AUDIO QUANTIZER AND AUDIO DEQUANTIZER AND RELATED METHODS

    公开(公告)号:EP4447044A2

    公开(公告)日:2024-10-16

    申请号:EP24184655.9

    申请日:2021-07-05

    IPC分类号: G10L19/18

    摘要: An audio quantizer for quantizing a plurality of audio information items, comprises: a first stage vector quantizer (141, 143) for quantizing the plurality of audio information items to determine a first stage vector quantization result and a plurality of intermediate quantized items corresponding to the first stage vector quantization result; a residual item determiner (142) for calculating a plurality of residual items from the plurality of intermediate quantized items and the plurality of audio information items; and a second stage vector quantizer (145) for quantizing the plurality of residual items to obtain a second stage vector quantization result, wherein the first stage vector quantization result and the second stage vector quantization result are a quantized representation of the plurality of audio information items.

    THREE-COMPONENT CODEBOOK BASED CSI REPORTING
    12.
    发明公开

    公开(公告)号:EP4443754A2

    公开(公告)日:2024-10-09

    申请号:EP23209152.0

    申请日:2020-08-11

    IPC分类号: H04B7/00

    摘要: The present invention relates to method performed by a user equipment (UE) for providing channel state information (CSI) feedback in the form of one or more CSI reports in a wireless communication system (A), comprising receiving, from a network node, (gNB), higher layer configuration(s) of one or more downlink reference signals, and one or more CSI report configuration(s) associated with the downlink reference signal configuration(s), and a radio signal via a MIMO channel, the radio signal including the downlink reference signal(s) according to the one or more downlink reference signal configuration(s), estimating, the downlink MIMO channel based on measurements on the received one or more downlink reference signals, the downlink reference signals provided over a configured number of frequency domain resources, time domain resources and one or more ports, determining, for each CSI report configuration, a precoding matrix based on an estimated channel matrix and two codebooks, the two codebooks including a spatial codebook comprising one or more spatial domain (SD) basis components of the precoder, and a delay codebook comprising one or more delay domain (DD) basis components of the precoder, and one or more non-zero combining coefficients for complex combining of the one or more SD and DD basis vectors, and reporting, to the network node, the one or more CSI reports for the one or more CSI report configurations, wherein each CSI report contains the selected precoding matrix in the form of a precoding matrix identifier, PMI, and a rank identifier, RI, indicating the transmission rank for the RI layers of the precoding matrix, and wherein each CSI report comprises two parts: CSI part 1 and CSI part 2, wherein CSI part 1 has a fixed payload size and comprises information indicating the size of the payload of CSI part 2, wherein CSI part 2 comprises at least the amplitude and phase information of the selected non-zero combining coefficients of the CSI report, and wherein a portion, or the entirety, of CSI part 2 is available for omission from the CSI report.

    APPARATUS AND METHOD FOR PROCESSING AN INFORMATION SIGNAL USING A MULTI-STAGE PROCESSING

    公开(公告)号:EP4439560A1

    公开(公告)日:2024-10-02

    申请号:EP23165199.3

    申请日:2023-03-29

    IPC分类号: G10L25/30 G10L21/02 G06N3/045

    摘要: An apparatus for processing an information signal comprises: a feature extractor (100) for extracting a set of features from the information signal, wherein each feature of the set of features comprises at least two feature components, and wherein the set of features comprises a first subset with the first feature components and a second subset with the second feature components; and a neural network processor (300) comprising: a first neural network (340) for receiving, as an input, the first subset and for outputting a processed first subset; a combiner (350) for combining the processed first subset and the second subset to obtain a combined subset; and a second neural network (360) for receiving, as an input, the combined subset and for outputting a processed combined output, wherein the processed combined output represents a processed information signal, or wherein the apparatus is configured to calculate the processed information signal using the processed combined output, and wherein a complexity of the first neural network (340) is greater than a complexity of the second neural network.

    METHOD FOR SCREENING SUBSTANCES HAVING A REQUIRED PHYSICAL PROPERTY, CHEMICAL PROPERTY OR PHYSIOLOGICAL EFFECT FROM A GROUP OF SUBSTANCES USING ELECTRON DENSITIES

    公开(公告)号:EP4432293A1

    公开(公告)日:2024-09-18

    申请号:EP23161477.7

    申请日:2023-03-13

    IPC分类号: G16C20/30 G16C20/64

    CPC分类号: G16C20/30 G16C20/70 G16C20/64

    摘要: The present invention provides a method for screening substances having a requested physical property, chemical property or physiological effect from a group of substances comprising the steps
    • providing a group of k substances by a user, wherein k ∈ N;
    • providing a classification or a property label for a physical property, chemical property or physiological effect comprising Ci classes or Vi values, wherein i ∈ N;
    • calculating electron density cube files for every substance by semiempirical molecular calculation and providing weights Wk, such as electronegativity or electron affinity cube files for every substance;
    • providing a trained artificial neural network architecture for the classification or label property, wherein the artificial neural network architecture uses the electron density cube files and weights Wk as input to calculate a tensor of shape of each substance describing the spatial structure of the substance and a tensor of weights, such as electronegativity or electron affinity assigned to the spatial structure of the substance;
    • assigning each substance to a class Ci or a value Vi by utilizing the tensor of weights, such as electronegativity or electron affinity of substance k as weighting for the electronic density cube files in the artificial neural network architecture;
    • displaying and/or outputting of the substances assigned to the classes Ci of the classification or assigned to the values Vi of the property label;
    • selecting the substances assigned to the class Ci with the required physical property, chemical property or physiological effect or assigned to the required value Vi of a physical property, chemical property or physiological effect;
    • experimental verification by a user of the physical property, chemical property or physiological effect of at least part of the selected substances.