4,138 Hits in 7.7 sec

A Filter-And-Refine Indexing Method For Fast Similarity Search In Millions Of Music Tracks

Dominik Schnitzer, Arthur Flexer, Gerhard Widmer
2009 Zenodo  
CONCLUSIONS We have described a filter-and-refine method for fast approximate music similarity search in large collections.  ...  A prototype implementation of our method handling 2.5 million tracks is able to answer music similarity queries in about half a second on a standard desktop CPU.  ... 
doi:10.5281/zenodo.1417830 fatcat:hn2bjbteanbwlgck524y4h5lx4

A fast audio similarity retrieval method for millions of music tracks

Dominik Schnitzer, Arthur Flexer, Gerhard Widmer
2010 Multimedia tools and applications  
We present a filter-and-refine method to speed up nearest neighbor searches with the Kullback-Leibler divergence for multivariate Gaussians.  ...  Overall the method accelerates the search for similar music pieces by a factor of 10-30 and yields high recall values of 95-99% compared to a standard linear search.  ...  Acknowledgements This research is supported by the Austrian Research Fund (FWF) under grant L511-N15, and by the Austrian Research Promotion Agency (FFG) under project number 815474-BRIDGE.  ... 
doi:10.1007/s11042-010-0679-8 fatcat:bjqi4ujejbgtlm4b4uzhaxz4fa

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

Benjamin Martin 0001, Daniel G. Brown 0001, Pierre Hanna, Pascal Ferraro
2012 Zenodo  
A practical way of indexing the search space is to fix a seed length N , and index every N -length substring (or words) of every sequence of the dataset in a fast access data structure.  ...  Facing a similar challenge, bioinformatics researchers developed a fast heuristic-based search tool dedicated to efficient indexing for local alignment.  ... 
doi:10.5281/zenodo.1417686 fatcat:2vv62azxtvb7vldkw4umm6d2iq

Investigating Music Collections at Different Scales with AudioDB

Christophe Rhodes, Tim Crawford, Michael Casey, Mark d'Inverno
2010 Journal of New Music Research  
In this paper, we consider a number of different use cases for content-based similarity search, at scales ranging between a detailed investigation of a single track to searching for fragments of a track  ...  against a collection of millions of media items.  ...  the Artists Without a Label collection.  ... 
doi:10.1080/09298215.2010.516832 fatcat:qvm4o3xbvnhsrduq5yaz2yc5d4

Incorporating Cultural Representations of Features Into Audio Music Similarity Estimation

Kris West, Stephen Cox
2010 IEEE Transactions on Audio, Speech, and Language Processing  
Conventional methods of audio music search use distance measures between features derived from the audio for this task.  ...  for and the utility of effective applications for organising, browsing and searching music collections and generating playlists from them.  ...  The challenge for music similarity estimation techniques is the building of efficient scalable indexes, which would facilitate the indexing and search of 'industrial sized' collections (500 000 to 3 000  ... 
doi:10.1109/tasl.2009.2025533 fatcat:corsnvvzbvbvtcmelvgrstygaq

Character index

2011 2011 IEEE International Conference on Multimedia and Expo  
doi:10.1109/icme.2011.6011827 fatcat:wjy7yvkmvbbf3hj4wbyjapx5gu

Content-Based Music Information Retrieval: Current Directions and Future Challenges

M.A. Casey, R. Veltkamp, M. Goto, M. Leman, C. Rhodes, M. Slaney
2008 Proceedings of the IEEE  
Some of the music collections available are approaching the scale of ten million tracks and this has posed a major challenge for searching, retrieving, and organizing music content.  ...  resulted in many proposed algorithmic and methodological solutions to music search using content-based methods.  ...  Scaling Content-Based Search to Millions of Tracks Pandora is an example of a working MIR system. It is a popular music service that has a large user base.  ... 
doi:10.1109/jproc.2008.916370 fatcat:ynpw7lyf6fchfdzzl5jll22cee

Earth mover's distance based similarity search at scale

Yu Tang, Leong Hou U, Yilun Cai, Nikos Mamoulis, Reynold Cheng
2013 Proceedings of the VLDB Endowment  
Still, EMD calculations in the refinement step remain the bottleneck of the whole similarity search process.  ...  In this paper, we focus on optimizing the refinement phase of EMD-based similarity search by (i) adapting an efficient min-cost flow algorithm (SIA) for EMD computation, (ii) proposing a dynamic distance  ...  In this work, we use SIA as a module for computing the EMD between two histograms p and q in the refinement step of similarity search, due to its efficiency and scalability to the number of histogram bins  ... 
doi:10.14778/2732240.2732249 fatcat:jqidwcrz4nf47oq6en7sy2sewy

Audio-based Musical Version Identification: Elements and Challenges [article]

Furkan Yesiler, Guillaume Doras, Rachel M. Bittner, Christopher J. Tralie, Joan Serrà
2021 arXiv   pre-print
In this article, we aim to provide a review of the key ideas and approaches proposed in 20 years of scientific literature around musical version identification (VI) research and connect them to current  ...  To appreciate two decades of novel ideas in VI research and to facilitate building better systems, we now review some of the successful concepts and applications proposed in the literature and study their  ...  Both lightweight input features and fast indexing yielded efficient lookup times (as fast as a few seconds on a one million track corpus) but exhibited poor accuracy compared to previous systems.  ... 
arXiv:2109.02472v1 fatcat:tbbd66yq2vcz3ahc4z5ymethgi

Mining Music from Large-Scale, Peer-to-Peer Networks

Y Shavitt, E Weinsberg, U Weinsberg
2011 IEEE Multimedia  
For this project, we studied the musical content shared by users in Gnutella, 5 then built a song-similarity graph, where the similarity between two songs is based on the number of users that share the  ...  Because this article focuses on MIR data, we identified files that are music-related by indexing only the files with a music-related suffix (MP3, WMA, FLAC, M4P, and M4A).  ...  Acknowledgments We thank Tomer Tankel for providing the data used in this article, and sharing valuable ideas for its successful analysis.  ... 
doi:10.1109/mmul.2011.13 fatcat:pmzvyu3sanfb7h2wt5txpaux3a

Music Information Retrieval: Recent Developments and Applications

Markus Schedl, Emilia Gómez, Julián Urbano
2014 Foundations and Trends in Information Retrieval  
These in turn enable a wide variety of music retrieval tasks, such as semantic music search or music identification ("query by example").  ...  We first elaborate on well-established and proven methods for feature extraction and music indexing, from both the audio signal and contextual data sources about music items, such as web pages or collaborative  ...  The authors would further like to thank Masataka Goto, Mohamed Sordo, and Edith Law for granting permission to include their visual material in this survey, and Juan J.  ... 
doi:10.1561/1500000042 fatcat:c5tjdcy3xrfqvp6isnktbr6lpy

Development of an Effective Bootleg Videos Retrieval System as a Part of Content-Based Video Search Engine

Ahmad Sedky Adly, Islam Hegazy, Taha Elarif, M. S. Abdelwahab
2022 International Scientific Journal of Computing  
In this paper, a novel and effective technique for a content-based video search engine with effective detection of bootleg videos is evaluated on a large-scale video index dataset of 1088 video records  ...  Many research studies in content-based video search engines are concerned with content-based video queries retrieval where a query by example is sent to retrieve a list of visually similar videos.  ...  to process and search for similarities inside the video index dataset.  ... 
doi:10.47839/ijc.21.2.2590 fatcat:ide3dr3aerarxczzi72laidtdm

Generating suggestions for queries in the long tail with an inverted index

Daniele Broccolo, Lorenzo Marcon, Franco Maria Nardini, Raffaele Perego, Fabrizio Silvestri
2012 Information Processing & Management  
of a full-text query over an inverted index.  ...  By exploiting a weak function for assessing the similarity between the current query and the knowledge base built from historical users' sessions, we re-conduct the suggestion generation phase to the processing  ...  A approach similar to our is represented by the query refinement/substitution technique discussed in (Jones et al., 2006) .  ... 
doi:10.1016/j.ipm.2011.07.005 fatcat:pl7y2q3d4ngw5mo4kt2rtsxqae


Azarias Reda, Yubin Park, Mitul Tiwari, Christian Posse, Sam Shah
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
Metaphor builds on a number of signals and filters that capture several dimensions of relatedness across member search activity.  ...  This paper describes the design, implementation, and deployment of Metaphor, the related search recommendation system on LinkedIn, a professional social networking site with over 175 million members worldwide  ...  Table 3 : 3 Overlap of recommendation signals. The Jaccard index is a statistic for comparing the similarity between sets and is defined as: J(A, B) = |A B| |A B| for sets A and B.  ... 
doi:10.1145/2396761.2396847 dblp:conf/cikm/RedaPTPS12 fatcat:4nttbjperngi5dj46fjtivsswe

Music Recommendation: A multi-faceted approach

Oscar Celma, Xavier Serra
2006 Zenodo  
As a test–bed example, two prototypes have been developed a music search engine and music discovery based on music similarity, and a hybrid music recommender.  ...  This thesis presents the current methods used to recommend music assets, and reviews also some proposals of modelling user's musical preferences.  ...  calculated-for more than 3 millions of tracks.  ... 
doi:10.5281/zenodo.3743108 fatcat:wcfdl34jnzeqtmzjzamjjvdt44
« Previous Showing results 1 — 15 out of 4,138 results