Filters








7 Hits in 1.6 sec

The AcousticBrainz Genre Dataset: Multi-Source, Multi-Level, Multi-Label, and Large-Scale

Dmitry Bogdanov, Alastair Porter, Hendrik Schreiber, Julián Urbano, Sergio Oramas
2019 Zenodo  
With this dataset, we hope to contribute to developments in content-based music genre recognition as well as cross-disciplinary studies on genre metadata analysis.  ...  This paper introduces the AcousticBrainz Genre Dataset, a large-scale collection of hierarchical multi-label genre annotations from different metadata sources.  ...  We also thank tagtraum industries for providing the Tagtraum genre annotations.  ... 
doi:10.5281/zenodo.3527818 fatcat:xkc345fzgjduvblwkrv3dhbaxe

Bayes-Optimal Hierarchical Multilabel Classification

Wei Bi, Jame T. Kwok
2015 IEEE Transactions on Knowledge and Data Engineering  
This paper summarizes our contribution (team DBIS) to the Acous-ticBrainz Genre Task: Content-based music genre recognition from multiple sources as part of MediaEval 2017.  ...  We utilize a hierarchical set of multilabel classifiers to predict genres and subgenres and rely on a voting scheme to predict labels across datasets.  ...  INTRODUCTION In the MediaEval AcousticBrainz Genre Task, the goal is to classify tracks into main and subgenres, using content-based features computed with Essentia [2] and collected by AcousticBrainz  ... 
doi:10.1109/tkde.2015.2441707 fatcat:q7wzvifruzhztf5agozmjyez7m

Music Classification: Beyond Supervised Learning, Towards Real-world Applications [article]

Minz Won, Janne Spijkervet, Keunwoo Choi
2021 Zenodo  
In this book, we focus on the more modern history of music classification since the popularization of deep learning in mid 2010s.  ...  NOTE: We strongly recommend visiting https://music-classification.github.io/tutorial/ and use a web version of the book.  ...  When the classification task has multiple labels, we need to aggregate multiple ROC-AUC scores and PR-AUC scores. In scikit-learn library, there is an option called average.  ... 
doi:10.5281/zenodo.5703780 fatcat:vpjixx4nmfaqtipf3ytuu7srwa

Knowledge Extraction And Representation Learning For Music Recommendation And Classification

Sergio Oramas, Xavier Serra
2017 Zenodo  
Next, we focus on learning new data representations from multimodal content using deep learning architectures, addressing the problems of cold-start music recommendation and multi-label music genre classification  ...  To this end, we first focus on the problem of linking music-related texts with online knowledge repositories and on the automated construction of music knowledge bases.  ...  Finally, the C@merata task (Sutcliffe et al., 2016 (Sutcliffe et al., , 2015 , part of the MediaEval evaluation campaigns from 2013 to 2017, is focused on music Question & Answering (Q&A) systems.  ... 
doi:10.5281/zenodo.1048497 fatcat:kdh5jhvocbh3riwln6n2f756su

Knowledge Extraction And Representation Learning For Music Recommendation And Classification

Sergio Oramas, Xavier Serra
2017 Zenodo  
Next, we focus on learning new data representations from multimodal content using deep learning architectures, addressing the problems of cold-start music recommendation and multi-label music genre classification  ...  To this end, we first focus on the problem of linking music-related texts with online knowledge repositories and on the automated construction of music knowledge bases.  ...  Finally, the C@merata task (Sutcliffe et al., 2016 (Sutcliffe et al., , 2015 , part of the MediaEval evaluation campaigns from 2013 to 2017, is focused on music Question & Answering (Q&A) systems.  ... 
doi:10.5281/zenodo.1100973 fatcat:yfpmc6qxbbakjp6qzvywyoaoci

Music Classification: Beyond Supervised Learning, Towards Real-world Applications [article]

Minz Won, Janne Spijkervet, Keunwoo Choi
2021 Zenodo  
In this book, we focus on the more modern history of music classification since the popularization of deep learning in mid 2010s.  ...  NOTE: We strongly recommend visiting https://music-classification.github.io/tutorial/ and use a web version of the book.  ...  When the classification task has multiple labels, we need to aggregate multiple ROC-AUC scores and PR-AUC scores. In scikit-learn library, there is an option called average.  ... 
doi:10.5281/zenodo.5703779 fatcat:ggefiongcnb5boahjsz4lgiuz4

Searching for musical features using natural language queries: the C@merata evaluations at MediaEval

Richard Sutcliffe, Eduard Hovy, Tom Collins, Stephen Wan, Tim Crawford, Deane L. Root
2018 Language Resources and Evaluation  
Experts can usually identify the features in question in music scores but a means of performing this task automatically could be very useful for experts and beginners alike.  ...  Following work on textual question answering over many years as co-organisers of the QA tasks at the Cross Language Evaluation Forum, we decided in 2013 to propose a new type of task where the input would  ...  Oramas et al. (2016c) describes the creation of a dataset of 65,000 albums constructed from multiple sources, namely Amazon reviews, MusicBrainz 19 and AcousticBrainz. 20 Once again, they performed named  ... 
doi:10.1007/s10579-018-9422-2 fatcat:bwzkvrrzajckvmdog7w6l4ds6a