Bytecover3: Accurate Cover Song Identification On Short Queries

Deep learning based methods have become a paradigm for cover song identification (CSI) in recent years, where the ByteCover systems have achieved state-of-the-art results on all the mainstream datasets of CSI. However, with the burgeon of short videos, many real-world applications require matching s...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1 - 5
Main Authors Du, Xingjian, Wang, Zijie, Liang, Xia, Liang, Huidong, Zhu, Bilei, Ma, Zejun
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.06.2023
Subjects
Benchmark testing
ByteCover
Cover song identification
Deep learning
Feature extraction
Length measurement
local alignment loss
Loss measurement
MaxMean similarity
Pipelines
short queries
Signal processing
Online AccessGet full text

Cover

More Information
Summary:Deep learning based methods have become a paradigm for cover song identification (CSI) in recent years, where the ByteCover systems have achieved state-of-the-art results on all the mainstream datasets of CSI. However, with the burgeon of short videos, many real-world applications require matching short music excerpts to full-length music tracks in the database, which is still under-explored and waiting for an industrial-level solution. In this paper, we upgrade the previous ByteCover systems to ByteCover3 that utilizes local features to further improve the identification performance of short music queries. ByteCover3 is designed with a local alignment loss (LAL) module and a two-stage feature retrieval pipeline, allowing the system to perform CSI in a more precise and efficient way. We evaluated ByteCover3 on multiple datasets with different benchmark settings, where ByteCover3 beat all the compared methods including its previous versions.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10095389