RECORD
Learning a Representation for Cover Song Identification Using Convolutional Neural Network
Multimedia · Submitted 1 Nov 2019
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experimental results show that our approach outperforms state-of-the-art methods on all public datasets, improving the performance especially on the large dataset.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Cover song identification represents a challenging task in the field of Music Information Retrieval (MIR) due to complex musical variations between query tracks and cover versions. Previous works typically utilize hand-crafted features and alignment algorithms for the task. More recently, further breakthroughs are achieved employing neural network approaches. In this paper, we propose a novel Convolutional Neural Network (CNN) architecture based on the characteristics of the cover song task. We first train the network through classification strategies; the network is then used to extract music representation for cover song identification. A scheme is designed to train robust models against tempo changes. Experimental results show that our approach outperforms state-of-the-art methods on all public datasets, improving the performance especially on the large dataset.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Cover song identification represents a challenging task in the field of Music Information Retrieval (MIR) due to complex musical variations between query tracks and cover versions. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s1 | Previous works typically utilize hand-crafted features and alignment algorithms for the task. | background 1.00 | 0.03 | 0.01 | asserted 1.00 |
| s2 | More recently, further breakthroughs are achieved employing neural network approaches. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s3 | In this paper, we propose a novel Convolutional Neural Network (CNN) architecture based on the characteristics of the cover song task. | contribution 0.93 | 0.86 | 0.05 | asserted 1.00 |
| s4 | We first train the network through classification strategies; the network is then used to extract music representation for cover song identification. | method 0.98 | 0.93 | 0.05 | asserted 0.98 |
| s5 | A scheme is designed to train robust models against tempo changes. | method 0.88 | 0.86 | 0.02 | asserted 0.95 |
| s6 | Experimental results show that our approach outperforms state-of-the-art methods on all public datasets, improving the performance especially on the large dataset. | result 1.00 | 0.96 | 0.90 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Cover song identification represents a challenging task in the field of Music Information Retrieval (MIR) due to complex musical variations between query tracks and cover versions. Previous works typically utilize hand-crafted features and alignment algorithms for the task. More recently, further breakthroughs are achieved employing neural network approaches. In this paper, we propose a novel Convolutional Neural Network (CNN) architecture based on the characteristics of the cover song task. We first train the network through classification strategies; the network is then used to extract music representation for cover song identification. A scheme is designed to train robust models against tempo changes. Experimental results show that our approach outperforms state-of-the-art methods on all public datasets, improving the performance especially on the large dataset.
Human review
How the literature uses it
3 arXiv papers cite this in 6 sentences
Papers citing it · 1 sentence without a confident label
Cites it as background 3 papers
-
[ref] and [ref] devised TPP-Net and CQT-Net that could be naturally adapted to deal with key transposition in cover songs and they designed a training scheme to make their model more robust.
Contrastive Learning with Positive-Negative Frame Mask for Music Representation · Cover Song Identification · 0.91
-
In [ref] , the authors use VGG on CQT features with variable length to tackle the problem of tempo changes of the cover songs.
A Semi-Supervised Deep Learning Approach to Dataset Collection for Query-By-Humming Task · Related Work · 0.81
-
And cover songs identification : [ref] , [ref] , [ref] , etc.
An approach to hummed-tune and song sequences matching · Related Works · 1.00
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.