-
公开(公告)号：WO2022255941A2
公开(公告)日：2022-12-08
申请号：PCT/SG2022/050342
申请日：2022-05-23
Applicant: LEMON INC.
Inventor： RASHID, Imran , SMITH, Jordan , SMITH, Fraser , HAWKINS, Will , NEWTON-REX, Edmund Philip
IPC: H04N5/265 , G11B27/06 , G10L25/57 , G11B27/007 , G11B27/031
Abstract: The present invention relates to method for generating a video remix, the method comprising: receiving an input video (101); selecting at least one excerpt from the input video (103), wherein an audio signal of the selected excerpt includes at least one onset; determining a plurality of sub-sequences of the at least one excerpt (104); and rearranging the plurality of sub-sequences according to a predetermined pattern (105) to form the video remix.
-
公开(公告)号：WO2023063881A2
公开(公告)日：2023-04-20
申请号：PCT/SG2022/050705
申请日：2022-09-29
Applicant: LEMON INC.
Inventor： SMITH, Jordan , WANG, Ju-Chiang , LU, Wei Tsung , SONG, Xuchen
Abstract: Devices, systems, and methods related to implementing supervised metric learning during a training of a deep neural network model are disclosed herein. In examples, audio input may be received, where the audio input includes a plurality of song fragments from a plurality of songs. For each song fragment, an aligning function may be performed to center the song fragment based on determined beat information, thereby creating a plurality of aligned song fragments. For each song fragment of the plurality of song fragments, an embedding vector may be obtained from the deep neural network. Thus, a batch of aligned song fragments from the plurality of aligned song fragments may be selected, such that a training tuple may be selected. A loss metric may be generated based on the selected training tuple and one or more weights of the deep neural network model may be updated based on the loss metric.
