Towards Richer Online Music Public-domain Archives

Livrables

Mid-term evaluation [M27; T6.1] This deliverable includes the description of the pilots, in terms of user engagement, number of users involved, number and type of activities undertaken (e.g., methods used). It will also report eventual deviations with respect to the pilot planning defined in D6.2 and reasons for that.

Music description

Music description [M10, M20; T3.2] Identification and implementation of multimodal music descriptors of interest for the end user pilots

Annotation tools

Annotation tools [M12; M34; T5.5] The first release will include basic annotation tasks and initial integration of crowd planning strategies. The second release will consist of a consolidated version of the first release, including additional annotation tasks.

Multimodal music information alignment

Multimodal music information alignment [M10, M24; T3.5] Selected pieces of the standard repertoire provided with temporal alignment between different modalities, including partial sources.

Project handbook

Project handbook [M3; T1.1] Including all procedures, communication channels and operational framework

Music performance assessment

Music performance assessment [M12, M34; T5.4] This deliverable will include automatic models to predict performance difficulty of (solo) instrumental scores and to rate the quality of their performance. At first, “difficulty indices” to denote performance difficulty of a given piece are specified and validated on preliminary data (e.g., solo lute and piano repertoire). Subsequently, performance quality assessment metrics involving audio and score information are developed and systematically validated via human feedback.

Progress/ Interim report

Progress/ Interim report [M24; T8.1] This report includes M12-24 activity and management report and describe work status/main scientific achievements, technical or managerial consortium problems, dissemination exploitation activities, indicative man months spent for that period and also to provide any policy relevant updates.

Planning for the execution of pilots in real life settings

Planning for the execution of pilots in real life settings [M14; T6.1] This report sets up the pilot phase by outlining a planning for pilot activities, user recruitment strategies, general pilot coordination and technical support, eventual acquisition of user devices to run the pilot activities (e.g., tablets, SIM cards, etc.).

Annual dissemination report

Annual dissemination report [M12, 24, 36; T7.1–5] Dissemination overview and yearly plan, listing achievements per year and outlook for next year covering different stakeholders.

TROMPA processing library

TROMPA processing library [M12, M34; T5.3] This deliverable will provide a library for embeddable descriptions and synthesis of music data coming from supported music data repositories. First release: library components individually available; Second release: all library components working in sync together.

Score edition component

Score edition component [M12, M34; T5.2] This deliverable will consist on a digital score edition tool according to current standards (e.g. MEI schema). First release: Allowing basic access to and annotation (at the measure level) of scores and metadata Second release: Allow detailed linking and annotation across and between score documents and audio recordings

Data infrastructure

Data infrastructure [M6, M30; T5.1] Iterations of the TROMPA data infrastructure jointly built by partners in T5.1

Final evaluation

Final evaluation [M36; T6.1] Overall results of the entire pilot phases

Data resource preparation

Data resource preparation [M10, M18; T3.1] Identification and collecting of musical (multimodal) data to be exploited within TROMPA. It will consider musicological collections available for research as well as existing digital repositories relevant for the different pilots.

Crowd evaluation methodologies

Crowd evaluation methodologies [M20; T4.1]. This deliverable contains the crowd-based ground truth provision and evaluation methodologies for the WP3-technology. It also contains the results of crowdsourcing experiments to elicit novel non-obvious music descriptors relevant to the different TROMPA-audiences, which feed the technology development in WP3.

Visual analysis of scanned scores

Visual analysis of scanned scores [M29; T3.4] Technologies for visual analysis and description of scanned scores

Working prototype for scholars

Working prototype for scholars [M24, M34; T6.2] Deliverable describing the music scholar prototype.

Working prototype for singers

Working prototype for singers [M24, M34; T6.5] Deliverable describing the singer prototype.

Working prototype for music enthusiasts

Working prototype for music enthusiasts [M24, M34; T6.6] Deliverable describing the music enthusiast prototype.

Working prototype for instrument players

Working prototype for instrument players [M24, M34; T6.4] Deliverable describing the instrument player prototype.

Working prototype for orchestras

Working prototype for orchestras [M24, M34; T6.3] Deliverable describing the orchestra prototype.

Develop project website and blog

Develop project website and blog [M3; T7.1-6] Project website: a multimedia website with public information on the project and its evolution. It will include a blog to achieve the goals of tasks 7.1 and a private space for partners only as a discussion space and document repository.

Communication channels

Communication channels [M3;T1.2] Definition of communication channels within the consortium, the EC and other parties out of the project

Data Management Plan

Data Management Plan [M6, M18 and M36; T1.3] A report describing the data management life cycle for all data sets that will be collected, processed or generated by the research project. It is a document outlining how research data will be handled during a research project, and even after the project is completed, describing what data will be collected, processed or generated and following what methodology and standards, whether and how this data will be shared and/or made open, and how it will be curated and preserved. The first version of the DMP is delivered at M6 in compliance with the template provided by the Commission. The DMP will be updated at least by the mid-term and final review to fine-tune it to the data generated and the uses identified by the consortium.

Publications

Transfer learning from speech to music: towards language-sensitive emotion recognition models

Auteurs: Gómez-Cañón, Juan Sebastián; Cano, Estefanía; Herrera, Perfecto; Gómez, Emilia
Publié dans: Proceedings of the 28th European Signal Processing Conference (EUSIPCO), 2021
Éditeur: IEEE
DOI: 10.5281/zenodo.4076790

Less is more: Faster and better music version identification with embedding distillation

Auteurs: Yesiler, Furkan; Serra, Joan; Gomez, Emilia
Publié dans: Proceedings of the 21stInternational Society for Music Information Retrieval Conference, 2020
Éditeur: International Society for Music Information Retrieval Conference
DOI: 10.5281/zenodo.4245569

Vocoder-Based Speech Synthesis from Silent Videos

Auteurs: Daniel Michelsanti, Olga Slizovskaia, Gloria Haro, Emilia Gómez, Zheng-Hua Tan, Jesper Jensen
Publié dans: Interspeech 2020, 2020, Page(s) 3530-3534
Éditeur: ISCA
DOI: 10.21437/interspeech.2020-1026

20 Years of Playlists: A Statistical Analysis on Popularity and Diversity

Auteurs: Porcaro, Lorenzo; Gómez Gutiérrez, Emilia, 1975-
Publié dans: 20th International Society for Music Information Retrieval Conference, Numéro 1, 2019
Éditeur: International Society for Music Information Retrieval Conference
DOI: 10.5281/zenodo.3527757

A deep learning based analysis-synthesis framework for unison singing

Auteurs: Chandna, Pritish; Cuesta, Helena; Gómez, Emilia
Publié dans: Proceedings of the 21st International Society for Music Information Retrieval Conference, 2020, Page(s) 598-604
Éditeur: International Society for Music Information Retrieval
DOI: 10.5281/zenodo.4245501

Rehearsal Encodings with a Social Life.

Auteurs: Weigl, D. M. and Goebl, W.
Publié dans: Music Encoding Conference (MEC2020), 2020
Éditeur: De Luca, E.; and Flanders, J., editors.
DOI: 10.17613/5ae5-8387

Da-TACOS: A Dataset for Cover Song Identification and Understanding

Auteurs: Yesiler, Furkan; Tralie, Chris; Correya, Albin; Silva, Diego Furtado; Tovstogan, Philip; Gomez, Emilia; Serra, Xavier
Publié dans: Proceedings of the 20th International Society for Music Information Retrieval Conference, ISMIR, Numéro 1, 2019
Éditeur: International Society for Music Information Retrieval Conference
DOI: 10.5281/zenodo.3527810

Combining musical features for cover detection

Auteurs: Doras, Guillaume; Yesiler, Furkan; Serra, Joan; Gomez, Emilia; Peeters, Geoffroy
Publié dans: Proceedings of the 21st International Society for Music Information Retrieval Conference, 2020, Page(s) 279-286
Éditeur: International Society for Music Information Retrieval
DOI: 10.5281/zenodo.4245423

Music in newspapers - interdisciplinary opportunities and data-related challenges

Auteurs: Liem, C.C.S.
Publié dans: DLfM '18 Proceedings of the 5th International Conference on Digital Libraries for Musicology, Numéro 3, 2018
Éditeur: ACM

The MediaEval 2018 AcousticBrainz genre task: content-based music genre recognition from multiple sources

Auteurs: Dmitry Bogdanov; Porter, A.; Urbano, J.; Schreiber, H.
Publié dans: Proceedings of the MediaEval 2018 Workshop, 2018
Éditeur: MediaEval

(F-TEMPO): a new approach to a finding aid for musicians and librarians.

Auteurs: Crawford, T.
Publié dans: IAML Congress 2019 (International Association of Music Libraries and Sound Archives), 2019
Éditeur: IAML

Measuring Diversity of Artificial Intelligence Conferences

Auteurs: Freire, Ana; Porcaro, Lorenzo; Gómez, Emilia
Publié dans: AAAI Workshop on Diversity in Artificial Intelligence (AIDBEI 2021), Numéro 12, 2021
Éditeur: AIDBEI

Multiple F0 Estimation in Vocal Ensembles using Convolutional Neural Networks

Auteurs: Cuesta, Helena; McFee, Brian; Gomez, Emilia
Publié dans: 21st International Society for Music Information Retrieval, 2020
Éditeur: International Society for Music Information Retrieval
DOI: 10.5281/zenodo.4245433

WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN

Auteurs: Pritish Chandna, Merlijn Blaauw, Jordi Bonada, Emilia Gomez
Publié dans: 2019 27th European Signal Processing Conference (EUSIPCO), 2019, Page(s) 1-5, ISBN 978-9-0827-9703-9
Éditeur: IEEE
DOI: 10.23919/eusipco.2019.8903099

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

Auteurs: Dmitry Bogdanov; Alastair Porter; Hendrik Schreiber; Julián Urbano; Sergio Oramas
Publié dans: International Society for Music Information Retrieval Conference 2019, Numéro 28, 2019
Éditeur: Ubiquity Press
DOI: 10.5281/zenodo.3527817

End-to-end Sound Source Separation Conditioned on Instrument Labels

Auteurs: Olga Slizovskaia, Leo Kim, Gloria Haro, Emilia Gomez
Publié dans: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Page(s) 306-310, ISBN 978-1-4799-8131-1
Éditeur: IEEE
DOI: 10.1109/icassp.2019.8683800

Semi-supervised Learning for Singing Synthesis Timbre

Auteurs: Bonada, Jordi; Blaauw, Merlijn
Publié dans: IEEE International Conference on Acoustics, Speech and Signal Processing, 2021
Éditeur: IEEE

Joyful for you and tender for us: the influence of individual characteristics and language on emotion labeling and classification

Auteurs: Gómez-Cañón, Juan Sebastián; Cano, Estefanía; Herrera, Perfecto; Gómez, Emilia
Publié dans: Proceedings of the 21st International Society of Music Information Retrieval Conference, 2020
Éditeur: International Society of Music Information Retrieval Conference (ISMIR),
DOI: 10.5281/zenodo.4245568

A Case Study of Deep-Learned Activations via Hand-Crafted Audio Features

Auteurs: Slizovskaia, Olga; Gómez, Emilia; Haro, Gloria
Publié dans: Numéro 1, 2018
Éditeur: Joint Workshop on Machine Learning for Music

Language-Sensitive Music Emotion Recognition Models: are We Really There Yet?

Auteurs: Juan Sebastian Gomez-Canon, Estefania Cano, Ana Gabriela Pandrea, Perfecto Herrera, Emilia Gomez
Publié dans: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, Page(s) 576-580, ISBN 978-1-7281-7605-5
Éditeur: IEEE
DOI: 10.1109/icassp39728.2021.9413721

Accurate and Scalable Version Identification Using Musically-Motivated Embeddings

Auteurs: Furkan Yesiler, Joan Serra, Emilia Gomez
Publié dans: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 21-25, ISBN 978-1-5090-6631-5
Éditeur: IEEE
DOI: 10.1109/icassp40776.2020.9053793

Statistical Significance Testing in Information Retrieval: An Empirical Analysis of Type I, Type II and Type III Errors

Auteurs: Urbano Merino, J.; De Lima, H.A.; Hanjalic, A.
Publié dans: SIGIR'19 Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, Numéro 20, 2019
Éditeur: ACM
DOI: 10.1145/3331184.3331259

A Vocoder Based Method for Singing Voice Extraction

Auteurs: Pritish Chandna, Merlijn Blaauw, Jordi Bonada, Emilia Gomez
Publié dans: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Page(s) 990-994, ISBN 978-1-4799-8131-1
Éditeur: IEEE
DOI: 10.1109/icassp.2019.8683323

Towards Richer Online Music Public-domain Archives: Providing enriched access to classical music encodings.

Auteurs: Weigl, D. M., Liem, C., Gómez, E., Crawford, T., Ahmed, R., Klerkx, W., & Goebl, W
Publié dans: Music Encoding Conference 2019, 2019
Éditeur: De Luca, E.; and Flanders, J., editors

A New Perspective on Score Standardization

Auteurs: Julián Urbano, Harlley Lima, Alan Hanjalic
Publié dans: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019, Page(s) 1061-1064, ISBN 9781450361729
Éditeur: ACM
DOI: 10.1145/3331184.3331315

Music in newspapers - interdisciplinary opportunities and data-related challenges

Auteurs: Cynthia C. S. Liem
Publié dans: Proceedings of the 5th International Conference on Digital Libraries for Musicology - DLfM '18, 2018, Page(s) 47-51, ISBN 9781-450365222
Éditeur: ACM Press
DOI: 10.1145/3273024.3273032

End-to-End Sound Source Separation Conditioned On Instrument Labels

Auteurs: Slizovskaia, Olga; Kim, Leo; Haro, Gloria; Gomez, Emilia
Publié dans: 2019 International Conference on Acoustics, Speech, and Signal Processing., Numéro 2, 2019
Éditeur: IEEE

A Framework for Multi-f0 Modeling in SATB Choir Recordings

Auteurs: Cuesta, H., Gómez E., & Chandna P.
Publié dans: Sound and Music Computing (SMC) Conference., 2019
Éditeur: SMC

Analysis of Intonation in Unison Choir Singing

Auteurs: Cuesta, H., Gómez E., Martorell A., & Loáiciga F.
Publié dans: 15th International Conference on Music Perception and Cognition (ICMPC), 2018
Éditeur: Universitty of Graz
DOI: 10.5281/zenodo.1319597

Read/Write Digital Libraries for Musicology

Auteurs: David M. Weigl, Werner Goebl, Alex Hofmann, Tim Crawford, Federico Zubani, Cynthia C. S. Liem, Alastair Porter
Publié dans: 7th International Conference on Digital Libraries for Musicology, 2020, Page(s) 48-52, ISBN 9781450387606
Éditeur: ACM
DOI: 10.1145/3424911.3425519

Sequence-to-Sequence Singing Synthesis Using the Feed-Forward Transformer

Auteurs: Merlijn Blaauw, Jordi Bonada
Publié dans: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 7229-7233, ISBN 978-1-5090-6631-5
Éditeur: IEEE
DOI: 10.1109/icassp40776.2020.9053944

Deep learning based source separation applied to choir ensembles

Auteurs: Petermann, Darius; Pritish Chandna; Cuesta, Helena; Bonada, Jordi; Gomez, Emilia
Publié dans: Proceedings of the 21st International Society for Music Information Retrieval Conference, 2020, Page(s) 733-739
Éditeur: International Society for Music Information Retrieval
DOI: 10.5281/zenodo.4245535

Hundreds of Thousands of Pieces in MEI: Encoding Tablatures at Scale

Auteurs: Ahmed, R.; Crawford, T.; Lewis, D.
Publié dans: Music Encoding Conference., 2019
Éditeur: De Luca, E.; and Flanders, J., editors

Music recommendation diversity: a tentative framework and preliminary results

Auteurs: Porcaro, Lorenzo; Castillo, Carlos; Gómez Gutiérrez, Emilia, 1975-
Publié dans: 1st Workshop on Designing Human-Centric MIR Systems, Numéro 1, 2019
Éditeur: International Society for Music Information Retrieval

Interweaving and Enriching Digital Music Collections for Scholarship, Performance, and Enjoyment

Auteurs: David M. Weigl, Werner Goebl, Tim Crawford, Aggelos Gkiokas, Nicolas F. Gutierrez, Alastair Porter, Patricia Santos, Casper Karreman, Ingmar Vroomen, Cynthia C. S. Liem, Álvaro Sarasúa, Marcel van Tilburg
Publié dans: 6th International Conference on Digital Libraries for Musicology, 2019, Page(s) 84-88, ISBN 9781450372398
Éditeur: ACM
DOI: 10.1145/3358664.3358666

Solos: A Dataset for Audio-Visual Music Analysis

Auteurs: Montesinos, Juan F.; Slizovskaia, Olga; Haro, Gloria
Publié dans: 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP), Numéro 23, 2020
Éditeur: IEEE

Exploring Artist Gender Bias in Music Recommendation

Auteurs: Shakespeare, Dougal; Porcaro, Lorenzo; Gómez Gutiérrez, Emilia, 1975-; Castillo, Carlos
Publié dans: 2nd Workshop on the Impact of Recommender Systems (ImpactRS), at the 14th ACM Conference on Recommender Systems, Numéro 20, 2020
Éditeur: ACM

Content Based Singing Voice Extraction from a Musical Mixture

Auteurs: Pritish Chandna, Merlijn Blaauw, Jordi Bonada, Emilia Gomez
Publié dans: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, Page(s) 781-785, ISBN 978-1-5090-6631-5
Éditeur: IEEE
DOI: 10.1109/icassp40776.2020.9053024

A Model for evaluating popularity and semantic information variations in radio listening sessions

Auteurs: Porcaro, Lorenzo; Gómez Gutiérrez, Emilia, 1975-
Publié dans: 13th ACM Conference on Recommender Systems (RecSys 2019), 2019
Éditeur: ACM

Recognizing Musical Entities in User-generated Content

Auteurs: Lorenzo Porcaro, Horacio Saggion
Publié dans: Computación y Sistemas, Numéro 23/3, 2019, ISSN 1405-5546
Éditeur: Centro de Investigacion en Computacion (CIC) del Instituto Politecnico Nacional (IPN)
DOI: 10.13053/cys-23-3-3280

Dagstuhl ChoirSet: A Multitrack Dataset for MIR Research on Choral Singing

Auteurs: Sebastian Rosenzweig, Helena Cuesta, Christof Weiß, Frank Scherbaum, Emilia Gómez, Meinard Müller
Publié dans: Transactions of the International Society for Music Information Retrieval, Numéro 3/1, 2020, Page(s) 98-110, ISSN 2514-3298
Éditeur: Ubiquity Press
DOI: 10.5334/tismir.48

Music Tempo Estimation: Are We Done Yet?

Auteurs: Hendrik Schreiber, Julián Urbano, Meinard Müller
Publié dans: Transactions of the International Society for Music Information Retrieval, Numéro 3/1, 2020, Page(s) 111, ISSN 2514-3298
Éditeur: Ubiquity press
DOI: 10.5334/tismir.43

Mapping by Observation: Building a User-Tailored Conducting System From Spontaneous Movements

Auteurs: Álvaro Sarasúa, Julián Urbano, Emilia Gómez
Publié dans: Frontiers in Digital Humanities, Numéro 6, 2019, ISSN 2297-2668
Éditeur: Frontiers
DOI: 10.3389/fdigh.2019.00003

Demo: VOICEFUL: Voice Analysis, Transformation and Synthesis on the Web.

Auteurs: Mayor O., Janer J., Parra H., Sarasúa, Á.
Publié dans: Web Audio Conference 2019, 2019
Éditeur: Web Audio Conference

Choir Singing Synthesis for Rehearsal Tools with Large-scale Multilingual Repertoires.

Auteurs: Sarasúa, Á., Janer, J., Mayor, O., Bonada J., & Blaauw. M.
Publié dans: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2020
Éditeur: IEEE

Microtask crowdsourcing for music score Transcriptions: an experiment with error detection.

Auteurs: Samiotis, I. P., Qiu, S., Mauri, A., Liem, C. C., Lofi, C., & Bozzon, A.
Publié dans: 21st Conference of the International Society for Music Information Retrieval (ISMIR 2020)., 2020
Éditeur: International Society for Music Information Retrieval

Analysis of Intonation in Unison Choir Singing

Auteurs: Cuesta; H.; Gómez E.; Martorell A.; Loáiciga F.
Publié dans: 15th International Conference on Music Perception and Cognition (ICMPC), 2018
Éditeur: International Conference on Music Perception and Cognition

Deep Learning for Singing Processing: Achievements, Challenges and Impact on Singers and Listeners

Auteurs: Gómez, Emilia; Blaauw, Merlijn; Bonada, Jordi; Chandna, Pritish; Cuesta, Helena
Publié dans: 2018 Joint Workshop on Machine Learning for Music. The Federated Artificial Intelligence Meeting (FAIM), Numéro 3, 2018
Éditeur: CML, IJCAI/ECAI, and AAMAS

Deep Learning for Singing Processing: Achievements, Challenges and Impact on Singers and Listeners

Auteurs: Gómez, Emilia; Blaauw, Merlijn; Bonada, Jordi; Chandna, Pritish; Cuesta, Helena
Publié dans: Numéro 1, 2018
Éditeur: Joint Workshop on Machine Learning for Music

Playing with a Web of Music: Connecting and enriching online music repositories

Auteurs: Weigl, D. M. and Goebl, W.
Publié dans: Music – Media – History: Re-Thinking Musicology in an Age of Digital Media, 2021, ISBN 9783837651454
Éditeur: In Matej Santi and Elias Berner (Edsit.)

Recherche de données OpenAIRE...

Livrables

Publications

Partager cette page

Télécharger