publications

2025

1. OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction

   Pablo Alonso-Jiménez, Pedro Ramoneda, R. Oguz Araz, Andrea Poltronieri, and Dmitry Bogdanov

   In ACM Multimedia Conference (ACMMM), Open Source Track, 2025

   DOI arXiv Bib Code

   @inproceedings{alonso2025omar,
     title = {OMAR-RQ: Open Music Audio Representation Model Trained with Multi-Feature Masked Token Prediction},
     author = {Alonso-Jim{\'e}nez, Pablo and Ramoneda, Pedro and Araz, R. Oguz and Poltronieri, Andrea and Bogdanov, Dmitry},
     booktitle = {ACM Multimedia Conference (ACMMM), Open Source Track},
     year = {2025},
     doi = {10.1145/3746027.3756871},
   }

2. ManyMusic: An Open-Access Music Audio Dataset for Human Experiments on Musical Emotions

   Seung-Goo Kim, Pablo Alonso-Jiménez, Dmitry Bogdanov, and Daniela Sammler

   In Workshop on Human-Centric Music Information Research at ISMIR, 2025

   Bib

   @inproceedings{alonso2025omas,
     title = {{ManyMusic}: An Open-Access Music Audio Dataset for Human Experiments on Musical Emotions},
     author = {Kim, Seung-Goo and Alonso-Jim{\'e}nez, Pablo and Bogdanov, Dmitry and Sammler, Daniela},
     booktitle = {Workshop on Human-Centric Music Information Research at ISMIR},
     year = {2025},
   }

2024

1. Deep Audio Representation Learning for Music Using Weak Supervision

   Pablo Alonso-Jiménez

   Universitat Pompeu Fabra, 2024

   PhD thesis

   DOI Bib Video

   @phdthesis{alonso2024deep,
     author = {Alonso-Jim{\'e}nez, Pablo},
     title = {Deep Audio Representation Learning for Music Using Weak Supervision},
     school = {Universitat Pompeu Fabra},
     year = {2024},
     doi = {10803/692389},
     note = {PhD thesis}
   }

2. Evaluation of Deep Audio Representations for Semantic Sound Similarity

   R. Oguz Araz, Dmitry Bogdanov, Pablo Alonso-Jiménez, and Frederic Font

   In International Conference on Content-Based Multimedia Indexing (CBMI), 2024

   DOI Bib

   @inproceedings{araz2024evaluation,
     title = {Evaluation of Deep Audio Representations for Semantic Sound Similarity},
     author = {Araz, R. Oguz and Bogdanov, Dmitry and Alonso-Jim{\'e}nez, Pablo and Font, Frederic},
     booktitle = {International Conference on Content-Based Multimedia Indexing (CBMI)},
     year = {2024},
     doi = {10.1109/CBMI62980.2024.10859250},
   }

3. Leveraging Pre-trained Autoencoders for Interpretable Prototype Learning of Music Audio

   Pablo Alonso-Jiménez, Leonardo Pepino, Roser Batlle-Roca, Pablo Zinemanas, Dmitry Bogdanov, Xavier Serra, and Martín Rocamora

   In ICASSP Workshop on Explainable AI for Speech and Audio (XAI-SA), 2024

   DOI Bib Supp Video Code

   @inproceedings{alonso2024interpretable,
     author = {Alonso-Jim{\'e}nez, Pablo and Pepino, Leonardo and Batlle-Roca, Roser and Zinemanas, Pablo and Bogdanov, Dmitry and Serra, Xavier and Rocamora, Mart{\'i}n},
     title = {Leveraging Pre-trained Autoencoders for Interpretable Prototype Learning of Music Audio},
     booktitle = {ICASSP Workshop on Explainable AI for Speech and Audio (XAI-SA)},
     year = {2024},
     doi = {10.1109/ICASSPW62465.2024.10669909},
   }

2023

1. mir_ref: A Representation Evaluation Framework for Music Information Retrieval Tasks

   Christos Plachouras, Pablo Alonso-Jiménez, and Dmitry Bogdanov

   In Conference on Neural Information Processing Systems (NeurIPS), Machine Learning for Audio Workshop, 2023

   arXiv Bib Code

   @inproceedings{plachouras2023mirref,
     author = {Plachouras, Christos and Alonso-Jim{\'e}nez, Pablo and Bogdanov, Dmitry},
     title = {mir\_ref: A Representation Evaluation Framework for Music Information Retrieval Tasks},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS), Machine Learning for Audio Workshop},
     year = {2023},
   }

2. Efficient Supervised Training of Audio Transformers for Music Representation Learning

   Pablo Alonso-Jiménez, Xavier Serra, and Dmitry Bogdanov

   In International Society for Music Information Retrieval Conference (ISMIR), 2023

   Awarded DOI arXiv Bib Video Code Website

   Dolby Barcelona Scientific Paper Award (runner-up)

   @inproceedings{alonso2023efficient,
     author = {Alonso-Jim{\'e}nez, Pablo and Serra, Xavier and Bogdanov, Dmitry},
     title = {Efficient Supervised Training of Audio Transformers for Music Representation Learning},
     booktitle = {International Society for Music Information Retrieval Conference (ISMIR)},
     year = {2023},
     doi = {10.5281/zenodo.10265413},
   }

3. Pre-Training Strategies Using Contrastive Learning and Playlist Information for Music Classification and Similarity

   Pablo Alonso-Jiménez, Xavier Favory, Hadrien Foroughmand, Grigoris Bourdalas, Xavier Serra, Thomas Lidy, and Dmitry Bogdanov

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

   DOI arXiv Bib

   @inproceedings{alonso2023pretraining,
     author = {Alonso-Jim{\'e}nez, Pablo and Favory, Xavier and Foroughmand, Hadrien and Bourdalas, Grigoris and Serra, Xavier and Lidy, Thomas and Bogdanov, Dmitry},
     title = {Pre-Training Strategies Using Contrastive Learning and Playlist Information for Music Classification and Similarity},
     booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     year = {2023},
     doi = {10.1109/ICASSP49357.2023.10095058},
   }

4. Multilabel Prototype Generation for data reduction in K-Nearest Neighbour classification

   Jose J. Valero-Mas, Antonio Javier Gallego, Pablo Alonso-Jiménez, and Xavier Serra

   Pattern Recognition, 2023

   DOI Bib

   @article{valero2023multilabel,
     title = {Multilabel Prototype Generation for data reduction in K-Nearest Neighbour classification},
     author = {Valero-Mas, Jose J. and Gallego, Antonio Javier and Alonso-Jim{\'e}nez, Pablo and Serra, Xavier},
     journal = {Pattern Recognition},
     volume = {135},
     pages = {109190},
     year = {2023},
     publisher = {Elsevier},
     doi = {10.1016/j.patcog.2022.109190},
   }

2022

1. Music Representation Learning Based on Editorial Metadata from Discogs

   Pablo Alonso-Jiménez, Dmitry Bogdanov, and Xavier Serra

   In International Society for Music Information Retrieval Conference (ISMIR), 2022

   DOI Bib PDF Video Poster

   @inproceedings{alonso2022discogs,
     author = {Alonso-Jim{\'e}nez, Pablo and Bogdanov, Dmitry and Serra, Xavier},
     title = {Music Representation Learning Based on Editorial Metadata from Discogs},
     booktitle = {International Society for Music Information Retrieval Conference (ISMIR)},
     year = {2022},
     doi = {10.5281/zenodo.7316789},
   }

2. MusAV: a Dataset of Relative Arousal-Valence Annotations for Validation of Audio Models

   Dmitry Bogdanov, Xacier Lizarraga-Seijas, Pablo Alonso-Jiménez, and Xavier Serra

   In International Society for Music Information Retrieval Conference (ISMIR), 2022

   DOI Bib PDF Supp Poster

   @inproceedings{bogdanov2022musav,
     author = {Bogdanov, Dmitry and Lizarraga-Seijas, Xacier and Alonso-Jim{\'e}nez, Pablo and Serra, Xavier},
     title = {{MusAV}: a Dataset of Relative Arousal-Valence Annotations for Validation of Audio Models},
     booktitle = {International Society for Music Information Retrieval Conference (ISMIR)},
     year = {2022},
     doi = {10.5281/zenodo.7316746},
   }

3. Ambiguity Modelling with Label Distribution Learning for Music Classification

   Morgan Buisson, Pablo Alonso-Jiménez, and Dmitry Bogdanov

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022

   DOI Bib PDF

   @inproceedings{buisson2022ambiguity,
     author = {Buisson, Morgan and Alonso-Jim{\'e}nez, Pablo and Bogdanov, Dmitry},
     title = {Ambiguity Modelling with Label Distribution Learning for Music Classification},
     booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     year = {2022},
     doi = {10.1109/ICASSP43922.2022.9747467},
   }

2021

1. Audio and Music Analysis on the Web using Essentia.js

   Albin A. Correya, Jorge Marcos-Fernández, Luis Joglar-Ongay, Pablo Alonso-Jiménez, Xavier Serra, and Dmitry Bogdanov

   Transactions of the International Society for Music Information Retrieval, 2021

   DOI Bib PDF

   @article{correya2021essentiajs,
     author = {Correya, Albin A. and Marcos-Fern{\'a}ndez, Jorge and Joglar-Ongay, Luis and Alonso-Jim{\'e}nez, Pablo and Serra, Xavier and Bogdanov, Dmitry},
     title = {Audio and Music Analysis on the Web using {Essentia.js}},
     journal = {Transactions of the International Society for Music Information Retrieval},
     year = {2021},
     doi = {10.5334/tismir.111},
   }

2. Essentia TensorFlow Models for Audio and Music Processing on the Web

   Albin A. Correya, Pablo Alonso-Jiménez, Jorge Marcos-Fernández, Xaver Serra, and Dmitry Bogdanov

   In Web Audio Conference (WAC), 2021

   Awarded Bib PDF Video

   Best paper award

   @inproceedings{correya2021essentiajt,
     author = {Correya, Albin A. and Alonso-Jim{\'e}nez, Pablo and Marcos-Fern{\'a}ndez, Jorge and Serra, Xaver and Bogdanov, Dmitry},
     title = {{Essentia} {TensorFlow} Models for Audio and Music Processing on the Web},
     booktitle = {Web Audio Conference (WAC)},
     year = {2021},
   }

2020

1. Deep embeddings with Essentia Models

   Pablo Alonso-Jiménez, Dmitry Bogdanov, and Xavier Serra

   In International Society for Music Information Retrieval Conference (ISMIR), 2020

   Late-breaking demo

   Bib PDF Poster

   @inproceedings{alonso2020deep,
     author = {Alonso-Jim{\'e}nez, Pablo and Bogdanov, Dmitry and Serra, Xavier},
     title = {Deep embeddings with {Essentia} Models},
     booktitle = {International Society for Music Information Retrieval Conference (ISMIR)},
     year = {2020},
     note = {Late-breaking demo},
   }

2. TensorFlow Audio Models in Essentia

   Pablo Alonso-Jiménez, Dmitry Bogdanov, Jordi Pons, and Xavier Serra

   In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020

   DOI arXiv Bib Video Slides Website

   @inproceedings{alonso2020tensorflow,
     author = {Alonso-Jim{\'e}nez, Pablo and Bogdanov, Dmitry and Pons, Jordi and Serra, Xavier},
     title = {{TensorFlow} Audio Models in Essentia},
     booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     year = {2020},
     doi = {10.1109/ICASSP40776.2020.9054688},
   }

2019

1. Automatic Detection of Audio Problems for Quality Control in Digital Music Distribution

   Pablo Alonso-Jiménez, Luis Joglar-Ongay, Xavier Serra, and Dmitry Bogdanov

   In Convention of the Audio Engineering Society (AES), 2019

   Bib PDF

   @inproceedings{alonso2019audioqc,
     author = {Alonso-Jim{\'e}nez, Pablo and Joglar-Ongay, Luis and Serra, Xavier and Bogdanov, Dmitry},
     title = {Automatic Detection of Audio Problems for Quality Control in Digital Music Distribution},
     booktitle = {Convention of the Audio Engineering Society (AES)},
     year = {2019},
   }

2017

1. Cross-Lingual Voice Conversion with Non-Parallel Data

   Pablo Alonso-Jiménez

   2017

   Master thesis

   DOI Bib Website

   @mastersthesis{alonso2017voiceconversion,
     author = {Alonso-Jim{\'e}nez, Pablo},
     title = {Cross-Lingual Voice Conversion with Non-Parallel Data},
     year = {2017},
     note = {Master thesis},
     doi = {10.5281/zenodo.1117153},
   }

2016

1. Development of a Noise Monitoring Service Based on Acoustic Vector Sensors

   Pablo Alonso-Jiménez

   2016

   Undergraduate thesis

   Bib PDF

   @bachelorsthesis{alonso2016noisemonitoring,
     author = {Alonso-Jim{\'e}nez, Pablo},
     title = {Development of a Noise Monitoring Service Based on Acoustic Vector Sensors},
     year = {2016},
     note = {Undergraduate thesis},
   }