Filters








1,081 Hits in 6.5 sec

How Similar Is Too Similar?: Exploring Users' Perceptions Of Similarity In Playlist Evaluation

Jin Ha Lee
2011 Zenodo  
The objective of this study is to explore one of the potential uses of the AMS evaluation task. One way of using music similarity data is to generate playlists or recommendations for users.  ...  This is also much closer to how users will respond to music playlists in real life.  ... 
doi:10.5281/zenodo.1417125 fatcat:3oy3orwwyvabpk5hioqoosvp4i

Exploring acoustic similarity for novel music recommendation

Derek S Cheng, Thorsten Joachims, Douglas Turnbull
2020 Zenodo  
Secondly, is acoustic similarity a good proxy for how an individual might construct a playlist or recommend music to a friend?  ...  preference, and 3) we identify a subset of acoustic features from the Spotify Web API that is particularly predictive of human similarity judgments.  ...  METHODOLOGY OF STUDY In this section, we describe both how we selected the song tuples and how we designed the user study.  ... 
doi:10.5281/zenodo.4245500 fatcat:ds4234rfzngarexpylpvynonjm

Similarity of Nearest-Neighbor Query Results in Deep Latent Spaces

Philip Tovstogan, Xavier Serra, Dmitry Bogdanov
2022 Zenodo  
Moreover, we perform an online user experiment to compare the perceived track-to-track similarity of the selected evaluated latent spaces.  ...  In those cases, it is possible to use content-based similarity spaces to retrieve the most similar tracks to be recommended based on the reference track.  ...  This work was conducted partially during the internship in Jamendo as part of the MIP-Frontiers project.  ... 
doi:10.5281/zenodo.6573229 fatcat:vaqrgv362baw7oucg2vgtzpkbu

Similarity of Nearest-Neighbor Query Results in Deep Latent Spaces

Philip Tovstogan, Xavier Serra, Dmitry Bogdanov
2022 Zenodo  
Moreover, we perform an online user experiment to compare the perceived track-to-track similarity of the selected evaluated latent spaces.  ...  In those cases, it is possible to use content-based similarity spaces to retrieve the most similar tracks to be recommended based on the reference track.  ...  This work was conducted partially during the internship in Jamendo as part of the MIP-Frontiers project.  ... 
doi:10.5281/zenodo.6797867 fatcat:m5aumfmvgnfztbiwwy7ns65sqq

Exploring Music Similarity With Acousticbrainz

Philip Tovstogan, Dmitry Bogdanov, Alastair Porter
2018 Zenodo  
However, subjective evaluation of most similarity metrics that are introduced in the research is usually performed with limited number of participants due to nature of experiments.  ...  Using user feedback as the evaluation source we are able to compare performance of various algorithms at large scale.  ...  Thus the problem that we address in this thesis is: how can we take advantage of large-scale data available in AB to perform an evaluation of state-of-the-art similarity algorithms and metrics?  ... 
doi:10.5281/zenodo.1479768 fatcat:bmljiqt3tnh6zbfbhcehgvjx5m

Ambient music experience in real and virtual worlds using audio similarity

Jakob Frank, Thomas Lidy, Ewald Peiszer, Ronald Genswaider, Andreas Rauber
2008 Proceeding of the 1st ACM international workshop on Semantic ambient media experiences - SAME '08  
Other interfaces support the creation of playlists via artist or album selection, up to more artistic installation of sound environments that users can navigate through.  ...  Sound and, specifically, music is a medium that is used for a wide range of purposes in different situations in very different ways.  ...  This will be broken down into a set of individual user studies on playlist generation and evaluation, followed by group-based user studies on joint playlist generation.  ... 
doi:10.1145/1461912.1461915 dblp:conf/mm/FrankLPGR08 fatcat:yolruibkd5czvbxmtto3x5mf3y

Learning music similarity from relative user ratings

Daniel Wolff, Tillman Weyde
2013 Information retrieval (Boston)  
and optimisation in Music Information Retrieval and for research in music perception and cognition.  ...  evaluation of this approach.  ...  The users of music exploration and recommendation systems have often been neglected by assuming a general consensus on music similarity perception and retrieval criteria.  ... 
doi:10.1007/s10791-013-9229-0 fatcat:6qxuhak54fecdd5cda36u4esam

Beyond Similarity: Relation Embedding with Dual Attentions for Item-based Recommendation [article]

Liang Zhang, Guannan Liu, Junjie Wu
2019 arXiv   pre-print
The key of ICF lies in the similarity measurement between items, which however is a coarse-grained numerical value that can hardly capture users' fine-grained preferences toward different latent aspects  ...  A relational user embedding is then proposed by aggregating the relation embeddings between all purchased items of a user, which not only better characterizes user preferences but also alleviates the data  ...  Since it is too time-consuming to rank all the items for every user during evaluation, we follow the experimental settings in (He et al. 2017 ) which randomly samples 100 negative items of each user and  ... 
arXiv:1911.04099v1 fatcat:5vog6dczs5hklpo5cabaq7zqum

Harvesting microblogs for contextual music similarity estimation: a co-occurrence-based framework

Markus Schedl, David Hauger, Julián Urbano
2013 Multimedia Systems  
We evaluate the approaches on a collection of microblogs crawled from Twitter over a period of 10 months and compare them to standard tf-idf approaches.  ...  As evaluation criteria we use precision and recall in an artist retrieval task as well as rank proximity.  ...  Open Access This article is distributed under the terms of the Creative Commons Attribution License which permits any use, distribution, and reproduction in any medium, provided the original author(s)  ... 
doi:10.1007/s00530-013-0321-5 fatcat:dm7hmwwg5feclhryi74i4gsdlu

Learning music similarity using audio and textual input

Alexander Keijser, Minz Won, Bogdanov
2020 Zenodo  
that encodes information about di˙erent aspects of a song in separate parts of its embedding.  ...  The incredibly large amount of music that is available online nowadays has created a need for powerful retrieval and recommendation algorithms.  ...  Since a couple of years, Spotify offers personalised playlists such as "Discover Weekly" and "Release Radar", helping users to discover new music in the abundance that is available.  ... 
doi:10.5281/zenodo.4091448 fatcat:rnh2xhbro5httkrwv6pjxkkcz4

How Playlist Evaluation Compares to Track Evaluations in Music Recommender Systems

Sophia Hadash, Yu Liang, Martijn C. Willemsen
2019 ACM Conference on Recommender Systems  
In this study, we investigate how individual track evaluation compares to holistic playlist evaluation in music recommender systems, especially how playlist attractiveness is related to individual track  ...  In addition, inclusion of the highest and last track rating (peak-end) is equally good in predicting playlist attractiveness as the inclusion of all track evaluations.  ...  RELATED WORK 2.1 User-centric evaluation in music recommendation User-centric evaluation for recommendation approaches is necessary in order to understand users' perception of the given recommendations  ... 
dblp:conf/recsys/HadashLW19 fatcat:o6bf3n7sabajzcwdsm5hw2m6pe

Incorporating Cultural Representations of Features Into Audio Music Similarity Estimation

Kris West, Stephen Cox
2010 IEEE Transactions on Audio, Speech, and Language Processing  
In fact, this assumed relationship is used to conduct automated pseudo-objective evaluations of the performance of audio music similarity estimators [6], [9]- [11] .  ...  We contend that human perception of musical similarity is correlated with the division of music into culturally defined categories, and such information needs to be included in any useful music similarity  ...  mimic human perception of music similarity, evaluations of performance must be based on the measurement of similarity estimates by humans.  ... 
doi:10.1109/tasl.2009.2025533 fatcat:corsnvvzbvbvtcmelvgrstygaq

Islands Of Gaussians: The Self Organizing Map And Gaussian Music Similarity Features

Dominik Schnitzer, Arthur Flexer, Gerhard Widmer, Martin Gasser
2010 Zenodo  
ACKNOWLEDGMENTS This research is supported by the Austrian Research Fund (FWF) under grants L511-N15, P21247 and the Vienna Science and Technology Fund (WWTF).  ...  In research it is not yet settled how to extract and represent good music similarity features that correspond well with the human perception of general music similarity.  ...  EVALUATION To compare SOMs generated with different approaches, we quantify how well the original neighborhood topology is preserved in a SOM mapping.  ... 
doi:10.5281/zenodo.1415248 fatcat:d3bvl5b3xzbzrhci6pxjo5wyyu

A Probabilistic Model to Combine Tags and Acoustic Similarity for Music Retrieval

Riccardo Miotto, Nicola Orio
2012 ACM Transactions on Information Systems  
With this aim in mind, the article explores a novel music retrieval framework based on combining tags and acoustic similarity through a probabilistic graph-based representation of a collection of songs  ...  One major issue in music information retrieval is how to combine such noisy and heterogeneous information sources in order to improve retrieval effectiveness.  ...  of Padova, Italy.  ... 
doi:10.1145/2180868.2180870 fatcat:o3lg45gku5eojovrv6ptzbpzs4

Searching 100M Images by Content Similarity

Paolo Bolettieri, Fabrizio Falchi, Claudio Lucchese, Yosi Mass, Raffaele Perego, Fausto Rabitti, Michal Shmueli-Scheuer
2009 Italian Research Conference on Digital Library Management Systems  
A desirable feature of such models is that of being both "fully expressive" and "minimal", that is (i) the set of primitives they provide should be capable of describing any information object model and  ...  The DLS is capable of (i) ingesting or importing publication objects, i.e. metadata records and/or payloads, from other domains in the form of "simple" compound objects (digital objects with no relationships  ...  Acknowledgements The authors would like to thank the staff of The European Library Office for their systematic support during the analysis of logs which is reported in the paper. The  ... 
dblp:conf/ircdl/BolettieriFLMPRS09 fatcat:k3n4ffi4bfbwjgyooga22rummq
« Previous Showing results 1 — 15 out of 1,081 results