Abstract: A signal processing device according to an embodiment of the present invention includes: a conversion unit configured to convert an input mixed acoustic signal into a plurality of first internal states, a weighting unit configured to generate a second internal state which is a weighted sum of the plurality of first internal states based on auxiliary information regarding an acoustic signal of a target sound source when the auxiliary information is input, and generate the second internal state by selecting one of the plurality of first internal states when the auxiliary information is not input, and a mask estimation unit configured to estimate a mask based on the second internal state.

Abstract: To sufficiently suppress noise and reverberation, a convolutional beamformer for calculating, at each time point, a weighted sum of a current signal and a past signal sequence having a predetermined delay and a length of 0 or more such that it increases a probability expressing a speech-likeness of an estimation signals based on a predetermined probability model is acquired where the estimation signals are acquired by applying the convolutional beamformer to frequency-divided observation signals corresponding respectively to a plurality of frequency bands of observation signals acquired by picking up acoustic signals emitted from a sound source, whereupon target signals are acquired by applying the acquired convolutional beamformer to the frequency-divided observation signals.

Abstract: To begin with, an acoustic model training apparatus extracts speech features representing speech characteristics, and calculates an acoustic-condition feature representing a feature of an acoustic condition of the speech data using an acoustic-condition calculation model that is represented as a neural network, based on an acoustic-condition calculation model parameter characterizing the acoustic-condition calculation model. The acoustic model training apparatus then generates an adjusted parameter that is an acoustic model parameter adjusted based on the acoustic-condition feature, the acoustic model parameter characterizing an acoustic model represented as a neural network to which an output layer of the acoustic-condition calculation model is coupled. The acoustic model training apparatus then updates the acoustic model parameter based on the adjusted parameter and the speech features, and updates the acoustic-condition calculation model parameters based on the adjusted parameter and the speech features.

Abstract: A signal processing device includes a power estimating unit that treats the feature quantity of a signal including reverberation as the input; inputs an observation feature quantity corresponding to an observation signal to a neural network which is learnt in such a way that the estimate value of the feature quantity corresponding to the power of the signal having reduced reverberation, from among the input signal, is output; and estimates the estimate value of the feature quantity corresponding to the power of the signal having reduced reverberation and corresponding to the observation signal. Moreover, the signal processing device includes a regression coefficient estimating unit that uses the estimate value of the feature quantity corresponding to the power as obtained as the estimation result by the power estimating unit, and estimates a regression coefficient of the autoregressive process for generating the observation signal.

Abstract: A laser welding method includes a pretreatment process and a welding process. At least one metal member of the plurality of metal members is formed from a metal-plated steel plate in which a base metal has been covered with a coating material that has a melting point lower than the base metal. In the pretreatment process, with the position of the first metal member in the in-plane direction fixed, processing is performed from the front surface of the first metal member to form on the back surface, a protrusion that bulges from the back surface. Then, in the welding process, the first metal member in which a protrusion has been formed is superposed on a second metal member with the protrusion therebetween while maintaining the position in the in-plane direction, and laser light is irradiated on the superposed region to weld the plurality of metal members to each other.

Abstract: A speech intelligibility calculating method is a method executed by a speech intelligibility calculating apparatus, the speech intelligibility calculating method including: a speech intelligibility calculating step of calculating a speech intelligibility that is an objective assessment index of a speech quality, based on a difference component between features found through an analysis of an input clean speech and an input enhanced speech, using one or more filter banks; and a step of outputting the speech intelligibility calculated at the speech intelligibility calculating step. This speech intelligibility calculating method is capable of calculating a speech intelligibility without any dependency on a speech enhancement method.

Abstract: An estimation device includes a memory, and processing circuitry coupled to the memory and configured to receive an input of an input audio signal that is an audio signal in which sounds from a plurality of sound sources are mixed, and an input of supplemental information, and output an estimation result of mask information that identifies a mask for extracting a sound of any one of the sound sources included in an entire or a part of a signal included in the input audio signal, the signal being identified by the supplemental information, cause a neural network to iterate a process of outputting the estimation result of the mask information, and cause the neural network to output an estimation result of the mask information for a different sound source, by inputting a different piece of the supplemental information to the neural network at each iteration.

Abstract: A mask estimation apparatus includes processing circuitry configured to estimate, for a target segment to be processed among a plurality of segments of a continuous time, a first mask which is an occupancy ratio of a target signal to an observation signal of the target segment, based on a first feature obtained from a plurality of the observation signals of the target segment recorded at a plurality of locations, and estimate a parameter for modeling a second feature and a second mask which is an occupancy ratio of the target signal to the observation signal based on an estimation result of the first mask in the target segment and the second feature obtained from the plurality of the observation signals of the target segment.

Abstract: To begin with, an acoustic model training apparatus extracts speech features representing speech characteristics, and calculates an acoustic-condition feature representing a feature of an acoustic condition of the speech data using an acoustic-condition calculation model that is represented as a neural network, based on an acoustic-condition calculation model parameter characterizing the acoustic-condition calculation model. The acoustic model training apparatus then generates an adjusted parameter that is an acoustic model parameter adjusted based on the acoustic-condition feature, the acoustic model parameter characterizing an acoustic model represented as a neural network to which an output layer of the acoustic-condition calculation model is coupled. The acoustic model training apparatus then updates the acoustic model parameter based on the adjusted parameter and the speech features, and updates the acoustic-condition calculation model parameters based on the adjusted parameter and the speech features.

Abstract: A mask estimation apparatus for estimating mask information for specifying a mask used to extract a signal of a specific sound source from an input audio signal includes a converter which converts the input audio signal into embedded vectors of a predetermined dimension using a trained neural network model and a mask calculator which calculates the mask information by fitting the embedded vectors to a mixed Gaussian model.

Abstract: A cluster weight calculator calculates weights corresponding to respective clusters in a mask calculation NN with at least one of the layers divided into the clusters, based on the signals of speech of a target speaker using a cluster weight calculation NN. A mask calculator calculates a mask for extracting features of speech of the target speaker from features in observed speech signals of one or more speakers based on the features in the observation signals of the speech of the one or more speakers using the mask calculator NN weighted by the weights calculated by the cluster weight calculator.

Abstract: A noise estimation apparatus which estimates a non-stationary noise component on the basis of the likelihood maximization criterion is provided. The noise estimation apparatus obtains the variance of a noise signal that causes a large value to be obtained by weighted addition of the sums each of which is obtained by adding the product of the log likelihood of a model of an observed signal expressed by a Gaussian distribution in a speech segment and a speech posterior probability in each frame, and the product of the log likelihood of a model of an observed signal expressed by a Gaussian distribution in a non-speech segment and a non-speech posterior probability in each frame, by using complex spectra of a plurality of observed signals up to the current frame.

Abstract: A laser welding method includes a pretreatment process and a welding process. At least one metal member of the plurality of metal members is formed from a metal-plated steel plate in which a base metal has been covered with a coating material that has a melting point lower than the base metal. In the pretreatment process, with the position of the first metal member in the in-plane direction fixed, processing is performed from the front surface of the first metal member to form on the back surface, a protrusion that bulges from the back surface. Then, in the welding process, the first metal member in which a protrusion has been formed is superposed on a second metal member with the protrusion therebetween while maintaining the position in the in-plane direction, and laser light is irradiated on the superposed region to weld the plurality of metal members to each other.

Abstract: A power transmitting apparatus is usable for wireless power and data transmission. The power transmitting apparatus includes a power transmitting section configured to transmit power and data to be transmitted as being converted into a pulse train; and a control section configured to control the power transmitting section such that a change of the power caused by superimposition of the data is decreased.

Abstract: A power transmitter 50 is usable in a wireless power transmission system for transmitting power wirelessly. The power transmitter 50 includes a power transmitting section 51 for transmitting power; a communication section 52 for communicating information, for controlling the transmission of the power, with the power receiver 60; and a control section 53 for controlling the power transmitting section 51 such that the power to be sent out by the power transmitting section 51 is higher while the communication section 52 is performing the communication.

Abstract: A noise estimation apparatus which estimates a non-stationary noise component on the basis of the likelihood maximization criterion is provided. The noise estimation apparatus obtains the variance of a noise signal that causes a large value to be obtained by weighted addition of the sums each of which is obtained by adding the product of the log likelihood of a model of an observed signal expressed by a Gaussian distribution in a speech segment and a speech posterior probability in each frame, and the product of the log likelihood of a model of an observed signal expressed by a Gaussian distribution in a non-speech segment and a non-speech posterior probability in each frame, by using complex spectra of a plurality of observed signals up to the current frame.

Abstract: The transmitter of a wireless power transmission audio system includes: a transmission signal generating section for generating a transmission signal comprised of an RF signal; a first resonant circuit which receives and sends out the transmission signal; a detecting section for sensing a variation in the transmission signal; and a transmission signal adjusting section. The loudspeaker of the system includes: a second resonant circuit for receiving the transmission signal by producing a magnetic field resonant coupling phenomenon; and an audio output section for reproducing the audio signal. At least one of the transmitter and the loudspeaker includes an impedance adjusting section which changes an impedance value on the transmission line of the transmission signal. When the impedance adjusting section changes the impedance value, the transmission signal adjusting section changes the signal waveform of the transmission signal.

Abstract: A wireless receiver including a dipole antenna and a circuit board, wherein high directivity characteristics can be acquired for wireless signals is provided. The wireless receiver includes a balanced feed antenna and a circuit board arranged in parallel to the longitudinal direction of the aforementioned balanced feed antenna. A conductive pattern formed on the aforementioned circuit board is composed of two or more partial patterns arranged with a gap interposed therebetween. The gap is formed at a position in between both ends of the aforementioned balanced feed antenna.

Abstract: A wireless power transmission system transmits power wirelessly from a power transmitter to a power receiver. The power transmitter includes a class E amplifier, a transmitting-end resonant circuit, a detector that detects a voltage or current waveform at a predetermined position in the class E amplifier in accordance with the impedance of the transmitting-end resonant circuit as viewed from the class E amplifier, and a signal extractor that extracts a signal according to the waveform. The power receiver includes a receiving-end resonant circuit, a rectifier circuit, a power reproducing section, and an impedance changer connected between the rectifier circuit and the power reproducing section to change its impedance. When the impedance is changed, the detector detects the waveform variation and the signal extractor extracts and outputs a signal corresponding to the waveform detected by the detector.

Abstract: The receiver diversity-receives radio wave with a plurality of antennas. The receiver includes a conductive case having a receiving section for executing diversity-receiving processing, a first through hole and a second through hole that are disposed on the surface of the same side of the case and penetrate the case from the outside to the inside, a first antenna and a second antenna for supplying a received signal to the receiving section, and a first hinge and a second hinge that are fixed to the inside of the case, pass the first through hole and the second through hole, directly or indirectly support the first antenna and the second antenna, and are movable, respectively. A partition is disposed between the first through hole and the second through hole.