Browse State-of-the-Art › Cover song identification

Cover song identification

7 papers with code · 4 benchmarks · 0 datasets archive 2025-07-28

Cover Song Identification is the task of identifying an alternative version of a previous musical piece, even though it may differ substantially in timbre, tempo, structure, and even fundamental aspects relating to the harmony and melody of the song. The term “cover” is so wide that it ranges from acoustic renditions of a previous song, to Jimi Hendrix’ famous (and radical) reinterpretation of Bob Dylan’s “All Along the Watchtower”, to Rage Against the Machine essentially rewriting Bob Dylan’s “Maggie’s Farm”. Beyond its value for computational musicology and for enhancing music recommendation, Cover Song Identification is of interest because of its potential for benchmarking other music similarity and retrieval algorithms. Chord analysis, melody extraction and music similarity are all strongly connected to Cover Song Identification - another field of music analysis where AI has been applied.

Source: Artificial Musical Intelligence: A Survey

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Dataset	Best model (first row in archive order)	Paper	Code	Syntology	Compare
SHS100K-TEST (8 rows)	CoverHunter-256	CoverHunter: Cover Song Identification with Refined Attention and...	code	—	Compare
Covers80 (5 rows)	ByteCover2	BYTECOVER2: TOWARDS DIMENSIONALITY REDUCTION OF LATENT EMBEDDING...	—	—	Compare
Da-TACOS (4 rows)	ByteCover2	BYTECOVER2: TOWARDS DIMENSIONALITY REDUCTION OF LATENT EMBEDDING...	—	—	Compare
YouTube350 (4 rows)	SCNN-M	SIMILARITY LEARNING FOR COVER SONG IDENTIFICATION USING...	—	—	Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

7 shown of 7 papers with code (18 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

Learning a Representation for Cover Song Identification Using Convolutional Neural Network

1 Nov 2019 2 repositories listed

We first train the network through classification strategies; the network is then used to extract music representation for cover song identification.
A Semi-Supervised Deep Learning Approach to Dataset Collection for Query-By-Humming Task

2 Dec 2023 1 repository listed

To expand our dataset, we employ a semi-supervised model training pipeline that leverages the QbH task as a specialized case of cover song identification (CSI) task.
CoverHunter: Cover Song Identification with Refined Attention and Alignments

15 Jun 2023 1 repository listed

Abstract: Cover song identification (CSI) focuses on finding the same music with different versions in reference anchors given a query track.
ByteCover: Cover Song Identification via Multi-Loss Training

27 Oct 2020 1 repository listed

We present in this paper ByteCover, which is a new feature learning method for cover song identification (CSI).
Towards Cover Song Detection with Siamese Convolutional Neural Networks

20 May 2020 1 repository listed

A cover song, by definition, is a new performance or recording of a previously recorded, commercially released song.
Accurate and Scalable Version Identification Using Musically-Motivated Embeddings

28 Oct 2019 1 repository listed

The version identification (VI) task deals with the automatic detection of recordings that correspond to the same underlying musical piece.
Large-Scale Cover Song Detection in Digital Music Libraries Using Metadata, Lyrics and Audio Features

30 Aug 2018 1 repository listed

In this work, we investigate whether textual music information (such as metadata and lyrics) can be used along with audio for large-scale cover identification problem in a wide digital music library.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections