Similarity Learning For Cover Song Identification Using Cross-Similarity Matrices of Multi-Level Deep Sequences
Abstract
In recent years, several deep learning models have been proposed for cover song identification and they have been designed to learn fixed-length feature vectors for music tracks. However, the aspect of temporal progression of music, which is important for measuring the melody similarity between two tracks, is not well represented by fixed-length vectors. In this paper, we propose a new Siamese network architecture for music melody similarity metric learning. The architecture consists of two parts. One part is a network for learning the deep sequence representation of music tracks, and the other is a similarity estimation network which takes as input the cross-similarity matrices calculated from the deep sequences of a pair of tracks. The two networks are jointly trained and optimized to achieve high melody similarity prediction accuracy. Experiments conducted on several public datasets demonstrate the superiority of the proposed architecture.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Deep reinforcement learning encoders suffer from observation overfitting, so data augmentation can improve data efficiency and generalisation ability of a DRL agent.
“In general, DRL encoders suffer from observation overfitting [160,161], so DA can also be used to improve data efficiency and generalisation ability of a DRL agent [141,142].”
From Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future Prospects (2023) · cites this paper as [160]
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · see citing works
librosa: Audio and Music Signal Analysis in Python
McFee, B., Raffel, C., Liang, D., Ellis, D. P. W., McVicar, M., Battenberg, E., & Nieto, O. (2015) · Proceedings of the Python in Science Conferences · doi:10.25080/majora-7b98e3ed-003 · Cited by 3,099 · see citing works
Calculation of a constant Q spectral transform
Brown, J. C. (1991) · The Journal of the Acoustical Society of America · doi:10.1121/1.400476 · Cited by 898 · see citing works
Realtime Chord Recognition of Musical Sound : a System Using Common Lisp Music
Fujishima, T. (1999) · University of Michigan Library Repository · Cited by 404 · see citing works
Chroma Binary Similarity and Local Alignment Applied to Cover Song Identification
Serrà, J., Gómez, E., Herrera, P., & Serra, X. (2008) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2008.924595 · Cited by 260 · see citing works
Audio Matching Via Chroma-Based Statistical Features.
Müller, M., Kurth, F., & Clausen, M. V. (2005) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.1416799 · Cited by 200 · see citing works
Cross recurrence quantification for cover song identification
Serrà, J., Serra, X., & Andrzejak, R. G. (2009) · New Journal of Physics · doi:10.1088/1367-2630/11/9/093017 · Cited by 155 · see citing works
Audio Cover Song Identification and Similarity: Background, Approaches, Evaluation, and Beyond
Serrà, J., Gómez, E., & Herrera, P. (2010) · Studies in computational intelligence · doi:10.1007/978-3-642-11674-2_14 · Cited by 124 · see citing works
Large-Scale Cover Song Recognition Using the 2D Fourier Transform Magnitude
Ellis, D. P. W., & Bertin-Mahieux, T. (2012) · Columbia Academic Commons (Columbia University) · doi:10.7916/d8z60zbv · Cited by 84 · see citing works
Measuring Structural Similarity in Music
Bello, J. P. (2011) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2011.2108287 · Cited by 71 · see citing works
Bello, J. P. (2007) · doi:10.5281/zenodo.1417910 · Cited by 70 · see citing works
Simple: Assessing Music Similarity Using Subsequences Joins.
Silva, D. F., Yeh, C. M., Batista, G. E. A. P. A., et al. (2016) · Scientific Electronic Library Online (São Paulo Research Foundation, Latin American and Caribbean Center on Health Sciences Information, Conselho Nacional de Desenvolvimento Científico e Tecnológico) · doi:10.5281/zenodo.1415011 · Cited by 60 · see citing works
Temporal Pyramid Pooling Convolutional Neural Network for Cover Song Identification
Yu, Z., Xu, X., Chen, X., et al. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/673 · Cited by 59 · see citing works
Self-citationKey-Invariant Convolutional Neural Network Toward Efficient Cover Song Identification
Xu, X., Chen, X., & Yang, D. (2018) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486531 · Cited by 50 · see citing works
Self-citationFusing similarity functions for cover song identification
Chen, N., Li, W., & Xiao, H. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4456-9 · Cited by 49 · see citing works
Identification of versions of the same musical composition by processing audio descriptions
Julià, J. S. (2011) · Cited by 41 · see citing works
Cover song identification with 2D Fourier Transform sequences
Seetharaman, P., & Rafii, Z. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952229 · Cited by 29 · see citing works
BLAST FOR AUDIO SEQUENCES ALIGNMENT: A FAST SCALABLE COVER IDENTIFICATION TOOL
Martin, B. A., Brown, D. G., Hanna, P., et al. (2012) · Cited by 21 · see citing works
Music Shapelets For Fast Cover Song Recognition.
Silva, D. F., Souza, V. M. A., & Batista, G. E. A. P. A. (2015) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.1416235 · Cited by 17 · see citing works
Audio Cover Song Identification using Convolutional Neural NetworkPreprint
Chang, S., Lee, J., Choe, S. K., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.00166 · Cited by 15 · see citing works
Summarizing and Comparing Music Data and Its Application on Cover Song Identification
Silva, D. F., Felipe, & Andrade, N. (2018) · International Symposium/Conference on Music Information Retrieval · doi:10.5072/zenodo.251850 · Cited by 14 · see citing works
A Video Compression-Based Approach To Measure Music Structural Similarity.
Silva, D. F., Papadopoulos, H., Batista, G. E. A. P. A., et al. (2013) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.5281/zenodo.1417086 · Cited by 12 · see citing works
Cheng, Y., Chen, X., Yang, D., et al. (2017) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3077136.3080680 · Cited by 6 · see citing works
Self-citationBlast for Audio Sequences Alignment: a Fast Scalable Cover Identification
Martin, B. A., Brown, D. G., Hanna, P., et al. (2012) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 4 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Deep learning approaches for similarity computation: A survey
Yang, P., Wang, H., Yang, J., Qian, Z., Zhang, Y., & Lin, X. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3422484 · Cited by 28 · see citing works
Kadi, H. A., & Terzić, K. (2023) · Sensors · doi:10.3390/s23052389 · Cited by 19 · see citing works
- Authors
- Jiang, C., Yang, D., & Chen, X.
- Affiliations
- Peking University (CN)
- ORCID
- Jiang, Chaoya
- Venue
- ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2020-05
- Pages
- 26-30
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W3015847222
- Cited by
- 15
- References
- 24
- Citations by year
- 2025: 1 · 2024: 3 · 2023: 4 · 2022: 3 · 2021: 2 · 2020: 2
- FWCI
- 1.72
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Music Technology and Sound Studies
- Social Sciences › Arts and Humanities › Music › Musicology and Musical Analysis
- Keywords
- cover song identification, melody similarity, metric learning, Siamese network, music information retrieval
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
