object of the present invention is to provide an optical pulse test apparatus and an optical pulse test method that are capable of determining a change in state of an optical fiber connection portion without the need for reference and without being affected by changes in gap interval before and after the change in state. The optical pulse test apparatus according to the present invention is configured to perform an OTDR measurement by using test optical pulses having spectral widths of from several nm to several hundred nm arranged at intervals of several ten nm to several hundred nm, calculate a reflection peak value caused by the Fresnel reflection at the connection portion from the obtained OTDR waveform, and determine a state such as water immersion of the optical fiber connection portion based on the value.

Abstract: To be able to convert to a voice of the desired attribution. A learning unit learns a converter to minimize a value of a learning criterion of the converter, learns a voice identifier to minimize a value of a learning criterion of the voice identifier, and learns an attribution identifier to minimize a value of a learning criterion of the attribution identifier.

Abstract: Paralinguistic information is estimated with high accuracy even when an utterance for which it is difficult to identify paralinguistic information is used for model learning. An acoustic feature extraction unit 11 extracts an acoustic feature from an utterance. An anti-teacher decision unit 12 decides, based on a paralinguistic information label indicating a determination result of paralinguistic information given by a plurality of listeners for each utterance, an anti-teacher label indicating an anti-teacher serving as incorrect paralinguistic information for the utterance. An anti-teacher estimation model learning unit 13 learns, based on an acoustic feature extracted from the utterance and the anti-teacher label, an anti-teacher estimation model for outputting a posterior probability of anti-teacher for an input acoustic feature.

Abstract: A technique is provided that can reduce degradation of the sound quality due to a tandem connection of paired coding and decoding, and can reduce the operation processing amount and the required memory amount of a multipoint control unit. In multipoint connection between terminals of a plurality of communication networks (for example, a fixed phone line and a mobile phone line) having different communication capacities, when a multichannel coding including a monaural coding scheme of a communication network having a smaller communication capacity is used in a communication network having a larger communication capacity to transmit sounds of a plurality points to the communication network terminal having the larger communication capacity, control is exercised such that monaural codes of the plurality points are output.

Abstract: An anomaly detection apparatus (10) includes a storage unit (14) that stores dictionary information (14b) in which a partial character string of a message representing a type of a message included in a text log output from a system and an ID set for the type of the message are associated with each other. The anomaly detection apparatus (10), when the message included in the text log output from the system is acquired, refers to the dictionary information (14b) stored in the storage unit (14), classifies the message included in the text log by the type, and assigns the ID to the message that has been classified; and detects an anomaly based on the ID assigned to the message.

Abstract: An optical module that has a structure ensuring reduction in size. The optical module has a structure where a part of a fiber block is protruded from a housing. By including a thin plate, this optical module can avoid entering of dust in the housing, allows a position shift of the fiber block due to a mounting position error of an optical component in the housing, a position shift of an opening portion due to a dimensional error of the housing, or a displacement due to a temperature change, and can reduce the coupling loss due to the optical axis misalignment.

Abstract: An inference method includes acquiring similarities between a domain name serving as an analysis object and each domain name indicated in a legitimate domain name list as feature amounts, and inferring a degree that the domain name serving as the analysis object is wrongly recognized as a legitimate domain name based on the feature amounts acquired at the acquiring and a training model that outputs, as a response to input of the feature amounts, a degree that the domain name serving as the analysis object is wrongly recognized as the legitimate domain name, by processing circuitry.

Abstract: A training data generation apparatus (10) according to the present invention includes a noise determination unit (11) that determines whether or not training data that is to be used in machine learning includes noise, and a noise addition unit (12) that generates new training data by adding noise to training data that has been determined by the noise determination unit (11) as not including noise.

Abstract: An information processing apparatus according to an embodiment includes: a common data model management unit that manages information indicating a common data model corresponding to a plurality of modules in common; a unique data model management unit that manages information indicating a unique data model corresponding to at least one of the modules; and a common management unit that manages a version of a module corresponding to the common data model managed by the common data model management unit, a version of a module corresponding to the unique data model managed by the unique data model management unit, and a version of a module corresponding to a newly installed data model, and verifies compatibility of the versions.

Abstract: An object of the present invention is to provide a personal information protection apparatus, a personal information protection method, and a program that make it possible to easily control a range of personal information to be provided to an application. The personal information protection apparatus according to the present invention performs machine learning on terms of use, classifications, and access settings of applications installed in a terminal, and holds them as a user policy, and when an attempt is made to change the access settings of a certain application, presents, to the user, recommended settings based on the user policy. When the user changes access settings of an application based on a policy that is different from the prior and existing policy, this personal information protection apparatus performs learning on the user policy again using the changed access settings.

Abstract: To provide a connector plug that makes it possible to facilitate a plurality of persons' confirmation of a connector plug before its removal or after its insertion and to prevent erroneous work. The connector plug according to the present invention has a discoloration member mounted on a gripping portion for pinching during work. The color of the discoloration member changes due to heat of a worker's fingertips when the worker pinches the connector plug or pressure when the worker pinches the connector plug. The discoloration member is discolored by one worker pinching the connector plug. Another worker looks at the discolored discoloration member, and then is able to confirm whether the connector plug is a work target.

Abstract: A technique is provided that can reduce degradation of the sound quality due to a tandem connection of paired coding and decoding, and can reduce the operation processing amount and the required memory amount of a multipoint control unit. In multipoint connection between terminals of a plurality of communication networks (for example, a fixed phone line and a mobile phone line) having different communication capacities, when a multichannel coding including a monaural coding scheme of a communication network having a smaller communication capacity is used in a communication network having a larger communication capacity to transmit sounds of a plurality points to the communication network terminal having the larger communication capacity, control is exercised such that monaural codes of the plurality points are output.

Abstract: A credit segment identifying device includes an extracting unit which extracts, from a first speech signal, a plurality of first partial speech signals which are each a part of the first speech signals and shifted from each other in time direction and an identifying unit which identifies a credit segment in the first speech signal by determining whether each of the first partial speech signals includes a credit according to an association between each of second partial signals extracted from a second speech signal and the presence/absence of a credit, so that credit segments can be identified more efficiently.

Abstract: A testing device (10) transmits a test packet that increases processing load to a device protected by a security system, the security system performing authentication of a packet transmitted to a to-be-protected device and a packet limit per source IP address. In addition, the testing device (10) generates a test session according to a scenario when transmitting the test packet and configures a packet so that the test packet uses a plurality of source IP addresses. In addition, the testing device (10) responds to a response request up to a predetermined stage of authentication among a plurality of stages of authentication performed by the security system so that the security system authenticates the test packet to be valid. In addition, the testing device (10) monitors, at a predetermined stage, packet filtering situation and processing load of the security system to which the test packet is transmitted.

Abstract: A wavelength-selective optical reception device includes a photoreceptor (21) that converts optical signals (201) into electric signals and outputs the electric signals, a base (31) on which the photoreceptor (21) is provided, a housing (41) that is mounted on the base (31) and surrounds the photoreceptor (21) along with the base (31), and that is provided with a window (51) to pass optical signals (203) including the optical signals (201) and including optical signals (202) of a wavelength different from a first wavelength of the optical signals (201) and a window (52) to pass the optical signals (202), and an optical filter (61) that is disposed inside the housing between the window (51) and the photoreceptor (21) along the optical axis (205) of the optical signals (203), and that outputs, out of the optical signals (203) that enter thereto, the optical signals (201) toward the photoreceptor (21), and reflects the optical signals (202) toward a near side in a direction of travel of the optical signals (203)

Abstract: Access to an array is efficiently performed without reveling an accessed position. A storage 10 stores an array of concealed values [x??] of an array x?? and an array of addresses a?? corresponding to respective elements of the array of concealed values [x??]. A refresh unit 11 determines a concealed value [F] of a random parameter F, an array of concealed values [x?] of an array x? generated by permutating the array x?? with random permutation ?, and an array of public tags b? calculated from respective elements of the array of addresses a? with the function TagF. An access unit 12 performs a desired access to an element of the array of concealed values [x?] corresponding to a tag that is calculated from a concealed value [j] of an access position j with the function Tag and the concealed value [F] of the parameter.

Abstract: Event occurrence is estimated from time series information which is high-dimensional information such as an image. A hazard estimation unit 11 estimates a likelihood of occurrence of an event according to a hazard function for each of a plurality of time-series image groups including time-series image groups in which no events have occurred and time-series image groups in which events have occurred, each of the plurality of time-series image groups being given an occurrence time of an event in advance, and a parameter estimation unit 12 estimates a parameter of the hazard function such that a likelihood function that is represented by including the occurrence time of an event given for each of the plurality of time-series image groups and the likelihood of occurrence of an event estimated for each of the plurality of time-series image groups is optimized.

Abstract: An object of the present invention is to provide a Raman gain efficiency distribution testing method and a Raman gain efficiency distribution testing apparatus for measuring a Raman gain efficiency distribution of a fundamental mode and a first high-order mode in a few-mode fiber.

Abstract: Provided is a path control method of controlling a path of communication in a network including a high priority device dealing with high priority traffic, a high priority control device communicating with the high priority device through a plurality of signal transfer devices transferring signals by periodically repeating a high priority signal transmissible period in which high priority traffic is transmissible and a low priority signal transmissible period in which low priority traffic is transmissible, a low priority device dealing with the low priority traffic, and a low priority control device communicating with the low priority device through the plurality of signal transfer devices, the path control method including calculating a low priority signal transmissible period in each of paths between the low priority device and the low priority control device, and performing setting for switching the path between the low priority device and the low priority control device so that the low priority traffic is