Filters








202 Hits in 12.2 sec

Chroma Binary Similarity and Local Alignment Applied to Cover Song Identification

J. Serra, E. Gomez, P. Herrera, X. Serra
2008 IEEE Transactions on Audio, Speech, and Language Processing  
Cover song identification is a task whose popularity has increased in the music information retrieval (MIR) community along in the past, as it provides a direct and objective way to evaluate music similarity  ...  We have studied several components of these (such as chroma resolution and similarity, transposition, beat tracking or dynamic time warping constraints), in order to discover which characteristics would  ...  ACKNOWLEDGMENT The authors would like to thank their colleagues and staff at the Music Technology Group (UPF) for their support and encouragement, especially G.  ... 
doi:10.1109/tasl.2008.924595 fatcat:cdfa4tu42zc3veqchoffa4obze

Cover Song Identification with Timbral Shape Sequences [article]

Christopher J. Tralie, Paul Bendich
2015 arXiv   pre-print
By contrast, all other work to date on cover songs exclusively relies on matching note sequences from Chroma derived features.  ...  If we treat MFCC embeddings as point clouds and cast the problem as a relative shape sequence, we are able to correctly identify 42/80 cover songs in the "Covers 80" dataset.  ...  We choose a version of Smith Waterman with diagonal constraints, which was shown to work well for aligning binary cross-similarity matrices for chroma in cover song identification [23] .  ... 
arXiv:1507.05143v1 fatcat:qzn3kdiipbhhpcfodz35xpmyli

Salient Chromagram Extraction Based on Trend Removal for Cover Song Identification

Jin S. SEO
2021 IEICE transactions on information and systems  
We apply the proposed salient chromagram to the sequence-alignment based cover song identification.  ...  This paper proposes a salient chromagram by removing local trend to improve cover song identification accuracy.  ...  The binary similarity matrix is the input to the local sequence alignment by the SW algorithm, which gives the highest score to the best aligned subsequence.  ... 
doi:10.1587/transinf.2020mul0002 fatcat:ugntke6z3vdyfnkdutq7ggajcy

Cover Song Recognition Using Machine Learning Techniques

Andree Silva-Reyes, Fabiola Martínez-Licona, Alma Martínez Licona
2018 Research in Computing Science  
According to the results, a system that integrates a frequency processing on the pitches with beat alignment, a sparse codification and a clustering technique was obtained with correct cover identification  ...  similar to the state of the art results.  ...  The first author would like to thank the Consejo Nacional de Ciencia y Tecnología (CONACYT), Mexico, for a grant given to him by them.  ... 
doi:10.13053/rcs-147-4-1 fatcat:jn3fniknxzeermocj5masfgs5q

Cover Song Identification With Timbral Shape Sequences

Christopher J. Tralie, Paul Bendich
2015 Zenodo  
This is similar in spirit to the approximate nearest neighbors schemes proposed in [28] for large scale cover song identification, and we could adapt their sparse Smith Waterman algorithm to our problem  ...  In addition to the Covers 80 benchmark, we apply our cover songs score to a recent popular music controversy, the "Blurred Lines" controversy [16] .  ... 
doi:10.5281/zenodo.1416824 fatcat:q4pucwlylbdpxk6cftzqe3p5c4

Blast For Audio Sequences Alignment: A Fast Scalable Cover Identification Tool

Benjamin Martin 0001, Daniel G. Brown 0001, Pierre Hanna, Pascal Ferraro
2012 Zenodo  
Thus, we first computed on both TSD and MSD local alignments between cover songs using the local transposition variant described in 3.2.2.  ...  From every cover class in TSD, we computed alignments of each member to the rest of the class and to confusing songs.  ... 
doi:10.5281/zenodo.1417686 fatcat:2vv62azxtvb7vldkw4umm6d2iq

Large-Scale Cover Song Identification Using Chord Profiles

Maksim Khadkevich, Maurizio Omologo
2013 Zenodo  
This suggests that using alternative chroma feature sets to represent a song can lead to an improvement in chord recognition rate, and as a consequence in cover song identification performance.  ...  In this paper, we propose an approach to large-scale cover song identification using chord progressions and chord profiles.  ... 
doi:10.5281/zenodo.1415844 fatcat:5dheqqywkfeonpgoyf2zm7rbdq

Pairwise Similarity Normalization Based on a Hubness Score for Improving Cover Song Retrieval Accuracy

Jin S. SEO
2022 IEICE transactions on information and systems  
A hubness-score based normalization of the pairwise similarity is proposed for the sequence-alignment based cover song retrieval.  ...  Experiments on two cover song datasets confirm that the proposed similarity normalization improves the cover song retrieval accuracy.  ...  The binary similarity matrix is the input to the local sequence alignment by SW algorithm, which gives the highest score to the best aligned subsequence.  ... 
doi:10.1587/transinf.2021edl8075 fatcat:np4m3hvqwbespkxjj5bcwps4du

Audio Cover Song Identification using Convolutional Neural Network [article]

Sungkyun Chang, Juheon Lee, Sang Keun Choe, Kyogu Lee
2020 arXiv   pre-print
Most previous studies extract the feature vectors that characterize the cover song relation from a pair of songs and used it to compute the (dis)similarity between the two songs.  ...  In this paper, we propose a new approach to cover song identification using a CNN (convolutional neural network).  ...  Acknowledgments This work was supported by Kakao and Kakao Brain corporations.  ... 
arXiv:1712.00166v2 fatcat:rdga2rsglnandptqbbexjl77za

An audio fingerprinting system for live version identification using image processing techniques

Zafar Rafii, Bob Coover, Jinyu Han
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Suppose that you are at a music festival checking on an artist, and you would like to quickly know about the song that is being played (e.g., title, lyrics, album, etc.).  ...  Compact fingerprints are derived using a logfrequency spectrogram and an adaptive thresholding method, and template matching is performed using the Hamming similarity and the Hough Transform.  ...  Cover identification systems are designed to capture the melodic similarity while being robust to the other musical aspects [9] .  ... 
doi:10.1109/icassp.2014.6853675 dblp:conf/icassp/RafiiCH14 fatcat:hbqeyqqlqbe73olydeyil6vqle

Audio Content-Based Music Retrieval

Peter Grosche, Meinard Müller, Joan Serrà, Marc Herbstritt
2012 Dagstuhl Publications  
Such strategies can be loosely classified according to their specificity, which refers to the degree of similarity between the query and the database documents.  ...  Using a classification scheme based on specificity and granularity, we identify various classes of retrieval scenarios, which comprise audio identification, audio matching, and version identification.  ...  Acknowledgment We would like to express our gratitude to Christian Dittmar, Emilia Gómez, Frank Kurth, and Markus Schedl for their helpful and constructive feedback.  ... 
doi:10.4230/dfu.vol3.11041.157 dblp:conf/dagstuhl/GroscheMS12 fatcat:ig3p6d4ukrggpeod2altxt4iuy

Early Mfcc And Hpcp Fusion For Robust Cover Song Identification

Christopher J. Tralie
2017 Zenodo  
sets before creating a binary cross-similarity matrix (CSM) and applying Smith Waterman.  ...  Most work on automatic cover song identification to date has focused on estimating and matching note-based features such as chord estimates [1] , chroma [8, 11] , harmonic pitch class profiles (HPCP)  ... 
doi:10.5281/zenodo.1417331 fatcat:hal2s2pjxrdhzj6xjfwuhnpyyy

Combining Features For Cover Song Identification

Julien Osmalskyj, Peter Foster, Simon Dixon, Jean-Jacques Embrechts
2015 Zenodo  
In this paper, we make a distinction between cover song retrieval and cover song identification.  ...  A cover song identification system may therefore be conceived as measuring the similarity between two songs to classify them into a similar or a dissimilar class.  ... 
doi:10.5281/zenodo.1417295 fatcat:4leomqbxeje75kdginehqbhrk4

Simple: Assessing Music Similarity Using Subsequences Joins

Diego Furtado Silva, Chin-Chia Michael Yeh, Gustavo E. A. P. A. Batista, Eamonn J. Keogh
2016 Zenodo  
Acknowledgements: The authors would like to thank FAPESP by the grants #2013/26151-5 and #2015/07628-0 and CNPq by the grants #303083/2013-1 and #446330/2014-0, and NSF by the grant IIS 1510741.  ...  A widely used method for music similarity proposes the use of a binary distance function to compare chroma-based features followed by a dynamic programming local alignment [15] .  ...  Algorithms that search for local similarities have been successfully used to provide structural invariance to the cover song identification task.  ... 
doi:10.5281/zenodo.1415011 fatcat:du2wzbkccfhbtkdkkobnss3cta

Slides for the PhD defence of MIRages: an account of music audio extractors, semantic description and context-awareness, in the three ages of MIR

Perfecto Herrera
2018 Zenodo  
Chroma binary similarity and local alignment applied to cover song identification.  ...  "Chroma binary similarity and local alignment applied to cover song identification".  ...  (2013) (2014) (2015) • Creative systems to enhance music creativity (not for the sake of showing creativity) • Evaluation issues  ... 
doi:10.5281/zenodo.2527496 fatcat:ext24euysvbdrefz2xhyrnkgqi
« Previous Showing results 1 — 15 out of 202 results