Abstract: A solar cell structure includes a semiconductor substrate having a front side and a back side. A pyramid structure is disposed on the front side of the semiconductor substrate. The pyramid structure has an aspect ratio between 0.5-1.2. A front passivation layer is disposed on the pyramid structure. A first anti-reflection layer is disposed on the pyramid structure. The first anti-reflection layer is a multi-layered, graded anti-reflection layer having at least three coating layers. The at least three coating layers comprise a silicon oxynitride layer having a thickness of 15-30 nm and a refractive index between 1.65 and 1.75. The silicon oxynitride layer is an outermost layer of the multi-layered, graded anti-reflection layer.

Abstract: A data processing method includes in response to determining that data corresponding to received data to be written exists, determining a first data identifier of the data corresponding to the data to be written, where the first data identifier is used to obtain a first storage area corresponding to the data, generating a second data identifier of the data to be written, writing the data to be written into the second storage area, in response to receiving a data rollback instruction, obtaining a target data identifier corresponding to the data rollback instruction, and determining a target storage area based on the target data identifier to obtain rollback data from the target storage area. The second data identifier is different from the first data identifier, and the second data identifier corresponds to a second storage area different from the first storage area.

Abstract: The present disclosure belongs to the field of energy materials, and relates to a preparation method of a solid electrolyte, in particular to a method for forming a membrane by using an electrolyte to activate a porous powder material prepared by in-situ polymerization of a polymer on the surfaces of cellulose nanocrystals, and then hot-pressing. According to the technical solution of the present disclosure, cellulose nanocrystals are used as templates, the powder material with a porous structure is prepared by in-situ polymerization growth of the polymer on the surfaces of the cellulose nanocrystals, a small amount of electrolyte is used to activate the powder, and the solid electrolyte is prepared by hot-pressing membrane formation. The solid electrolyte prepared by the present disclosure has excellent electrochemical performance and mechanical performance, and a broad application prospect.

Abstract: A method includes receiving an overlapped audio signal that includes audio spoken by a speaker that overlaps a segment of synthesized playback audio. The method also includes encoding a sequence of characters that correspond to the synthesized playback audio into a text embedding representation. For each character in the sequence of characters, the method also includes generating a respective cancelation probability using the text embedding representation. The cancelation probability indicates a likelihood that the corresponding character is associated with the segment of the synthesized playback audio overlapped by the audio spoken by the speaker in the overlapped audio signal.

Abstract: A method for training a generalized automatic speech recognition model for joint acoustic echo cancellation, speech enhancement, and voice separation includes receiving a plurality of training utterances paired with corresponding training contextual signals. The training contextual signals include a training contextual noise signal including noise prior to the corresponding training utterance, a training reference audio signal, and a training speaker vector including voice characteristics of a target speaker that spoke the corresponding training utterance. The operations also include training, using a contextual signal dropout strategy, a contextual frontend processing model on the training utterances to learn how to predict enhanced speech features. Here, the contextual signal dropout strategy uses a predetermined probability to drop out each of the training contextual signals during training of the contextual frontend processing model.

Abstract: A computer-implemented method includes receiving a sequence of acoustic frames corresponding to an utterance and generating a reference speaker embedding for the utterance. The method also includes receiving a target speaker embedding for a target speaker and generating feature-wise linear modulation (FiLM) parameters including a scaling vector and a shifting vector based on the target speaker embedding. The method also includes generating an affine transformation output that scales and shifts the reference speaker embedding based on the FiLM parameters. The method also includes generating a classification output indicating whether the utterance was spoken by the target speaker based on the affine transformation output.

Abstract: There is provided an information processing device including: a global map acquiring unit that acquires at least a part of a global map representing positions of objects in a real space where a plurality of users are in activity; a local map generating unit that generates a local map representing positions of nearby objects detectable by a device of one user among the plurality of users; and an updating unit that updates the global map based on position data of objects included in the local map.

Abstract: A system enables entities to access a single platform in order to utilize electronic data storage for storing different types of information. One or more computers may operate an electronic data storage processing network that entities can access when updating information in electronic data storage. The electronic data storage processing network may operate a plurality of electronic data storage processing modules, which can include an aggregator module, a formatter module, an operator signer module, and a validator module. Based on the specific use case for which electronic data storage is utilized, recordable data that is to be added to the electronic data storage can be processed by the appropriate aggregating, formatting, signing, and validating functions provided by the electronic data storage processing modules.

Abstract: A method includes storing, in one or more databases amongst a plurality of databases by one or more nodes in a distributed database system, data for one or more of network enabled devices. The data for each network enabled device includes encrypted private data, and metadata associated with the private data. The metadata may include permissions data, time period validation data, and encryption parameters. In addition, the method may include locating the encrypted first private data and determining using first permissions data associated with the encrypted first private data and using the second network-enabled device identifier if the second network-enabled device is authorized to access the first private data. The method includes providing the first private data to the second network-enabled device. The second network-enabled device obtains and decrypts the encrypted first private data to obtain the first private data.

Abstract: A method for performing biometric authentication is disclosed. In one example, the method includes obtaining first and second biometric templates and comparing them to determine if they match. The method also includes determining if a biometric certification token is valid. A computing device or other device may communicate with a verification system to determine the validity of the biometric certification token.

Abstract: A method includes obtaining a speaker identification (SID) model trained to predict speaker embeddings from utterances spoken by different speakers, the SID model includes a trained audio encoder and a trained SID head. The method also includes receiving a plurality of synthetic speech detection (SSD) training utterances that include a set of human-originated speech samples and a set of synthetic speech samples. The method also includes training, using the trained audio encoder, a SSD head on the SSD training utterances to learn to detect the presence of synthetic speech in audio encodings encoded by the trained audio encoder. The operations also include providing, for execution on a computing device, a multitask neural network model for performing both SID tasks and SSD tasks on input audio data in parallel.

Abstract: A method for efficiently storing and verifying records is disclosed. The method may comprise receiving a first hash of first interaction data and determining an interaction identifier associated with the first hash, then storing the first hash in a database along with the interaction identifier and determining a root hash of a hash tree. In addition, the method may also comprise providing the root hash of the hash tree to a public blockchain. Embodiments of the invention also allow users to easily present records to a third party or inquiring entity. Furthermore, interactions may be processed more quickly than previous blockchain methods that publish to a block during each individual interaction.

Abstract: Systems, methods, and devices are disclosed for preventing relay attacks. A user device may receive (e.g., when proximate to the first access device), from an intervening device, device identification data for a first access device. A message may be received from a second access device via the intervening device. The message may include a digital signature generated based at least in part on second access device identification data. The user device may validate the message utilizing the digital signature and a public key. If the message is invalid, the user device may discard the message. If the message is valid, (e.g., unaltered), the user device may determine that the user has not confirmed an intent to interact with the second access device and may terminate an further interaction with the second access device accordingly.

Abstract: Described herein are systems and methods for providing secure blockchain routing utilizing an extended blockchain protocol. In some embodiments, a blockchain routing node may join an overlay network including a plurality of blockchain routing nodes. The blockchain routing node may receive a plurality of forwarding tables from the plurality of blockchain routing nodes in accordance with an extended blockchain protocol. The blockchain routing node may determine a routing table for the overlay network based at least on part on the plurality of forwarding tables. In some embodiments, the blockchain routing node may route a payload message to a destination blockchain routing node in the overlay network in accordance with the determined routing table.

Abstract: A method includes receiving an utterance of speech and segmenting the utterance of speech into a plurality of segments. For each segment of the utterance of speech, the method also includes extracting a speaker=discriminative embedding from the segment and predicting a probability distribution over possible speakers for the segment using a probabilistic generative model configured to receive the extracted speaker-discriminative embedding as a feature input. The probabilistic generative model trained on a corpus of training speech utterances each segmented into a plurality of training segments. Each training segment including a corresponding speaker-discriminative embedding and a corresponding speaker label. The method also includes assigning a speaker label to each segment of the utterance of speech based on the probability distribution over possible speakers for the corresponding segment.

Abstract: Provided is a wearable device, including a base configured to be worn by a user, at least one data element at least partially positioned on or within the base and programmed or configured to have account data stored thereon, and at least one antenna including an open circuit, the at least one antenna at least partially positioned on or within the base and configured to transmit at least a portion of the account data and receive at least a portion of transaction data from at least one target device when the open circuit of the antenna is closed and becomes powered by at least one power source. Other expressions are also disclosed.

Abstract: The present disclosure provides a broadband dual-polarized solar cell antenna and an antenna array. The broadband dual-polarized solar cell antenna includes an antenna dipole layer, an isolation layer, a solar cell layer, and a ground that are arranged sequentially from top to bottom, where the antenna dipole layer is connected to the ground and a radio frequency (RF) coaxial connector through a metal feeding probe structure, the solar cell layer is placed on the ground, the isolation layer is located between the antenna dipole layer and the solar cell layer, and the isolation layer is made of a transparent material. The present disclosure is small in sunlight shielding and high in transparency, and has a broadband dual-polarized wide-angle scanning capability, which ensures performance of the antenna and power generation efficiency of the solar cell, and is highly applicable in engineering.

Abstract: Techniques disclosed herein are directed towards streaming keyphrase detection which can be customized to detect one or more particular keyphrases, without requiring retraining of any model(s) for those particular keyphrase(s). Many implementations include processing audio data using a speaker separation model to generate separated audio data which isolates an utterance spoken by a human speaker from one or more additional sounds not spoken by the human speaker, and processing the separated audio data using a text independent speaker identification model to determine whether a verified and/or registered user spoke a spoken utterance captured in the audio data. Various implementations include processing the audio data and/or the separated audio data using an automatic speech recognition model to generate a text representation of the utterance.

Abstract: The present disclosure belongs to the field of energy materials, and relates to a preparation method of a solid electrolyte, in particular to a method for forming a membrane by using an electrolyte to activate a porous powder material prepared by in-situ polymerization of a polymer on the surfaces of cellulose nanocrystals, and then hot-pressing. According to the technical solution of the present disclosure, cellulose nanocrystals are used as templates, the powder material with a porous structure is prepared by in-situ polymerization growth of the polymer on the surfaces of the cellulose nanocrystals, a small amount of electrolyte is used to activate the powder, and the solid electrolyte is prepared by hot-pressing membrane formation. The solid electrolyte prepared by the present disclosure has excellent electrochemical performance and mechanical performance, and a broad application prospect.

Abstract: Systems, methods, and computer readable media are for providing a hand free interaction between a user and a dispenser device. A mobile communication device and a beacon device associated with the dispenser device (or the dispenser device operating as a beacon device) may perform mutual authentication with a federated platform. Once the entities are authenticated, the user is allowed to dispense the resource utilizing the dispenser device. Data associated with the interaction and related to the resource dispensed may be provided to the federated platform via the mobile communication device and the interaction data may be recorded. The federated platform may subsequently provide the interaction data to a resource provider to enable the resource provider to conduct a settlement process.