-
公开(公告)号:US20240038215A1
公开(公告)日:2024-02-01
申请号:US18223265
申请日:2023-07-18
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Qiuyue MA , Yuxing ZHENG , Hosang SUNG , Lizhong WANG , Xiaoyan LOU
Abstract: The present disclosure provides methods, devices, and computer-readable mediums for audio signal processing. In some embodiments, a method executed by an electronic device includes obtaining guidance features corresponding to an audio signal to be processed, the guidance features indicating distinguishable features of at least one signal type of at least one signal category. The method further includes extracting, according to the guidance features, target audio features corresponding to the audio signal. The method further includes determining, according to the target audio features, a target signal type of the audio signal from among the at least one signal type of the at least one signal category. The method further includes performing corresponding processing according to the target signal type of the audio signal.
-
公开(公告)号:US20220083745A1
公开(公告)日:2022-03-17
申请号:US17533797
申请日:2021-11-23
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Wenbo YUAN , Yuxing ZHENG , Song LIU
IPC: G06F40/53 , G06F40/47 , G06F40/55 , G06F40/279
Abstract: Embodiments of the present disclosure provide a method, an apparatus and an electronic device for determining a word representation vector, and a computer-readable storage medium, which belong to a field of processing natural languages. The method includes obtaining a set of glyph units of a text; obtaining a context vector of the text based on the set of glyph units; and predicting next word of the text based on the context vector. The method for determining the word representation vector of the present disclosure can effectively obtain a corresponding set of glyph units even for hieroglyphics in which hyperbolic characters are prone to appear or languages evolved from the hieroglyphics, thereby improving an accuracy of determining the word representation vector.
-