Filters








6,994 Hits in 6.7 sec

A Game-Based Approach For Collecting Semantic Annotations Of Music

Douglas Turnbull, Ruoran Liu, Luke Barrington, Gert R. G. Lanckriet
2007 Zenodo  
Yazdani for helpful comments. We also thank everyone who played and provided feedback on Listen Game. This work is supported by NSF IGERT DGE-0333451 and NSF grant DMS-MSPA 062540922.  ...  Developing human computation games for annotating music is a useful approach for collecting semantic information.  ...  COLLECTING MUSIC ANNOTATIONS A supervised learning approach to semantic music annotation and retrieval requires a large corpus of song-word associations.  ... 
doi:10.5281/zenodo.1416464 fatcat:dsiivuk4gjhi3awymuvdk7mvxi

Five Approaches To Collecting Tags For Music

Douglas Turnbull, Luke Barrington, Gert R. G. Lanckriet
2008 Zenodo  
ACKNOWLEDGEMENTS We would like to thank our anonymous reviewers who had a large impact on this paper. This work is supported by NSF IGERT DGE-0333451 and NSF grant DMS-MSPA 062540922.  ...  In Section 3, we describe one implementation of a system for each approach and evaluate its performance on a tag-based music retrieval task.  ...  COMBINING SOURCES OF TAGS While the purpose of this paper is to compare various approaches for collecting tags for music, our ultimate goal is to combine these approaches in order to create a more powerful  ... 
doi:10.5281/zenodo.1416803 fatcat:3qzgudbreba3hccjiaw63fpjpm

Game-powered machine learning

L. Barrington, D. Turnbull, G. Lanckriet
2012 Proceedings of the National Academy of Sciences of the United States of America  
We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the "wisdom of the crowds."  ...  Herd It, an online music annotation game, collects reliable examples of how humans use semantic tags to describe music.  ... 
doi:10.1073/pnas.1014748109 pmid:22460786 pmcid:PMC3340027 fatcat:aqwwiculobdtbbjmhphvseipvy

Improving automatic music tag annotation using stacked generalization of probabilistic SVM outputs

Steven R. Ness, Anthony Theocharis, George Tzanetakis, Luis Gustavo Martins
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
We describe how stacked generalization can be used to improve the performance of a state-of-the-art automatic tag annotation system for music based on audio content analysis and report results on two publicly  ...  Personalized music recommendation systems such as Last.fm and Pandora rely on manual annotations (tags) as a mechanism for querying and navigating large music collections.  ...  Games with a purpose are an exciting new way of collecting tags for a variety of multimedia annotation tasks [20] by harnessing volunteer users who perform the annotation as part of casual gaming.  ... 
doi:10.1145/1631272.1631393 dblp:conf/mm/NessTTM09 fatcat:iaqqozzb3bgqti4tembvgj742u

From Improved Auto-Taggers to Improved Music Similarity Measures [chapter]

Klaus Seyerlehner, Markus Schedl, Reinhard Sonnleitner, David Hauger, Bogdan Ionescu
2014 Lecture Notes in Computer Science  
Intuitively music similarity measures based on auto-tags should profit from the improvement of the quality of the underlying audio tag predictors.  ...  Our results suggest a straight forward way to further improve content-based music similarity measures by improving the underlying auto-taggers.  ...  This huge dataset contains 21642 songs annotated with 188 tags. The tags were collected by a music and sound annotation game, the TagATune 4 game.  ... 
doi:10.1007/978-3-319-12093-5_11 fatcat:pd4k6qa3xve4hjz7emjsey2j2q

Semantic annotation of digital music

Fazilatur Rahman, Jawed Siddiqi
2012 Journal of computer and system sciences (Print)  
Several potential multimedia ontologies have been explored and a music annotation ontology, named mpeg-7Music, has been designed so that it can be used as a backbone for annotating music items.  ...  The current trend of searching for music by means of music consumers' keywords/tags is unable to provide satisfactory search results.  ...  But, a gaming approach needs to overcome the challenge of superficial tags applied by non-fans and collecting weak labels.  ... 
doi:10.1016/j.jcss.2011.10.010 fatcat:f7jmhdmvkzfnrcb2dg7zri5f5e

Learning to Tag from Open Vocabulary Labels [chapter]

Edith Law, Burr Settles, Tom Mitchell
2010 Lecture Notes in Computer Science  
We focus on the domain of tagging music clips, and demonstrate our results using data collected with a human computation game called TagATune.  ...  In this work, we present a new approach that organizes these noisy tags into well-behaved semantic classes using topic modeling, and learn to predict tags accurately using a mixture of topic classes.  ...  We gratefully acknowledge support for this work from a Microsoft Graduate Fellowship and DARPA under contract AF8750-09-C-0179.  ... 
doi:10.1007/978-3-642-15883-4_14 fatcat:77jx4mrxbrfuzgcjuzh7uvopri

Crowdsourcing Emotions in Music Domain

Erion Çano, Maurizio Morisio
2017 International Journal of Artificial Intelligence & Applications  
We also share our own experience, illustrating the steps we followed using tags collected from Last.fm for the creation of two music mood datasets which are rendered public.  ...  Recent crowdsourcing approaches such as harvesting social tags, design of collaborative games and web services or the use of Mechanical Turk, are becoming popular in the literature.  ...  Computational resources were provided by HPC@POLITO 11 , a project of Academic Computing within the Department of Control and Computer Engineering at Politecnico di Torino.  ... 
doi:10.5121/ijaia.2017.8403 fatcat:qziofuxemfa5jb56pqr34dqvvq

Semantic Annotation and Retrieval of Music and Sound Effects

Douglas Turnbull, Luke Barrington, David Torres, Gert Lanckriet
2008 IEEE Transactions on Audio, Speech, and Language Processing  
We collect a data set of 1700 human-generated annotations that describe 500 Western popular music tracks.  ...  We present a computer audition system that can both annotate novel audio tracks with semantically meaningful words and retrieve relevant tracks from a database of unlabeled audio content given a text-based  ...  ACKNOWLEDGMENT The authors would like to thank A. Chan, A. Cont, G. W. Cottrell, S. Dubnov, C. Elkan, L. Saul, N. Vasconcelos, and our anonymous reviewers for their helpful comments.  ... 
doi:10.1109/tasl.2007.913750 fatcat:6iqzxwufg5fp3eus6ghhm424hi

State Of The Art Report: Music Emotion Recognition: A State Of The Art Review

Youngmoo E. Kim, Erik M. Schmidt, Raymond Migneco, Brandon G. Morton, Patrick Richardson, Jeffrey J. Scott, Jacquelin A. Speck, Douglas Turnbull
2010 Zenodo  
A review of methods for emotion data collection for music is also a subject of this paper.  ...  HUMAN ANNOTATION A survey is a straightforward technique for collecting information about emotional content in music.  ... 
doi:10.5281/zenodo.1417945 fatcat:ftuitmsyijeybivecedowng2pi

Enabling Embodied Analogies in Intelligent Music Systems [article]

Fabio Paolizzo
2017 arXiv   pre-print
Main tasks include: (1) adapting wisdom-of-the-crowd approaches to embodiment in music and dance performance to create a dataset of music and music lyrics that covers a variety of emotions, (2) applying  ...  The present methodology is aimed at cross-modal machine learning and uses multidisciplinary tools and methods drawn from a broad range of areas and disciplines, including music, systematic musicology,  ...  In the last few years, collection of ground truth for mood labels has been increasingly carried out by using "games-with-a-purpose" [F 22] [23] , as based on the "wisdom of the crowds" phenomenon [24  ... 
arXiv:1712.00334v1 fatcat:gasuudyw75gxbk35c35dfy5gem

Using Artist Similarity To Propagate Semantic Information

Joon Hee Kim, Brian Tomasik, Douglas Turnbull
2009 Zenodo  
Following their approach, we collect a set of social tags (represented as a tag annotation vector t a ) for each artist a from Last.fm.  ...  Turnbull et al. suggest that there are five general distinct approaches to annotating music with tags: conducting a survey (e.g., Pandora), harvesting social tags (e.g., Last.fm), playing annotation games  ... 
doi:10.5281/zenodo.1416509 fatcat:3ugls7gkercrfgtibhdzioswm4

Leveraging Microblogs for Spatiotemporal Music Information Retrieval [chapter]

Markus Schedl
2013 Lecture Notes in Computer Science  
We present results of text data mining experiments for music retrieval, analyzing microblogs gathered from November 2011 to September 2012 to infer music listening patterns all around the world.  ...  The findings of our study will help improve music retrieval and recommendation systems in that it will allow to incorporate geospatial and cultural information into models for music retrieval, which has  ...  Conclusion and Outlook Based on a microblog collection covering 11 months, we presented an approach to annotate tweets with music artist/track names, semantic tags, and geographic data.  ... 
doi:10.1007/978-3-642-36973-5_87 fatcat:4hid3uaekzgd7ia2pr4mfpcziy

Constructing the Semantic Information Model using A Collective Intelligence Approach

Kigon Lyu
2011 KSII Transactions on Internet and Information Systems  
In this paper, we propose a collective intelligence approach of Games With A Purpose (GWAP) to collect various semantic resources, such as words and word-senses.  ...  Our proposal to collect semantic resources from the collective intelligence approach of GWAP (our FunWords) and to weight their semantic relationship can help construct the semantic information model or  ...  The GWAP approach has been shown to be widely used in various parts, such as image tagging [13] , music annotation [7] and common-sense collection [5] .  ... 
doi:10.3837/tiis.2011.10.001 fatcat:lytoindlp5evvcl2f4xlwsmtqm

Audio-Based Distributional Semantic Models For Music Auto-Tagging And Similarity Measurement

Ioannis Karamanolakis, Elias Iosif, Athanasia Zlatintsi, Aggelos Pikrakis, Alexandros Potamianos
2018 Zenodo  
Publication in the conference proceedings of Multi-Learn, Kos island, Greece, 2017  ...  The use of semantic tags for music similarity measurement is proposed in [7] , where each song is represented by a Semantic Multinomial Distribution over a vocabulary of tags.  ...  In addition, similarity data have been collected from the TagATune game [27] .  ... 
doi:10.5281/zenodo.1160326 fatcat:deptqqmy7jbrbk5d4c7ibjpwfm
« Previous Showing results 1 — 15 out of 6,994 results