|
|
| (24 intermediate revisions by the same user not shown) |
| Line 1: |
Line 1: |
| − | ==Patent applications for NIPPON TELEGRAPH AND TELEPHONE CORPORATION on November 30th, 2023==
| + | '''Summary of the patent applications from NIPPON TELEGRAPH AND TELEPHONE CORPORATION on November 30th, 2023''' |
| − | | |
| − | ===KINETIC CONTROL SUPPORT APPARATUS, KINETIC CONTROL SUPPORT METHOD, AND PROGRAM ([[US Patent Application 18250081. KINETIC CONTROL SUPPORT APPARATUS, KINETIC CONTROL SUPPORT METHOD, AND PROGRAM simplified abstract|18250081]])===
| |
| | | | |
| | + | NIPPON TELEGRAPH AND TELEPHONE CORPORATION has recently filed several patents related to various technological innovations. These patents cover a range of fields, including wireless communication, user-generated content analysis, battery technology, optical elements, audio signal processing, and voice signal conversion. |
| | | | |
| − | '''Main Inventor'''
| + | In the field of wireless communication, NTT has developed a learning method that uses machine learning to estimate wireless quality. This method involves training a model with measurement data from multiple terminals and continuously updating the model with new data to improve accuracy. This innovation can enhance the performance and reliability of wireless communication systems. |
| | | | |
| − | Arinobu NIIJIMA
| + | Another patent focuses on a device that can determine if user-generated content is generated by a malicious user or a legitimate user. By calculating characteristic amounts of user-generated content and using a learning process, the device creates a model to distinguish between legitimate and malicious content. |
| | | | |
| | + | NTT has also developed a relay device with features such as an internal clock, memory, and communication unit for transmitting and receiving signals between a master and a slave. The device uses synchronization signals and a retention time processing unit to ensure accurate signal transmission. |
| | | | |
| − | '''Brief explanation'''
| + | In the field of battery technology, NTT has filed patents for a metal-air battery with a specific electrolytic solution and a primary battery with unique components. These innovations aim to improve battery performance and enhance energy storage capabilities. |
| − | The patent application describes a force control support device that uses sound waves and electrical stimulation to assist users in applying force.
| |
| − | * The device includes a sound wave transmitting unit that causes a sound output device to transmit a specific sound wave.
| |
| − | * A sound wave receiving unit receives a second sound wave based on the transmitted sound wave.
| |
| − | * An estimation unit uses the transmitted and received sound waves to estimate the amount of force being applied by the user.
| |
| − | * An electrical stimulation presentation unit then presents electrical stimulation to the user based on the estimated force.
| |
| − | * The electrical stimulation is delivered through an electrode mounted on the user.
| |
| | | | |
| − | '''Abstract'''
| + | NTT has also developed an optical element with a transparent layer that guides light to two photoelectric conversion elements. This element is designed to improve image quality and capture more accurate data. |
| − | A force control support device includes: a sound wave transmitting unit that causes a sound output device mounted on a user to transmit a first sound wave having a predetermined waveform; a sound wave receiving unit that causes a sound input device mounted on the user to receive a second sound wave based on the first sound wave; an estimation unit that estimates an amount of force being applied by the user based on the first sound wave and the second sound wave; and an electrical stimulation presentation unit that presents an electrical stimulation according to the amount of force estimated by the estimation unit from an electrode mounted on the user.
| |
| | | | |
| − | ===HEAT TRACE AREA EXTRACTION APPARATUS, HEAT TRACE AREA EXTRACTION METHOD AND PROGRAM ([[US Patent Application 18031141. HEAT TRACE AREA EXTRACTION APPARATUS, HEAT TRACE AREA EXTRACTION METHOD AND PROGRAM simplified abstract|18031141]])===
| + | In the audio signal processing field, NTT has developed techniques for pitch enhancement and high-frequency compensation in decoded sound signals. These innovations aim to improve the quality and naturalness of audio signals. |
| | | | |
| | + | Lastly, NTT has filed a patent for a device that learns how to convert voice signals using machine learning models and adjustment parameters. This technology enables the conversion of input voice signals into desired voice signals. |
| | | | |
| − | '''Main Inventor'''
| + | Notable applications: |
| | + | * Learning method for estimating wireless quality using machine learning. |
| | + | * Device for determining if user-generated content is generated by a malicious user or a legitimate user. |
| | + | * Relay device with features for accurate signal transmission. |
| | + | * Metal-air battery with a specific electrolytic solution. |
| | + | * Primary battery with unique components. |
| | + | * Optical element with a transparent layer for improved image quality. |
| | + | * Techniques for pitch enhancement and high-frequency compensation in audio signals. |
| | + | * Device for converting voice signals using machine learning models. |
| | | | |
| − | Yoshinari SHIRAI
| |
| | | | |
| | | | |
| − | '''Brief explanation'''
| |
| − | - The patent application describes a device for extracting heat trace regions.
| |
| − | - The device includes a difference actual object image generation unit that generates an image showing the difference between an actual object image and a background actual object image.
| |
| − | - It also includes a difference thermal image generation unit that generates an image showing the difference between a thermal image of the actual object and a thermal image of the background.
| |
| − | - The device further includes a heat trace region extraction unit that extracts the heat trace region by removing the region of the actual object from the thermal image using the difference actual object image and the difference thermal image.
| |
| − | - The purpose of the device is to identify and extract heat trace regions from a thermal image by comparing it with background images and removing the influence of the actual object.
| |
| | | | |
| − | '''Abstract'''
| + | ==Patent applications for NIPPON TELEGRAPH AND TELEPHONE CORPORATION on November 30th, 2023== |
| − | A heat trace region extraction device includes: a difference actual object image generation unit that generates a difference actual object image which is an image of a difference between an actual object image which is an image of an actual object obtained by photographing a certain range with an actual object camera for photographing the actual object and a background actual object image which is an actual object image of a background of the certain range; a difference thermal image generation unit that generates a difference thermal image which is an image of a difference between a thermal image which is an image of heat emitted by the actual object obtained by photographing the certain range with a thermal camera for photographing the heat emitted by the actual object and a background thermal image which is a thermal image of the background; and a heat trace region extraction unit that extracts a heat trace region by removing a region of the actual object from the thermal image based on the difference actual object image and the difference thermal image.
| |
| | | | |
| − | ===SATELLITE SIGNAL RECEPTION APPARATUS, SATELLITE SIGNAL PROCESSING METHOD AND PROGRAM ([[US Patent Application 18251088. SATELLITE SIGNAL RECEPTION APPARATUS, SATELLITE SIGNAL PROCESSING METHOD AND PROGRAM simplified abstract|18251088]])=== | + | ===KINETIC CONTROL SUPPORT APPARATUS, KINETIC CONTROL SUPPORT METHOD, AND PROGRAM ([[US Patent Application 18250081. KINETIC CONTROL SUPPORT APPARATUS, KINETIC CONTROL SUPPORT METHOD, AND PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18250081]])=== |
| | | | |
| | | | |
| | '''Main Inventor''' | | '''Main Inventor''' |
| | | | |
| − | Seiji YOSHIDA
| + | Arinobu NIIJIMA |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===HEAT TRACE AREA EXTRACTION APPARATUS, HEAT TRACE AREA EXTRACTION METHOD AND PROGRAM ([[US Patent Application 18031141. HEAT TRACE AREA EXTRACTION APPARATUS, HEAT TRACE AREA EXTRACTION METHOD AND PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18031141]])=== |
| − | The patent application describes a device for receiving satellite signals.
| |
| − | * The device has a signal selection unit that chooses a specific number of satellite signals based on their reception quality.
| |
| − | * The device also has a measurement unit that uses the selected satellite signals for positioning or time synchronization purposes.
| |
| | | | |
| − | '''Abstract'''
| |
| − | A satellite signal reception device includes: a signal selection unit configured to select a predetermined number of satellite signals on a basis of reception quality of satellite signals received by a GNSS antenna; and a measurement unit configured to perform positioning or time synchronization using the predetermined number of satellite signals selected by the signal selection unit.
| |
| | | | |
| − | ===OPTICAL CONNECTING STRUCTURE, OPTICAL MODULE AND MANUFACTURING METHOD FOR OPTICAL CONNECTING STRUCTURE ([[US Patent Application 18031859. OPTICAL CONNECTING STRUCTURE, OPTICAL MODULE AND MANUFACTURING METHOD FOR OPTICAL CONNECTING STRUCTURE simplified abstract|18031859]])===
| + | '''Main Inventor''' |
| | | | |
| | + | Yoshinari SHIRAI |
| | | | |
| − | '''Main Inventor'''
| |
| | | | |
| − | Yohei Saito
| + | ===SATELLITE SIGNAL RECEPTION APPARATUS, SATELLITE SIGNAL PROCESSING METHOD AND PROGRAM ([[US Patent Application 18251088. SATELLITE SIGNAL RECEPTION APPARATUS, SATELLITE SIGNAL PROCESSING METHOD AND PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18251088]])=== |
| | | | |
| | | | |
| − | '''Brief explanation''' | + | '''Main Inventor''' |
| − | The patent application describes an optical connection structure that includes an optical waveguide device, an optical fiber, and a self-forming waveguide.
| |
| | | | |
| − | * The optical waveguide device consists of a substrate, a BOX layer, a first waveguide, and an overcladding.
| + | Seiji YOSHIDA |
| − | * The optical fiber is placed in a V-groove on the substrate.
| |
| − | * A self-forming waveguide is located between the end face of the optical waveguide device and the end face of the optical fiber.
| |
| − | * The self-forming waveguide is surrounded by a cladding.
| |
| − | * The positioning of the optical fiber allows the signal light emitted from the fiber to enter the waveguide.
| |
| − | * The self-forming waveguide is created by curing a portion of it with resin curing light.
| |
| | | | |
| − | '''Abstract'''
| |
| − | An optical connection structure includes an optical waveguide device that includes a substrate, a BOX layer, a first waveguide, and an overcladding in this order, an optical fiber disposed in a V-groove formed in the substrate, a self-forming waveguide disposed between an end face of the optical waveguide device and an end face of the optical fiber, and a cladding disposed around the self-forming waveguide. The optical fiber is positioned so that the end face of the optical fiber faces the end face of the optical waveguide device to cause signal light emitted from the optical fiber to enter the waveguide. The self-forming waveguide is formed with a portion cured by irradiation with resin curing light.
| |
| | | | |
| − | ===OFFLOAD SERVER, OFFLOAD CONTROL METHOD, AND OFFLOAD PROGRAM ([[US Patent Application 18248637. OFFLOAD SERVER, OFFLOAD CONTROL METHOD, AND OFFLOAD PROGRAM simplified abstract|18248637]])=== | + | ===OPTICAL CONNECTING STRUCTURE, OPTICAL MODULE AND MANUFACTURING METHOD FOR OPTICAL CONNECTING STRUCTURE ([[US Patent Application 18031859. OPTICAL CONNECTING STRUCTURE, OPTICAL MODULE AND MANUFACTURING METHOD FOR OPTICAL CONNECTING STRUCTURE simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18031859]])=== |
| | | | |
| | | | |
| | '''Main Inventor''' | | '''Main Inventor''' |
| | | | |
| − | Yoji YAMATO
| + | Yohei Saito |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===OFFLOAD SERVER, OFFLOAD CONTROL METHOD, AND OFFLOAD PROGRAM ([[US Patent Application 18248637. OFFLOAD SERVER, OFFLOAD CONTROL METHOD, AND OFFLOAD PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18248637]])=== |
| − | - The patent application describes an offload server that includes different sections for analyzing, generating patterns, and measuring performance.
| |
| − | - The code analysis section analyzes whether certain function blocks can be executed by an accelerator.
| |
| − | - The processing pattern generation section generates patterns for offloading the function blocks based on the analysis.
| |
| − | - The performance measurement section deploys each pattern to a verification machine to measure performance.
| |
| − | - If the measured performance satisfies a desired level, the processing pattern generation section generates patterns for offloading remaining loop statements except the function blocks.
| |
| − | - If the measured performance fails to satisfy the desired level, the processing pattern generation section generates patterns for offloading loop statements.
| |
| − | - The performance measurement section deploys each pattern to a verification environment to measure performance in both cases.
| |
| | | | |
| − | '''Abstract'''
| |
| − | An offload server includes a code analysis section for analyzing whether function blocks executable by an accelerator is included, a processing pattern generation section for generating patterns for offloading the function blocks, and a performance measurement section for deploying each pattern for offloading the function blocks to a verification machine to measure performance. When the performance measured by the performance measurement section satisfies a desired level, the processing pattern generation section generates patterns for offloading remaining loop statements except the function blocks, and the performance measurement section deploys each pattern to a verification environment to measure performance. When the performance measured by the performance measurement section fails to satisfy the desired level, the processing pattern generation section generates patterns for offloading loop statements, and the performance measurement section deploys each pattern to the verification environment to measure performance.
| |
| | | | |
| − | ===COLLECTION DEVICE, COLLECTION METHOD, AND COLLECTION PROGRAM ([[US Patent Application 18031618. COLLECTION DEVICE, COLLECTION METHOD, AND COLLECTION PROGRAM simplified abstract|18031618]])===
| + | '''Main Inventor''' |
| | | | |
| | + | Yoji YAMATO |
| | | | |
| − | '''Main Inventor'''
| |
| | | | |
| − | Hiroki NAKANO
| + | ===COLLECTION DEVICE, COLLECTION METHOD, AND COLLECTION PROGRAM ([[US Patent Application 18031618. COLLECTION DEVICE, COLLECTION METHOD, AND COLLECTION PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18031618]])=== |
| | | | |
| | | | |
| − | '''Brief explanation''' | + | '''Main Inventor''' |
| − | The abstract describes a collection device with processing circuitry that can acquire user-generated content from different services, generate search queries based on the content, and collect user-generated content from multiple services using these queries.
| |
| | | | |
| − | * The collection device has processing circuitry that can gather user-generated content from various services.
| + | Hiroki NAKANO |
| − | * It generates search queries by using words found in the user-generated content from each service.
| |
| − | * The device then collects user-generated content from multiple services by using these generated search queries.
| |
| − | * The purpose of this device is to efficiently gather user-generated content from different services in a predetermined period.
| |
| − | * This technology can be useful for analyzing and aggregating user-generated content from various platforms or services.
| |
| | | | |
| − | '''Abstract'''
| |
| − | A collection device includes processing circuitry configured to acquire user-generated content generated in each service in a predetermined period, generate a search query by using words that appear in the user-generated content for each service, and collect user-generated content generated in a plurality of services by using the generated search query.
| |
| | | | |
| − | ===NEURAL ARCHITECTURE SEARCH SYSTEM AND SEARCH METHOD ([[US Patent Application 18249723. NEURAL ARCHITECTURE SEARCH SYSTEM AND SEARCH METHOD simplified abstract|18249723]])=== | + | ===NEURAL ARCHITECTURE SEARCH SYSTEM AND SEARCH METHOD ([[US Patent Application 18249723. NEURAL ARCHITECTURE SEARCH SYSTEM AND SEARCH METHOD simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18249723]])=== |
| | | | |
| | | | |
| Line 123: |
Line 88: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===POINT PROCESS LEARNING METHOD, POINT PROCESS LEARNING APPARATUS AND PROGRAM ([[US Patent Application 18249772. POINT PROCESS LEARNING METHOD, POINT PROCESS LEARNING APPARATUS AND PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18249772]])=== |
| − | The patent application describes a neural architecture search system that improves the accuracy of neural networks while considering deployment constraints. Here are the key points:
| |
| − | | |
| − | * The system converts a constraint condition of a neural network implementation into a constraint condition for the network's architecture parameters.
| |
| − | * A learning engine unit trains the neural network and calculates its inference accuracy under a search condition.
| |
| − | * A model modification unit adjusts the architecture of the neural network based on the inference accuracy and the constraint condition.
| |
| − | * The goal is to find the best architecture that maximizes inference accuracy while meeting the given constraints.
| |
| − | | |
| − | '''Abstract'''
| |
| − | A neural architecture search system includes a deployment constraint management unit that converts a first constraint condition that defines a constraint of a system that implements a neural network into a second constraint condition that defines a constraint of a parameter that prescribes an architecture of the neural network, a learning engine unit that performs learning of the neural network under a search condition and calculates inference accuracy in a case where the learned neural network is used, and a model modification unit that causes the learning engine unit to perform the learning and the calculation of the inference accuracy while changing the architecture of the neural network on the basis of the inference accuracy and the second constraint condition so as to obtain the best inference accuracy.
| |
| − | | |
| − | ===POINT PROCESS LEARNING METHOD, POINT PROCESS LEARNING APPARATUS AND PROGRAM ([[US Patent Application 18249772. POINT PROCESS LEARNING METHOD, POINT PROCESS LEARNING APPARATUS AND PROGRAM simplified abstract|18249772]])=== | |
| | | | |
| | | | |
| Line 142: |
Line 96: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===INFERENCE DEVICE, INFERENCE METHOD, AND INFERENCE PROGRAM ([[US Patent Application 18034257. INFERENCE DEVICE, INFERENCE METHOD, AND INFERENCE PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18034257]])=== |
| − | The patent application describes a computer-based method for learning patterns in a series of events, called a point process.
| |
| − | | |
| − | * The method involves inputting a dataset of event occurrences, specifically a series of first events.
| |
| − | * The dataset is then divided based on a prediction time observation area, which includes the time series used for predicting future event occurrences.
| |
| − | * Finally, a model parameter, specifically the intensity function parameter of a predetermined point process model, is learned using the divided dataset.
| |
| − | | |
| − | '''Abstract'''
| |
| − | According to an embodiment, a point process learning method executed by a computer includes: an input procedure of inputting a learning data set including at least first event data representing a series of occurrences of first events; a division procedure of dividing the first event data included in the learning data set by using a prediction time observation area including at least a time series when predicting future event occurrence; and a learning procedure of learning a model parameter including a parameter of an intensity function of a predetermined point process model by using a divided learning data set divided in the division procedure.
| |
| − | | |
| − | ===INFERENCE DEVICE, INFERENCE METHOD, AND INFERENCE PROGRAM ([[US Patent Application 18034257. INFERENCE DEVICE, INFERENCE METHOD, AND INFERENCE PROGRAM simplified abstract|18034257]])=== | |
| | | | |
| | | | |
| Line 160: |
Line 104: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM ([[US Patent Application 18031588. SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18031588]])=== |
| − | - The patent application describes a system that compares target data with a learning data group to make inferences.
| |
| − | - If the comparison result does not meet a specific criterion, the system determines that the inference result is uncertain.
| |
| − | - When the inference result is uncertain, a notification is sent to the user along with the inference result.
| |
| − | - The purpose of this system is to provide users with information about uncertain inference results.
| |
| − | | |
| − | '''Abstract'''
| |
| − | A comparison unit compares target data to be inferred with a learning data group that is data used for learning of the inference model, and determines that an inference result is uncertain when a comparison result does not satisfy a fixed criterion. A notification unit notifies a user that the inference result is uncertain in addition to the inference result when the inference result is determined to be uncertain.
| |
| − | | |
| − | ===SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM ([[US Patent Application 18031588. SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM simplified abstract|18031588]])=== | |
| | | | |
| | | | |
| Line 177: |
Line 112: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM ([[US Patent Application 18031595. SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18031595]])=== |
| − | - The technology improves the quality of a decoded sound signal obtained from a different code derived from the same sound signal.
| |
| − | - A decoded sound common signal is obtained by downmixing the decoded sound signal of each channel.
| |
| − | - The decoded sound common signal is upmixed to generate an upmixed common signal.
| |
| − | - The upmixed common signal is subjected to signal purification using an upmixed monaural decoded sound signal.
| |
| − | - The purified upmixed signal is generated through signal purification.
| |
| − | - The upmixed common signal is subtracted from the decoded sound signal in each channel.
| |
| − | - The purified upmixed signal is added to the subtracted signal.
| |
| − | - This process generates a purified decoded sound signal.
| |
| − | | |
| − | '''Abstract'''
| |
| − | There is provided a technology that improves, in a case where there is a sound signal obtained from a different code that is different from a code from which a decoded sound signal is obtained and that is derived from the same sound signal, the decoded sound signal by using the sound signal obtained from the different code. A signal (hereinafter, referred to as an upmixed common signal) obtained by upmixing a decoded sound common signal obtained by downmixing a decoded sound signal of each channel is subjected to signal purification using a signal (hereinafter, referred to as an upmixed monaural decoded sound signal) obtained by upmixing a monaural decoded sound signal to thereby generate a purified upmixed signal, and in each channel, the upmixed common signal is subtracted from the decoded sound signal and the purified upmixed signal is added thereto, to thereby generate a purified decoded sound signal.
| |
| − | | |
| − | ===SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM ([[US Patent Application 18031595. SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM simplified abstract|18031595]])=== | |
| | | | |
| | | | |
| Line 198: |
Line 120: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM ([[US Patent Application 18032533. SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18032533]])=== |
| − | - The patent application describes a technology that improves the quality of a decoded sound signal obtained from a different code than the original code of the sound signal.
| |
| − | - The technology involves upmixing a decoded sound common signal obtained by downmixing the decoded sound signal of each channel.
| |
| − | - The upmixed common signal is then subjected to signal purification using an upmixed monaural decoded sound signal, resulting in a purified upmixed signal.
| |
| − | - In each channel, the upmixed common signal is subtracted from the decoded sound signal, and the purified upmixed signal is added to generate a purified decoded sound signal.
| |
| − | | |
| − | '''Abstract'''
| |
| − | There is provided a technology that improves, in a case where there is a sound signal obtained from a different code that is different from a code from which a decoded sound signal is obtained and that is derived from the same sound signal, the decoded sound signal by using the sound signal obtained from the different code. A signal (hereinafter, referred to as an upmixed common signal) obtained by upmixing a decoded sound common signal obtained by downmixing a decoded sound signal of each channel is subjected to signal purification using a signal (hereinafter, referred to as an upmixed monaural decoded sound signal) obtained by upmixing a monaural decoded sound signal to thereby generate a purified upmixed signal, and in each channel, the upmixed common signal is subtracted from the decoded sound signal and the purified upmixed signal is added thereto, to thereby generate a purified decoded sound signal.
| |
| − | | |
| − | ===SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM ([[US Patent Application 18032533. SOUND SIGNAL REFINEMENT METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM simplified abstract|18032533]])=== | |
| | | | |
| | | | |
| Line 215: |
Line 128: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===AUDIO SIGNAL CONVERSION MODEL LEARNING APPARATUS, AUDIO SIGNAL CONVERSION APPARATUS, AUDIO SIGNAL CONVERSION MODEL LEARNING METHOD AND PROGRAM ([[US Patent Application 18032529. AUDIO SIGNAL CONVERSION MODEL LEARNING APPARATUS, AUDIO SIGNAL CONVERSION APPARATUS, AUDIO SIGNAL CONVERSION MODEL LEARNING METHOD AND PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18032529]])=== |
| − | - The technology described in the patent application improves the quality of a decoded sound signal obtained from a different code than the original code of the sound signal.
| |
| − | - The decoded sound signal is derived from the same sound signal, but the different code introduces some distortion or noise.
| |
| − | - A decoded sound common signal is created by combining the decoded sound signals from each channel and then subjected to signal purification using a monaural decoded sound signal.
| |
| − | - The signal purification process generates a purified common signal, which is then subtracted from the decoded sound signal in each channel.
| |
| − | - The purified common signal is then added to the subtracted decoded sound signal, resulting in a purified decoded sound signal.
| |
| − | - This technology aims to enhance the quality of decoded sound signals by reducing the impact of distortion or noise introduced by a different code.
| |
| − | | |
| − | '''Abstract'''
| |
| − | There is provided a technology that improves, in a case where there is a sound signal obtained from a different code that is different from a code from which a decoded sound signal is obtained and that is derived from the same sound signal, the decoded sound signal by using the sound signal obtained from the different code. A signal (hereinafter, referred to as a decoded sound common signal) obtained by downmixing a decoded sound signal of each channel is subjected to signal purification using a monaural decoded sound signal to thereby generate a purified common signal, and in each channel, the decoded sound common signal is subtracted from the decoded sound signal and the purified common signal is added thereto, to thereby generate a purified decoded sound signal.
| |
| − | | |
| − | ===AUDIO SIGNAL CONVERSION MODEL LEARNING APPARATUS, AUDIO SIGNAL CONVERSION APPARATUS, AUDIO SIGNAL CONVERSION MODEL LEARNING METHOD AND PROGRAM ([[US Patent Application 18032529. AUDIO SIGNAL CONVERSION MODEL LEARNING APPARATUS, AUDIO SIGNAL CONVERSION APPARATUS, AUDIO SIGNAL CONVERSION MODEL LEARNING METHOD AND PROGRAM simplified abstract|18032529]])=== | |
| | | | |
| | | | |
| Line 234: |
Line 136: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===SOUND SIGNAL HIGH FREQUENCY COMPENSATION METHOD, SOUND SIGNAL POST PROCESSING METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM ([[US Patent Application 18033018. SOUND SIGNAL HIGH FREQUENCY COMPENSATION METHOD, SOUND SIGNAL POST PROCESSING METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18033018]])=== |
| − | The patent application describes a device that learns how to convert voice signals.
| |
| − | * The device acquires input voice signals for learning.
| |
| − | * It uses a machine learning model to convert the input voice signals into a desired voice signal.
| |
| − | * The conversion process involves acquiring feature quantities for subsets of the input data.
| |
| − | * An adjustment parameter value is obtained to adjust the statistical distribution of the feature quantities.
| |
| − | * The learning stage conversion processing converts the input data into the desired voice signal using the adjustment parameter value.
| |
| − | | |
| − | '''Abstract'''
| |
| − | A voice signal conversion model learning device comprising: a learning data acquisition unit that acquires learning input data which is an input voice signal; and a learning stage conversion unit that executes a conversion learning model which is a model of machine learning including learning stage conversion processing of converting the learning input data into learning stage conversion destination data which is a voice signal of a conversion destination, wherein the learning stage conversion processing includes local feature quantity acquisition processing of acquiring a feature quantity for each learning input-side subset which is a subset of processing target input data having the processing target input data as a population, based on the processing target input data which is data to be processed, the conversion learning model further includes adjustment parameter value acquisition processing of acquiring an adjustment parameter value, which is a value of a parameter for adjusting a statistical value of a distribution of the feature quantity, based on the learning input data, and the learning stage conversion processing converts the learning input data into the learning stage conversion destination data using a result of a predetermined calculation based on the adjustment parameter value.
| |
| − | | |
| − | ===SOUND SIGNAL HIGH FREQUENCY COMPENSATION METHOD, SOUND SIGNAL POST PROCESSING METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM ([[US Patent Application 18033018. SOUND SIGNAL HIGH FREQUENCY COMPENSATION METHOD, SOUND SIGNAL POST PROCESSING METHOD, SOUND SIGNAL DECODE METHOD, APPARATUS THEREOF, PROGRAM, AND STORAGE MEDIUM simplified abstract|18033018]])=== | |
| | | | |
| | | | |
| Line 253: |
Line 144: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===PITCH EMPHASIS APPARATUS, METHOD AND PROGRAM FOR THE SAME ([[US Patent Application 18219562. PITCH EMPHASIS APPARATUS, METHOD AND PROGRAM FOR THE SAME simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18219562]])=== |
| − | The patent application describes a method for compensating high frequencies in a decoded sound signal.
| |
| − | * The method involves processing a stereo sound signal and decoding it into individual channel signals.
| |
| − | * A high-frequency compensation gain is calculated for each channel to match the high-frequency energy of the compensated decoded sound signal to the original decoded sound signal.
| |
| − | * The compensated decoded sound signal is obtained by adding the purified decoded sound signal and the high-frequency component multiplied by the compensation gain.
| |
| − | * This method aims to improve the quality of the sound signal by accurately reproducing high-frequency details.
| |
| − | | |
| − | '''Abstract'''
| |
| − | For each frame, an n-th channel compensated decoded sound signal X′is obtained that is a signal obtained by compensating a high frequency of an n-th channel purified decoded sound signal Xobtained by performing signal processing in a time domain on an n-th channel decoded sound signal {circumflex over ( )}X(n is each integer of 1 or more and N or less) that is a decoded sound signal of each channel of stereo obtained by decoding a stereo code CS. At this time, for the each frame with respect to the each channel, an n-th channel high-frequency compensation gain ρthat is a value for bringing high-frequency energy of the n-th channel compensated decoded sound signal X′close to high-frequency energy of the n-th channel decoded sound signal {circumflex over ( )}Xis obtained, and for the each frame with respect to the each channel, a signal obtained by adding the n-th channel purified decoded sound signal Xand a signal obtained by multiplying a high-frequency component of the n-th channel decoded sound signal {circumflex over ( )}Xby the n-th channel high-frequency compensation gain ρis obtained and output as the n-th channel compensated decoded sound signal.
| |
| − | | |
| − | ===PITCH EMPHASIS APPARATUS, METHOD AND PROGRAM FOR THE SAME ([[US Patent Application 18219562. PITCH EMPHASIS APPARATUS, METHOD AND PROGRAM FOR THE SAME simplified abstract|18219562]])=== | |
| | | | |
| | | | |
| Line 271: |
Line 152: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===OPTICAL ELEMENT, IMAGE SENSOR AND IMAGING DEVICE ([[US Patent Application 18031156. OPTICAL ELEMENT, IMAGE SENSOR AND IMAGING DEVICE simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18031156]])=== |
| − | The patent application describes a pitch enhancement processing technique that aims to improve the quality of audio signals, particularly in consonant sounds, without sounding unnatural to listeners.
| |
| − | | |
| − | * The pitch enhancement processing focuses on time segments where the spectral envelope of the signal is flat.
| |
| − | * In these time segments, an output signal is generated for each time point within the segment.
| |
| − | * The output signal is a combination of the current signal and a signal obtained by multiplying a past signal by a pitch period and a pitch gain, along with a predetermined constant and a value between 0 and 1.
| |
| − | * The goal is to enhance the pitch of the signal in a way that minimizes unnaturalness and discontinuities, even when switching frequently between consonant and other time segments.
| |
| − | | |
| − | '''Abstract'''
| |
| − | Provided is pitch enhancement processing having little unnaturalness even in time segments for consonants, and having little unnaturalness to listeners caused by discontinuities even when time segments for consonants and other time segments switch frequently. A pitch emphasis apparatus carries out the following as the pitch enhancement processing: for a time segment in which a spectral envelope of a signal has been determined to be flat, obtaining an output signal for each of times in the time segment, the output signal being a signal including a signal obtained by adding (1) a signal obtained by multiplying the signal of a time, further in the past than the time by a number of samples Tcorresponding to a pitch period of the time segment, a pitch gain σof the time segment, a predetermined constant B, and a value greater than 0 and less than 1, to (2) the signal of the time.
| |
| − | | |
| − | ===OPTICAL ELEMENT, IMAGE SENSOR AND IMAGING DEVICE ([[US Patent Application 18031156. OPTICAL ELEMENT, IMAGE SENSOR AND IMAGING DEVICE simplified abstract|18031156]])=== | |
| | | | |
| | | | |
| Line 290: |
Line 160: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===Primary Battery ([[US Patent Application 18251042. Primary Battery simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18251042]])=== |
| − | The patent application describes an optical element with a transparent layer covering a pixel that has two photoelectric conversion elements.
| |
| − | * The transparent layer has two regions - a first region that guides light to the first photoelectric conversion element and a second region that guides light to the second photoelectric conversion element.
| |
| − | * The transparent layer also has a plurality of structures, which are located in at least the second region.
| |
| − | * The first region is smaller than the second region.
| |
| − | | |
| − | '''Abstract'''
| |
| − | An optical element includes a transparent layer which covers a pixel including a first photoelectric conversion element and a second photoelectric conversion element; and a plurality of structures disposed on the transparent layer or in the transparent layer in a plane direction of the transparent layer, in which the transparent layer includes a first region which guides incident light to the first photoelectric conversion element, and a second region which guides incident light to the second photoelectric conversion element, the plurality of structures are disposed in at least the second region among the first region and the second region, and the first region is smaller than the second region.
| |
| − | | |
| − | ===Primary Battery ([[US Patent Application 18251042. Primary Battery simplified abstract|18251042]])=== | |
| | | | |
| | | | |
| Line 307: |
Line 168: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===Metal Air Battery ([[US Patent Application 18248964. Metal Air Battery simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18248964]])=== |
| − | A primary battery with specific components and an electrolyte is described in the patent application. Here are the key points:
| |
| − | | |
| − | * The battery consists of a positive electrode made of iron oxyhydroxide.
| |
| − | * The negative electrode is made of either magnesium or aluminum.
| |
| − | * An electrolyte is placed between the positive and negative electrodes.
| |
| − | * The battery is classified as a primary battery, meaning it is non-rechargeable.
| |
| − | * The use of iron oxyhydroxide in the positive electrode is a unique feature.
| |
| − | * The choice of magnesium or aluminum for the negative electrode is another distinguishing factor.
| |
| − | * The specific combination of these components is intended to enhance the battery's performance.
| |
| − | * The electrolyte plays a crucial role in facilitating the movement of ions between the electrodes.
| |
| − | * The patent application provides a detailed description of the battery's construction and operation.
| |
| − | | |
| − | '''Abstract'''
| |
| − | A primary battery including a positive electrode containing iron oxyhydroxide, a negative electrode containing magnesium or aluminum, and an electrolyte disposed between the positive electrode and the negative electrode.
| |
| − | | |
| − | ===Metal Air Battery ([[US Patent Application 18248964. Metal Air Battery simplified abstract|18248964]])=== | |
| | | | |
| | | | |
| Line 331: |
Line 176: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===RELAY DEVICE, TIME SYNCHRONIZATION SYSTEM, AND PROGRAM ([[US Patent Application 18031886. RELAY DEVICE, TIME SYNCHRONIZATION SYSTEM, AND PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18031886]])=== |
| − | The abstract describes a metal-air battery with specific components and an electrolytic solution containing a specific compound.
| |
| − | * Metal-air battery with air electrode, negative electrode, and electrolytic solution
| |
| − | * Electrolytic solution contains alkyl glucoside compound
| |
| − | * Alkyl glucoside has a specific range of carbon atoms
| |
| − | * The patent application focuses on the specific composition of the electrolytic solution for improved battery performance.
| |
| − | | |
| − | '''Abstract'''
| |
| − | A metal-air battery includes an air electrode, a negative electrode, and an electrolytic solution disposed between the air electrode and the negative electrode, and the electrolytic solution contains an alkyl glucoside having or more and or less carbon atoms.
| |
| − | | |
| − | ===RELAY DEVICE, TIME SYNCHRONIZATION SYSTEM, AND PROGRAM ([[US Patent Application 18031886. RELAY DEVICE, TIME SYNCHRONIZATION SYSTEM, AND PROGRAM simplified abstract|18031886]])=== | |
| | | | |
| | | | |
| Line 349: |
Line 184: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===DETERMINATION DEVICE, DETERMINATION METHOD, AND DETERMINATION PROGRAM ([[US Patent Application 18031620. DETERMINATION DEVICE, DETERMINATION METHOD, AND DETERMINATION PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18031620]])=== |
| − | The patent application describes a relay device with the following features:
| |
| − | | |
| − | * The device has an internal clock to indicate time.
| |
| − | * It includes a memory to store information.
| |
| − | * A communication unit is used to transmit and receive signals, including synchronization signals and normal signals, between a master and a slave.
| |
| − | * A retention time processing unit stores synchronization signal information received by the communication unit in the memory.
| |
| − | * The retention time processing unit extracts the synchronization signal information from the memory when a retention setting time longer than a first predetermined time elapses from the reception of the synchronization signal.
| |
| − | * The device's internal clock is used to determine when the retention setting time has elapsed.
| |
| − | * A transmission signal control unit is responsible for controlling the communication unit.
| |
| − | * When the first predetermined time elapses from the reception of the synchronization signal, the transmission signal control unit stops transmitting the normal signal.
| |
| − | * Instead, the transmission signal control unit transmits the synchronization signal, which indicates the synchronization signal information stored in the memory.
| |
| − | | |
| − | '''Abstract'''
| |
| − | A relay device includes a device internal clock to indicate time; a memory to store information; a communication unit to transmit and receive a signal including a synchronization signal and a normal signal to and from a master and a slave. Further, there is a retention time processing unit to store synchronization signal information indicating the synchronization signal received by the communication unit in the memory and extract the synchronization signal information from the memory when a retention setting time longer than a first predetermined time elapses from the reception of the synchronization signal by using the time indicated by the device internal clock; and a transmission signal control unit to control the communication unit to stop transmitting the normal signal when the first predetermined time elapses from the reception of the synchronization signal and transmit the synchronization signal indicating the synchronization signal information.
| |
| − | | |
| − | ===DETERMINATION DEVICE, DETERMINATION METHOD, AND DETERMINATION PROGRAM ([[US Patent Application 18031620. DETERMINATION DEVICE, DETERMINATION METHOD, AND DETERMINATION PROGRAM simplified abstract|18031620]])=== | |
| | | | |
| | | | |
| Line 373: |
Line 192: |
| | | | |
| | | | |
| − | '''Brief explanation'''
| + | ===LEARNING METHOD, WIRELESS QUALITY ESTIMATION METHOD, LEARNING DEVICE, WIRELESS QUALITY ESTIMATION DEVICE, AND PROGRAM ([[US Patent Application 18245962. LEARNING METHOD, WIRELESS QUALITY ESTIMATION METHOD, LEARNING DEVICE, WIRELESS QUALITY ESTIMATION DEVICE, AND PROGRAM simplified abstract (NIPPON TELEGRAPH AND TELEPHONE CORPORATION)|18245962]])=== |
| − | The patent application describes a device that can determine if user-generated content is generated by a malicious user or a legitimate user.
| |
| − | | |
| − | * The device calculates a characteristic amount of user-generated content produced by a user within a specific time period.
| |
| − | * It then uses this calculated characteristic amount, along with the characteristic amount of content generated by a known malicious user, to perform a learning process.
| |
| − | * The learning process helps the device create a model that can distinguish between content generated by a legitimate user and content generated by a malicious user.
| |
| − | * Finally, the device uses the learned model to determine whether the user-generated content is generated by a malicious user or not.
| |
| − | | |
| − | '''Abstract'''
| |
| − | A determination device includes processing circuitry configured to calculate a characteristic amount of user-generated content generated by a user in a predetermined period, perform learning by using the calculated characteristic amount of the user-generated content generated by a legitimate user and a characteristic amount of content generated by a malicious user, and determine whether the user-generated content is generated by the malicious user using a learned model.
| |
| − | | |
| − | ===LEARNING METHOD, WIRELESS QUALITY ESTIMATION METHOD, LEARNING DEVICE, WIRELESS QUALITY ESTIMATION DEVICE, AND PROGRAM ([[US Patent Application 18245962. LEARNING METHOD, WIRELESS QUALITY ESTIMATION METHOD, LEARNING DEVICE, WIRELESS QUALITY ESTIMATION DEVICE, AND PROGRAM simplified abstract|18245962]])=== | |
| | | | |
| | | | |
| Line 390: |
Line 198: |
| | | | |
| | Keisuke WAKAO | | Keisuke WAKAO |
| − |
| |
| − |
| |
| − | '''Brief explanation'''
| |
| − | The patent application describes a learning method for estimating wireless quality using machine learning.
| |
| − | * The learning method involves a learning step where a pre-trained model is generated by training the model with measurement data from multiple terminals.
| |
| − | * The method also includes a retraining step where the pre-trained model is further trained using measurement data that meets a specific condition.
| |
| − | * The goal is to improve the accuracy of estimating wireless quality by continuously updating the model with new data.
| |
| − | * This innovation can be applied to various wireless communication systems to enhance their performance and reliability.
| |
| − |
| |
| − | '''Abstract'''
| |
| − | A learning method in which a learning device performs learning on a model for estimating wireless quality by machine learning, and the learning method includes a learning step of generating a pre-trained model by performing the learning on the model by using measurement data of wireless quality obtained by a plurality of terminals, and a retraining step of retraining the pre-trained model by using measurement data satisfying a predetermined condition.
| |
