Dmitry Bogdanov

Senior researcher and software developer at Audio Signal Processing Lab at Music Technology Group, Departament de Tecnologies de la Informació i les Comunicacions, Universitat Pompeu Fabra.

• Address: Roc Boronat, 138, 08018 Barcelona
• Phone: (+34) 935422176
• dmitry.bogdanov@upf.edu
• https://www.linkedin.com/in/dibogdanov/

Research interests

Music information retrieval, sound and music computing, music technology, audio analysis, music metadata, music recommendation, machine learning, deep learning, data mining.

My projects include research and development for Essentia audio analysis library and the large-scale music information retrieval database AcousticBrainz.

Academic background

• PhD in Information, Communication and Audiovisual Technologies at Pompeu Fabra University (2008-2013), Department of Information and Communication Technologies. Thesis: “From music similarity to music recommendation: Computational approaches based on audio features and metadata”.
• Diploma in Applied Mathematics and Informatics at Moscow State University (2001-2006), Faculty of Computational Mathematics and Cybernetics (CMC MSU). Specialization in Software for Computers.

Professional experience

• 2012 – Now - Developer of Essentia and Gaia C++ audio/music analysis libraries
• 2007 – Now - Researcher at Music Technology Group, Pompeu Fabra Universtiy, Barcelona.
• 2003 – 2007 - Researcher and developer at Computing Systems Laboratory, Faculty of Computational Mathematics and Cybernetics, Moscow State University.

Financed projects

• 2022 – Now - AISMA (AI models for Sound and Music Applications). Researcher and developer. Project co-supervision.
• 2020 – Now - Musical AI (Artificial intelligence to support musical experiences: towards a data-driven, human-centred approach). Researcher and developer.
• 2022 – Now - NextCore (Next generation of music monitoring technology, Ministry of Science and Innovation of the Spanish Government, RTC2019-007248-7). Project co-supervision.
• 2022 – Now - Challenges and Opportunities in Music Tech. Researcher.
• 2016 – 2019 - AudioCommons (Technologies for the reuse of open audio content, EC-ICT, H2020–6888382). Researcher and developer.
• 2016 – 2018 - MINGUS (Music Information Gathering, Structuring and Processing for Semantic Audio Applications, Ministerio de Economía y Competividad, TIN2015-69935-P MINECO/FEDER). Researcher and developer.
• 2016 – Now - Maria de Maeztu (Machine learning approaches for structuring large sound and music collections). Researcher and developer.
• 2013 – 2016 - GiantSteps (Seven League Boots for Music Creation and Performance, EC-ICT, FP7-ICT-2013-10 610591). Researcher and developer.
• 2013 – 2015 - SIGMUS (SIGnal Analysis for the Discovery of Traditional MUSic Repertories, Ministerio de Economía y Competividad, TIN2012-36650). Researcher and developer.
• 2007 – 2008 - Pharos (Platform for searcH of Audiovisual Resources across Online Spaces, EC-IST, FP6-45035). Researcher.
• 2004 – 2007 - Financed projects by Moscow State University. Researcher and developer.

R&D supervision for industrial partners

• 2018 – 2022 - Kakao: Music recommendation systems.
• 2018 – 2019 - LaCúpula Music/SonoSuite: Automatic quality assessment and semantic annotation of music audio for digital music distribution systems.
• 2018 – 2019 - Flits: Automatic identification and semantic annotation of music audio in the context of live music concerts.
• 2021 – 2022 - HearDis!: Automatic semantic music annotation for audio branding from audio.

Participation in other R&D industrial projects

• 2022 – Now - VoctroLabs/VoiceMod: Voice recording audio quality analysis.
• 2023 – Now - Odisei: Real-time saxophone pitch detection.

Datasets and software

Open-source software projects I am involved in:

• Essentia
• Essentia.js
• Gaia

Open datasets I am involved in:

• AcousticBrainz
• The AcousticBrainz Genre Dataset
• The MTG-Jamendo Dataset
• The MusAV Dataset
• Melon Playlist Dataset
• Freesound Datasets
• Freesound Loop Dataset
• ISMIR-2017-Discogs
• Song Describer Dataset

Publications

Google Scholar • ORCID • Scopus • ResearchGate

Journals

• Correya, A., Marcos-Fernández, J., Joglar-Ongay, L., Alonso-Jiménez, P., Serra, X., Bogdanov, D. (2021). Audio and music analysis on the web using Essentia.js. Transactions of the International Society for Music Information Retrieval. 4(1).
• Ferraro, A., Favory, X., Drossos, K., Yuntae, K., Bogdanov, D. (2021). Enriched music representations with multiple cross-modal contrastive learning. IEEE Signal Processing Letters. 28.
• Bogdanov, D., Wack N., Gómez E., Gulati S., Herrera P., Mayor O., et al. (2014). ESSENTIA: an open source library for audio analysis. ACM SIGMM Records. 6(1).
• Bogdanov, D., Haro M., Fuhrmann F., Xambó A., Gómez E., Herrera P., et al. (2013). Semantic content-based music recommendation and visualization based on user preference examples. Information Processing & Management. 49(1).
• Bogdanov, D., Serrà J., Wack N., Herrera P., & Serra X. (2011). Unifying low-level and high-level music similarity measures. IEEE Transactions on Multimedia. 13(4).

Conference proceedings (peer-reviewed)

2023

• Plachouras, C., Bogdanov, D., & Alonso-Jiménez, P. (2023). mir_ref: A representation evaluation framework for music information retrieval tasks. Machine Learning for Audio Workshop, Conference on Neural Information Processing Systems (NeurIPS 2023).
• Manco, I., Weck, B., Doh, S., Zhang, Y., Bogdanov, D., Wu, Y., Chen, K., Tovstogan, P., Benetos, E., Quinton, E., Fazekas, G., Nam, J, & Won, M. (2023). The Song Describer Dataset: a corpus of audio captions for music-and-language evaluation. Machine Learning for Audio Workshop, Conference on Neural Information Processing Systems (NeurIPS 2023).
• Alonso-Jiménez, P., Serra, X., & Bogdanov, D. (2023). Efficient supervised training of audio transformers for music representation learning. International Society for Music Information Retrieval Conference (ISMIR 2023).
• Alonso-Jiménez, P., Favory, X., Foroughmand, H., Bourdalas, G., Serra, X., Lidy, T., & Bogdanov, D. (2023). Pre-training strategies using contrastive learning and playlist information for music classification and similarity. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023).

2022

• Bogdanov, D., Lizarraga-Seijas, X., Alonso-Jiménez, P., & Serra, X. (2022). MusAV: A dataset of relative arousal-valence annotations for validation of audio models. International Society for Music Information Retrieval Conference (ISMIR 2022).
• Alonso-Jiménez, P., Serra, X., & Bogdanov, D. (2022). Music representation learning based on editorial metadata from Discogs. International Society for Music Information Retrieval Conference (ISMIR 2022).
• Buisson, M., Alonso-Jiménez, P., & Bogdanov, D. (2022). Ambiguity modelling with label distribution learning for music classification. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2022).
• Tovstogan, P., Xavier, S., & Bogdanov, D. (2022). Visualization of deep audio embeddings for music exploration and rediscovery. Sound and Music Computing Conference (SMC 2022).
• Tovstogan, P., Xavier, S., & Bogdanov, D. (2022). Similarity of nearest-neighbor query results in deep latent spaces. Sound and Music Computing Conference (SMC 2022).

2021

• Correya, A., Alonso-Jiménez, P., Marcos-Fernández, J., Serra, X. & Bogdanov, D. (2021). Essentia TensorFlow models for audio and music processing on the web. Web Audio Conference (WAC 2021).
• Ferraro, A., Kim, Y., Lee, S., Kim, B., Jo, N., Lim, S., Lim, S., Jang, J., Kim, S., Serra, X., & Bogdanov, D. (2021). Melon Playlist Dataset: a public dataset for audio-based playlist generation and music tagging. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021).

2020

• Ferraro, A., Bogdanov, D., Serra, X., Jeon, J. H., & Yoon, J. (2020). How low can you go? Reducing frequency and time resolution in current CNN architectures for music auto-tagging. The 28th European Signal Processing Conference (EUSIPCO 2020).
• Alonso-Jiménez, P., Bogdanov, D., Pons, J., & Serra, X. (2020). TensorFlow audio models in Essentia. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020).
• Correya, A., Bogdanov, D., Joglar-Ongay, L., & Serra, X. (2020) Essentia.js: a JavaScript library for music and audio analysis on the web. International Society for Music Information Retrieval Conference (ISMIR 2020).
• Won, M., Ferraro, A., Bogdanov, D., Serra, X. (2020). Evaluation of CNN-based Automatic Music Tagging Models. Sound and Music Computing Conference (SMC 2020).
• Ramires, A., Font, F., Bogdanov, D., Smith, J.B.L., Yang, Y., Ching, J., Chen, B., Wu, Y., Wei-Han, H., & Serra, X. The Freesound Loop dataset and annotation tool. International Society for Music Information Retrieval Conference (ISMIR 2020).
• Ferraro, A., Jeon, J. H., B. Kim, Serra, X., & Bogdanov D. (2020). Artist biases in collaborative filtering for music recommendation. Machine Learning for Media Discovery Workshop, International Conference on Machine Learning (ML4MD ICML 2020).
• Tovstogan, P., Serra, X., & Bogdanov, D. (2020). Web interface for exploration of latent and tag spaces in music auto-tagging. Machine Learning for Media Discovery Workshop, International Conference on Machine Learning (ML4MD ICML 2020).

2019

• Bogdanov, D., Won M., Tovstogan P., Porter A., & Serra X. (2019). The MTG-Jamendo dataset for automatic music tagging. Machine Learning for Music Discovery Workshop, International Conference on Machine Learning (ICML 2019).
• Bogdanov, D., Porter A., Schreiber H., Urbano J., & Oramas S. (2019). The AcousticBrainz Genre Dataset: Multi-source, multi-level, multi-label, and large-scale. 20th International Society for Music Information Retrieval Conference (ISMIR 2019).
• Alonso-Jiménez, P., Joglar-Ongay L., Serra X., & Bogdanov D. (2019). Automatic detection of audio problems for quality control in digital music distribution. AES 146th Convention.
• Ferraro, A., Bogdanov D., & Serra X. (2019). Skip prediction using boosting trees based on acoustic features of tracks in sessions. WSDM Cup Workshop 2019.
• Ferraro, A., Bogdanov D., Serra X., & Yoon J. (2019). Artist and style exposure bias in collaborative filtering based music recommendations. Workshop on Designing Human-Centric MIR Systems.

2018

• Ferraro, A., Bogdanov D., Yoon J., Kim K. S., & Serra X. (2018). Automatic playlist continuation using a hybrid recommender system combining features from text and audio. Workshop on the RecSys Challenge 2018.
• Ferraro, A., Bogdanov D., Choi K., & Serra X. (2018). Using offline metrics and user behavior analysis to combine multiple systems for music recommendation. RecSys 2018 Workshop on Offline Evaluation of Recommender Systems (REVEAL 2018).

2017

• Bogdanov, D., & Serra X. (2017). Quantifying music trends and facts using editorial metadata from the Discogs database. 18th International Society for Music Information Retrieval Conference (ISMIR 2017).
• Fonseca, E., Pons, J., Favory, X., Font, F., Bogdanov, D., Ferraro, A., Oramas, S., Porter, A., Serra, X. (2017). Freesound Datasets: A platform for the creation of open audio datasets. 18th International Society for Music Information Retrieval Conference (ISMIR 2017).
• Fonseca, E., Gong R., Bogdanov D., Slizovskaia O., Gomez E., & Serra X. (2017). Acoustic scene classification by ensembling gradient boosting machine and convolutional neural networks. Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2017).

2016

• Bogdanov, D., Porter A., Herrera P., & Serra X. (2016). Cross-collection evaluation for music classification tasks. 17th International Society for Music Information Retrieval Conference (ISMIR 2016).
• Porter, A., Bogdanov D., & Serra X. (2016). Mining metadata from the web for AcousticBrainz. 3rd International Digital Libraries for Musicology workshop (DL4M 2016).

2015

• Porter, A., Bogdanov D., Kaye R., Tsukanov R., & Serra X. (2015). AcousticBrainz: a community platform for gathering music information obtained from audio. 16th International Society for Music Information Retrieval Conference (ISMIR 2015).

2014

• Urbano, J., Bogdanov D., Herrera P., Gómez E., & Serra X. (2014). What is the effect of audio quality on the robustness of MFCCs and chroma features? International Society for Music Information Retrieval Conference (ISMIR 2014).

2013

• Bogdanov, D., Wack N., Gómez E., Gulati S., Herrera P., Mayor O., Roma G., Salamon J., Zapata J., & Serra X. (2013). ESSENTIA: an open-source library for sound and music analysis. ACM International Conference on Multimedia (MM 2013).
• Bogdanov, D., Wack N., Gómez E., Gulati S., Herrera P., Mayor O., Roma G., Salamon J., Zapata J., & Serra X. (2013). ESSENTIA: an audio analysis library for music information retrieval. International Society for Music Information Retrieval Conference (ISMIR 2013).

2012

• Bogdanov, D., & Herrera P. (2012). Taking advantage of editorial metadata to recommend music. 9th International Symposium on Computer Music Modeling and Retrieval (CMMR 2012).
• Yang, Y., Bogdanov D., Perfecto H., & Sordo M. (2012). Music retagging using label propagation and robust principal component analysis. 21st International World Wide Web Conference (WWW 2012): 4th International Workshop on Advances in Music Information Research (AdMIRe 2012).

2011

• Bogdanov, D., & Herrera P. (2011). How much metadata do we need in music recommendation? A subjective evaluation using preference sets. International Society for Music Information Retrieval Conference (ISMIR 2011).
• Bogdanov, D., Haro M., Fuhrmann F., Xambó A., Gómez E., & Herrera P. (2011). A Content-based system for music recommendation and visualization of user preferences working on semantic notions. 9th International Workshop on Content-based Multimedia Indexing (CBMI 2011).

2010

• Bogdanov, D., Haro M., Fuhrmann F., Gómez E., & Herrera P. (2010). Content-based music recommendation based on user preference examples. The 4th ACM Conference on Recommender Systems. Workshop on Music Recommendation and Discovery (Womrad 2010).
• Haro, M., Xambó A., Fuhrmann F., Bogdanov D., Gómez E., & Herrera P. (2010). The Musical Avatar - A visualization of musical preferences by means of audio content description. 5th Audio Mostly Conference: A Conference on Interaction with Sound (AM 2010).

2009

• Bogdanov, D., Serrà, J., Wack, N., & Herrera, P. (2009). From low-level to high-level: Comparative study of music similarity measures. IEEE International Symposium on Multimedia (ISM 2009). International Workshop on Advances in Music Information Research (AdMIRe).

Book chapters

• Schedl, M., Knees, P., McFee, B., & Bogdanov D. (2022). Music recommendation systems: Techniques, use cases, and challenges. Recommender Systems Handbook (3nd edition). Springer.
• Schedl, M., Knees, P., McFee, B., Bogdanov, D., & Kaminskas M. (2015). Music recommender systems. Recommender Systems Handbook (2nd edition). Springer.

Other publications

• Correya, A., Bogdanov, D., Alonso-Jiménez, P., & Serra X. (2022). Essentia API: a web API for music audio analysis. International Society for Music Information Retrieval Conference (ISMIR 2022). Late Breaking Demo.
• Manco, I., Weck, B., Tovstogan, P., Won, M., & Bogdanov, D. (2022). Song Describer: a platform for collecting textual descriptions of music recordings. International Society for Music Information Retrieval Conference (ISMIR 2022). Late Breaking Demo.
• Marcos-Fernández, J., Joglar-Ongay, L., Serra, X., & Bogdanov, D. (2022). Audio analysis applications in the browser with Essentia.js. Web Audio Conference (WAC 2022).
• Tovstogan P., Bogdanov, D., Porter, A. (2021). MediaEval 2021: Emotion and theme recognition in music using Jamendo. MediaEval 2021 Workshop.
• Alonso-Jiménez, P., Bogdanov, D., & Serra, X. (2020). Deep embeddings with Essentia models. International Society for Music Information Retrieval Conference (ISMIR 2020). Late Breaking Demo.
• Bogdanov, D., Porter, A., Tovstogan P., & Won M. (2020). MediaEval 2020: Emotion and theme recognition in music using Jamendo. MediaEval 2020 Workshop.
• Bogdanov, D., Porter, A., Tovstogan P., & Won M. (2019). MediaEval 2019: Emotion and theme recognition in music using Jamendo. MediaEval 2019 Workshop.
• Oramas, S., Bogdanov D., & Porter A. (2018). MediaEval 2018 AcousticBrainz Genre Task: A baseline combining deep feature embeddings across datasets. MediaEval 2018 Workshop.
• Bogdanov, D., Porter A., Urbano J., & Schreiber H. (2018). The MediaEval 2018 AcousticBrainz Genre Task: Content-based Music Genre Recognition from Multiple Sources. MediaEval 2018 Workshop.
• Bogdanov, D., Porter A., Urbano J., & Schreiber H. (2017). The MediaEval 2017 AcousticBrainz Genre Task: Content-based Music Genre Recognition from Multiple Sources. MediaEval 2017 Workshop.
• Bogdanov, D., Porter A., & Serra X. (2015). Taming wild horses with Essentia Music Extractor. International Society for Music Information Retrieval Conference (ISMIR 2015). Late Breaking Demo.
• Gong, R., Fonseca, E., Bogdanov, D., Slizovskaia, O., Gomez, E., & Serra X. (2017). Acoustic scene classification by fusing LightGBM and VGG-net multichannel predictions. Detection and Classification of Acoustic Scenes and Events (DCASE 2017). Technical report.
• Bogdanov, D., Wack N., Gómez E., Gulati S., Herrera P., Mayor O., et al. (2014). ESSENTIA: an open source library for audio analysis. ACM SIGMM Records. 6(1).
• Sordo, M., Celma Ò., & Bogdanov D. (2011). Audio Tag Classification using Weighted-Vote Nearest Neighbor Classification. Music Information Retrieval Evaluation eXchange (MIREX 2011) extended abstract.
• Bogdanov, D., Serrà J., Wack N., & Herrera P. (2010). Hybrid Music Similarity Measure. Music Information Retrieval Evaluation eXchange (MIREX 2010) extended abstract.
• Wack, N., Laurier C., Meyers O., Marxer R., Bogdanov D., Serrà J., et al. (2010). Music classification using high-level models. Music Information Retrieval Evaluation eXchange (MIREX 2010) extended abstract.
• Bogdanov, D., Serrà J., Wack N., & Herrera P. (2009). Hybrid Similarity Measures For Music Recommendation. Music Information Retrieval Evaluation eXchange (MIREX 2009) extended abstract.
• Wack, N., Guaus E., Laurier C., Meyers O., Marxer R., Bogdanov D., et al. (2009). Music type groupers (MTG): generic music classification algorithms. Music Information Retrieval Evaluation eXchange (MIREX 2009) extended abstract.

PhD thesis

• Bogdanov, D. (2013). From music similarity to music recommendation: Computational approaches based on audio features and metadata. Universitat Pompeu Fabra, Barcelona, Spain.

Invited talks and events

• Music audio representation learning research at MTG. Deep Learning Barcelona Symposium 2023 (DLBCN 2023). 2023-12-21.
• Challenges and Opportunities in Music Tech: Open debate. 2022-12-13.
• Essentia: past, present, and future. BCN Music Technology Forum. 2019-06-27.
• Music feature analysis with Essentia. MIP-Frontiers Summer School. 2019-05-22.
• Audio analysis and music information retrieval at MTG. KAISTxSNU Music and Audio Workshop. 2019-02-22.
• Sónar+D 2017 Innovation Challenge mentor. 2017-06-13 - 2017-06-16.
• The Musical Avatar. Escola Superior de Música de Catalunya, Seminaris de Sonologia. 2011-11-07.

In media

• La música del futuro, RTVE. TV documentary. 2023-07-10.

Demos

• Essentia: Open-source library and tools for audio and music analysis, description, and synthesis. Poster session. European Research Music Conference. 11.06.2018.
• My Musical Avatar. 9th International Workshop on Content-based Multimedia Indexing. 2011.
• My Musical Avatar. Fira Recerca en Directe. Barcelona. 2012.

Scientific services

Organization of scientific events

• Web Audio Conference, 2021. Artworks and Performances Chair.
• MediaEval Emotions and Themes in Music, 2021.
• MediaEval Emotions and Themes in Music, 2020.
• MediaEval Emotions and Themes in Music, 2019.
• MediaEval AcousticBrainz Genre Task, 2018.
• MediaEval AcousticBrainz Genre Task, 2017.

Reviewer for journals

• IEEE Transactions on Multimedia (IEEE)
• IEEE Signal Processing Magazine (IEEE)
• International Journal of Multimedia Information Retrieval (Springer)
• Journal of Intelligent Information Systems (Springer)
• Transactions of the International Society for Music Information Retrieval (TISMIR)
• Journal of the Audio Engineering Society (JAES)

Reviewer for conferences

• 24th International Society for Music Information Retrieval Conference (ISMIR), 2023 - meta-reviewer
• 23nd International Society for Music Information Retrieval Conference (ISMIR), 2022 - meta-reviewer
• 22nd International Society for Music Information Retrieval Conference (ISMIR), 2021
• 21st International Society for Music Information Retrieval Conference (ISMIR), 2020
• 1st Workshop on Designing Human-Centric MIR Systems, 2019
• 20th International Society for Music Information Retrieval Conference (ISMIR), 2019 - meta-reviewer
• ACM RecSys Challenge 2018 Workshop, 2018
• 18th International Society for Music Information Retrieval Conference (ISMIR), 2017
• 19th International Conference on Digital Audio Effects (DAFx), 2016
• 17th International Society for Music Information Retrieval Conference (ISMIR), 2016
• 13th International Society for Music Information Retrieval Conference (ISMIR), 2012
• 9th Sound and Music Computing Conference (SMC), 2012
• 8th Sound and Music Computing Conference (SMC), 2011
• 7th Sound and Music Computing Conference (SMC), 2010

Program Committee membership

• 20th International Society for Music Information Retrieval Conference (ISMIR), 2019
• ACM RecSys Challenge 2018 Workshop
• MediaEval 2019 Workshop
• MediaEval 2018 Workshop
• MediaEval 2017 Workshop
• 4th International Workshop on Advances in Music Information Research (AdMIRe), 2012

Teaching

• 2020 – Now - Music Technology Lab, Pompeu Fabra University, seminars
• 2015 – Now - Master in Sound and Music Computing, Pompeu Fabra University, theses supervision
• 2014 – 2017 - Master in Sound and Music Computing, Pompeu Fabra University, Audio and Music Processing Lab, seminars
• 2011 – 2012 - Signal processing undegraduate course, Pompeu Fabra University, seminars and practicals
• 2006 – 2007 - Algorithms and algorithmic languages, Moscow State University, undergraduate course (practicals)

PhD thesis supervision

• Recep Oğuz Araz - Music representation learning, ongoing.
• Pablo Alonso Jimenez - Deep Embeddings for Music Classification, ongoing
• Philip Tovstogan - Exploration of Music Collections with Audio Embeddings, defended in 2022
• Luis Joglar

Jury memberships of PhD defenses

• Daniel Gómez - 04/2017 - Drum Rhythm in Electronic Dance Music, Universitat Pompeu Fabra, Barcelona, Spain

Awards

• WAC 2021, Best Paper Award
• ISMIR 2020, Best Reproducibility Award
• ACM Multimedia 2013, Best Open Source Software Award

Languages

• Russian (native), English (fluent), Spanish (fluent), Catalan (fluent).