VOICE QUALITY ENHANCEMENT METHOD AND RELATED DEVICE

    公开(公告)号:US20240096343A1

    公开(公告)日:2024-03-21

    申请号:US18522743

    申请日:2023-11-29

    CPC classification number: G10L21/0232 G10L21/0308

    Abstract: This application relates to the artificial intelligence (AI) field, and specifically, to a voice quality enhancement method and a related device. The method includes: after a PNR mode is enabled, obtaining a noisy voice signal and target voice-related data, where the noisy-carrying voice signal includes a voice signal of a target user and an interfering noise signal, and the target voice-related data indicates a voice feature of the target user; and performing noise reduction on the noisy voice signal based on the target voice-related data by using a trained voice noise reduction model to obtain a noise-reduced voice signal of the target user, where the voice noise reduction model is implemented based on a neural network. In embodiments of this application, voice of a target person can be enhanced, and interference can be suppressed.

    ENCODING METHOD, DECODING METHOD, AND COMMUNICATION APPARATUS

    公开(公告)号:US20240014925A1

    公开(公告)日:2024-01-11

    申请号:US18472774

    申请日:2023-09-22

    CPC classification number: H04L1/0009 H04B7/0413

    Abstract: This application provides an encoding method, a decoding method, and a communication apparatus, to improve encoding and decoding performance. The method includes: obtaining n information bit sequences, where n is a quantity of antenna ports, and n is a positive integer greater than 1; performing first channel encoding on the n information bit sequences to obtain n first encoded sequences, where the n first encoded sequences have a same length; generating n second encoded sequences based on a polar encoding matrix and the n first encoded sequences; and outputting the n second encoded sequences.

    CODING METHOD AND RELATED DEVICE
    33.
    发明申请

    公开(公告)号:US20220224947A1

    公开(公告)日:2022-07-14

    申请号:US17584726

    申请日:2022-01-26

    Abstract: The present disclosure provides example coding method, apparatus, and computer-readable storage medium. One example method includes sorting a plurality of pieces of run-length encoding (RLE) data based on their distribution probabilities. The plurality of pieces of sorted RLE data are mapped onto a plurality of pieces of reassembled data. The plurality of pieces of reassembled data are expanded into a plurality of pieces of binary data. A first matrix is generated based on the plurality of pieces of binary data. A code sequence is determined by processing a source signal, where the code sequence comprises a first set and a second set. A first vector is decoded to output a third set, where the third set includes one or more bits reserved after processing the source signal and one or more locations at which a decoding error occurs in one or more bits discarded after processing the source signal.

    SOFTWARE HANDLING DEVICE, SERVER SYSTEM AND METHODS THEREOF

    公开(公告)号:US20200210602A1

    公开(公告)日:2020-07-02

    申请号:US16726593

    申请日:2019-12-24

    Abstract: The present disclosure relates to a software handling device and a server system. The software handling device comprises a processor and a transceiver, wherein the transceiver is configured to transmit various requests and to receive various verifications and encryption keys to and from a server system. The server system comprises an authentication server, a licensing server and a software application server, wherein the server system is configured to receive various requests and to transmit various verifications and encryption keys from and to a software handling device. Furthermore, the present disclosure also relates to corresponding methods, a computer program, and a computer program product.

    INFORMATION ADDING METHOD AND APPARATUS
    35.
    发明申请

    公开(公告)号:US20200052818A1

    公开(公告)日:2020-02-13

    申请号:US16659726

    申请日:2019-10-22

    Abstract: An information adding method and apparatus, to increase a quantity of terminals that can be represented by an identifier sequence. The method includes: performing, by a transmit end, polar code encoding on a first bit sequence to generate an encoded second bit sequence; adding, by the transmit end, a part or all of an identifier sequence to the second bit sequence to generate a third bit sequence, where the identifier sequence is used to identify a terminal; and sending, by the transmit end, the third bit sequence.

    METHODS AND APPARATUSES FOR CONSTRUCTING PUNCTURED POLAR CODE
    36.
    发明申请
    METHODS AND APPARATUSES FOR CONSTRUCTING PUNCTURED POLAR CODE 审中-公开
    用于构建受激极点代码的方法和装置

    公开(公告)号:US20170077954A1

    公开(公告)日:2017-03-16

    申请号:US15363028

    申请日:2016-11-29

    Inventor: Hui SHEN Bin LI

    CPC classification number: H03M13/13 H03M13/6362 H04L1/0058

    Abstract: Methods and apparatuses are provided for constructing a punctured polar code in the encoding and decoding field to improve decoding performance of a punctured polar code and reduce a frame error rate of the punctured polar code. The method is as follows: comparing a phase sequence number of a current bit channel with a period index of a puncturing pattern to obtain a comparison result; obtaining a transition probability of the bit channel according to the comparison result and bit parity conditions of a sequence number of the bit channel in each phase; obtaining a reliability value of each bit channel according to the transition probability; and determining an information bit index set according to the reliability values.

    Abstract translation: 提供了用于在编码和解码字段中构建穿孔极性码的方法和装置,以改善打孔的极性码的解码性能并降低穿孔极性码的帧错误率。 该方法如下:将当前比特信道的相序号与打孔图案的周期索引进行比较以获得比较结果; 根据比较结果和每个相位中比特信道的序列号的比特奇偶校验条件获得比特信道的转换概率; 根据转换概率获得每个位信道的可靠性值; 以及根据可靠性值确定信息比特索引集合。

    ENCODING OR DECODING METHOD AND APPARATUS

    公开(公告)号:US20140328399A1

    公开(公告)日:2014-11-06

    申请号:US14317083

    申请日:2014-06-27

    Abstract: Embodiments of the present invention provide an encoding or decoding method and apparatus. The method includes: extracting first information in a bitstream; determining a chroma component intra prediction mode according to the first information; when the chroma component intra prediction mode cannot be determined according to the first information, extracting second information in the bitstream; and determining the chroma component intra prediction mode according to the second information, where the first information includes information for indicating whether the chroma component intra prediction mode is a DM mode or an LM mode, the second information is used to indicate a remaining mode as the chroma component intra prediction mode, and the remaining mode is one of available chroma component intra prediction modes other than a mode that may be determined according to the first information.

Patent Agency Ranking