News and Events

Presentations of PhD proposals
30 Jun 2014

On June 30th 2014 we have the defences of the thesis proposals of 5 first-year PhD students of the MTG. The presentations are open to everyone.

10:15h - Nadine Kroher (Supervisor: Emilia Gomez). Title of proposal: "Computational Transcription, Description and Analysis of the Flamenco Singing Voice". Room 55.410 (Tanger building)

11:00h - Marius Miron (Supervisor: Emilia Gomez). Title of proposal: "Source Separation and Signal Modeling of Orchestral Music Mixtures". Room 55.410 (Tanger building)

11:45h - Georgi Dhambazov (Supervisor: Xavier Serra). Title of proposal: "Analysis of timbral and phonetic characteristics of singing voice in the Turkish art music tradition". Room 55.410 (Tanger building)

12:30h - Sergio Oramas (Supervisor: Xavier Serra). Title of proposal: "Harvesting, Structuring and Exploiting Social Data in Music Information Retrieval". Room 55.410 (Tanger building)

16:00h - Rafael Caro Repetto (Supervisor: Xavier Serra).  Title of proposal: "Understanding Xipi and Erhuang. Analysis of the musical dimension of Jingu Arias". room 20.287 (Ciutadella campus)

20 Jun 2014 - 16:22 | view
Participation to FMA 2014
Nadine Kroher, Georgi Dzhambazov, Sertan Şentürk and Xavier Serra participate to the 4th International Workshop on Folk Music Analysis that takes place in Istanbul, Turkey, on June 12th and 13th, 2014. 
They are presenting the following work done at the MTG:  
10 Jun 2014 - 17:37 | view
SMC master thesis defense
1 Jul 2014 - 4 Jul 2014

What? SMC master students 2013/2014 defend their final projects on July 1st-4th

Where? Room 55.309 Tanger building

Detailed schedule:

Student name   Title   Supervisor   Date   Hour 
Aram Estiu Graugés   Animal vocalization analysis/synthesis   Jordi Janer and Jordi Bonada   July 1st   9:30  
S.I. Mimilakis   Voice quality modelling with the Wide-Band Harmonic Sinusoidal Modeling Algorithm   Jordi Bonada   July 1st   10:00  
Roger Rios Rubiras   A comparative study of speech dereverberation algorithms on music signals for interactive remixing applications   Stanislaw Gorlow and Jordi Janer   July 1st   10:30  
Oriol Romaní Picas   Score alignment in recordings from large ensembles   Julio J. Carabías-Orti and Jordi Janer   July 1st   11:15  
Charalambos Christopoulos   Augmented music performance by gestural recognition in 3D space using Polhemus sensors   Alfonso Perez   July 1st   11:45  
Giacomo Herrero Coli   Supervised music structure segmentation/annotation   Joan Serrà   July 2nd   9:30  
Toros Ufuk Senan   Preservation and study of ancient wood musical instruments stored in museums and conservatories.   Enric Guaus and Paul Poletti   July 2nd   10:00  
Nuno Hespanhol   Automatic Classification of Musical Sounds   Xavier Serra and Frederic Font   July 2nd   10:30  
Constantinos A. Dimitriou   Similarity Measures for Audio Classes   Xavier Serra and Frederic Font   July 2nd   11:15  
Vignesh Ishwar   Prominent pitch analysis for the study of vocal melodies in music   Xavier Serra   July 2nd   11:45  
Andrés Pérez López   Real time tools for 3d audio spatialization   Daniel Arteaga   July 3rd   9:30  
Nicholas Harley   Evaluation of Pitch-Class Set Similarity Measures for Tonal Analysis   Agustín Martorell   July 3rd   10:00  
Belén Nieto Núñez   Melody Extraction: addressing user satisfaction and context-awareness   Emilia Gómez   July 3rd   10:30  
Jorge A. Cuarón   Perceptual Validation of Chord Estimation Evaluation Standards   Agustín Martorell   July 3rd   11:15  
Jaime Parra Damborenea   ReactBlocks: A 3D Tangible Interface for Music Learning   Sergi Jordà and Cárthach Ó Nuanáin   July 4th   9:30  
Hazar Emre Tez   Symbolic Modular 2D GUIs with Physical Properties   Sergi Jordà and Cárthach Ó Nuanáin   July 4th   10:00  
Daniel Gómez Marín   Smart Percussive spaces   Sergi Jorda   July 4th   10:30  
Marcel Schmidt   A Musical Interface for People with Motor Disabilities   Zacharias Vamvakousis   July 4th   11:15  
Francisco Rodríguez Algarra   Audio-based computational stylometry for electronic music   Perfecto Herrera   July 4th   11:45  
Erim Yurci   Emotion detection from EEG signals: correlating cerebral cortex activity with music evoked emotion   Rafael Ramirez   July 4th   12:15  
Urbez Caplabo Harmony high level features Perfecto Herrera and Sergi Jordà  July 3rd  13:00


10 Jun 2014 - 17:03 | view
Xavier Serra receives the ICREA Academia price for the second time

Xavier Serra has received the ICREA Academia price, given by the Catalan Institution for Research and Advanced Studies, for the second time.

The ICREA Academia program recognizes the research excellence and leadership with the goal to motivate and retain university faculty members from the catalan public universities. ICREA is an institution of the catalan government that has as a fundamental objective to hire researchers from around the world through a selection process based on scientific talent.

4 Jun 2014 - 13:22 | view
Concert and lecture demonstration by the Gundecha Brothers
19 Jun 2014

On June 19th 2014 and in the context of CompMusic we are organizing a lecture demonstration and a concert of the Gundecha Brothers, which are among the most prominent singers of the Dhrupad music tradition of India.

Venue: Auditorium of the Conservatori Municipal de Música de Barcelona, Bruc 112, Barcelona

17.00h–18.45h. Lecture demonstration by the Gundecha Brothers on “Making of Voice & Raga in Indian Music” 

19.30h-20.00h. Presentation of the CompMusic project by Xavier Serra  

20.00h–21.45h. Dhrupad concert by the Gundecha Brothers

30 May 2014 - 13:31 | view
Seminar on repovizz at McGill

A seminar by Esteban Maestre, Marie Curie Fellow, McGill University + Universitat Pompeu Fabra;
With assistance by Quim Limona, Universitat Pompeu Fabra

DATE: Tuesday June 10, 2014 at 12:30pm
LOCATION: Room A832, New Music Building, 527 Sherbrooke Street West (CIRMMT)

ABSTRACTrepovizz is an integrated online system capable of structural formatting and remote storage, browsing, exchange, annotation, and visualization of synchronous multi-modal, time-aligned data. Motivated by a growing need for data-driven collaborative research, repovizz aims to resolve commonly encountered difficulties in sharing or browsing large collections of multi-modal datasets. At its current state, repovizz is designed to hold time-aligned streams of heterogeneous data: audio, video, motion capture, physiological signals, extracted descriptors, annotations, et cetera. Most popular formats for audio and video are supported, while CSV formats are adopted for streams other than audio or video (e.g. motion capture or physiological signals). The data itself is structured via customized XML files, allowing the user to (re-) organize multi-modal data in any hierarchical manner. Datasets are stored in an online database, allowing the user to interact with the data remotely through a powerful HTML5 visual interface accessible from any current web browser; this feature can be considered a key aspect of repovizz since data can be explored, annotated, or visualized from any location.

repovizz has been developed by the Music Technology Group of Universitat Pompeu Fabra in the context of large-scale research projects over the past few years, and now it is close to launching as beta. In this seminar we'll give an overview of the main capabilities of repovizz and its current state of development, followed by a short tutorial.

27 May 2014 - 09:39 | view
Sonar Festival 2014
12 Jun 2014 - 14 Jun 2014

Following the tradition, the MTG is behind a bunch of interesting events at Sonar Festival in Barcelona. For this year’s edition, that will take place from June 12th to 14th at Fira de Montjuïc, the MTG organises a great number of activities in the frame of the Sonar+D section.


Music Hack Day (MHD) – Thursday, June 12th at 9AM to 13th at 6PM (Thu to Fri)

This year’s edition presents news and some changes, here’s a little flavour of what’s happening:

  • We count with the participation of 20 amazing and innovative technologies, like the kickstarter Mogees that turns daily objects into music instruments or Xth sense that allows the sonification of muscles (among others).
  • The Giant Steps European project plays an important role this year, sending two challenges to hackers and carrying out user studies to better understand the creative process that participants follow for the conceptualisation of their hacks.
  • Thanks to the collaboration with Made makerspace, we’re facilitating the onsite design and manufacturing of anything needed by hackers.
  • Wayra, the popular startup incubator, is also putting their two cents in the MHD by helping hackers preparing the 3’ presentations.

We are really grateful to our sponsors for helping us putting this edition on: 7Digital, Deezer, GiantSteps, Kiics, MusixMatch, Native Instruments, Patchblocks, Rdio, Sendgrid, TECNIO and Universal Music.

Check out the MHD website for further details

‘MTG & FRIENDS’ stand at Market Lab – from June 12th to 14th (Thu to Sat)

Exhibition of several installations and demos of our technologies, spin-offs, students and Phonos-MTG grant:

With the occasion of the 5th anniversary of the Music Hack Day initiative, we are also exhibiting in our stand some of the best hacks in MHD since its first edition in London 2009. The list of best hacks was carefully selected by a group of MHD veterans and experts and is as follows:

Together with the selection of the best hacks, people visiting the MTG stand will also have the chance to try new interactive musical interfaces based on brain activity. Two of the hacks developed within the Neuro-track in last year’s MHD will be expanded both in technological and business aspects. The two selected applications are Play your Mood, a music explorer based on the users’ emotional states, and BrainLoops, a musical interface for patients with locked-in syndrome.

These projects will be technologically supported by Starlab, whereas Barcelona Activa will provide business support to the selected creators. This initiative is promoted by KiiCS, and the Observatori de Comunicació Científica (OCC) of UPF.

Further details available here.

Giant Steps panel discussion – June 12th (Thu) from 18.30 to 19.30

Sergi Jordà, Principal Investigator of the project, will chair a panel discussion about several topics related to the Giant Steps project in which will participate two experts in electronic instruments design from Native Instruments experts and two Red Bull Music Academy musicians.

Check out the GiantSteps project website for further details

Spectral Diffractions – Mies van der Rohe pavilion – June 12th to 14th (Thu to Sat)

The SMC master student Antònio Sa Pinto collaborates with the artist Edwin van der Heide in the sound installation “Spectral Diffractions”.

Further details available in the Sonar's website

21 May 2014 - 19:12 | view
new COFLA project

The MTG contributes to a new project on Computational Analysis of Flamenco Music (COFLA) coordinated by José Miguel Díaz Bañez (Escuela Técnica Superior de Ingeniería - Universidad de Sevilla) and funded by the Andalusian Government. The project started in February 2014 and has a duration of 4 years.

The MTG tasks will be devoted to of automatic transcription, similarity computation, automatic classification and synthesis of flamenco singing. Researchers involved are Nadine Kroher, Jordi Bonada, Sergio Oramas & Emilia Gómez.

Feb 2014-Feb 2018. COFLA2: Análisis Computacional de la Música Flamenca, Proyectos de Excelencia de la Junta de Andalucía, P12-TIC-1362

14 Mar 2014 - 09:43 | view
New IEEE/ACM TASP paper on multi-feature beat tracking

Our article on multi-feature beat tracking for the IEEE/ACM Transactions on Audio, Speech and Language Processing is now available online! This is a work carried leaded by Jose R. Zapata for his PhD thesis in collaboration with Mathew Davies from the SMC group in Porto, based on the idea of combining different experts, represented by periodicity from different onset detection functions, for beat estimation. This is a simple and clever idea, already used to combine different beat tracking algorithms and evaluate the difficulty of the task, that has been integrated in a different method.

Zapata, J. R., Davies M. E. P., & Gómez E. (2014). Multi-feature beat tracking. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 22(4), 816 – 825. RTF, Tagged, XML, BibTex, Google Scholar

Abstract: A recent trend in the field of beat tracking for musical audio signals has been to explore techniques for measuring the level of agreement and disagreement between a committee of beat tracking algorithms. By using beat tracking evaluation methods to compare all pairwise combinations of beat tracker outputs, it has been shown that selecting the beat tracker which most agrees with the remainder of the committee, on a song-by-song basis, leads to improved performance which surpasses the accuracy of any individual beat tracker used on its own. In this paper we extend this idea towards presenting a single, standalone beat tracking solution which can exploit the benefit of mutual agreement without the need to run multiple separate beat tracking algorithms. In contrast to existing work, we re-cast the problem as one of selecting between the beat outputs resulting from a single beat tracking model with multiple, diverse input features. Through extended evaluation on a large annotated database, we show that our multi-feature beat tracker can outperform the state of the art, and thereby demonstrate that there is sufficient diversity in input features for beat tracking, without the need for multiple tracking models.

27 Feb 2014 - 20:51 | view
Melody Extraction Review published in the IEEE Signal Processing Magazine

Our review article on melody extraction algorithms for the IEEE Signal Processing Magazine is finally available online! The printed edition will be coming out in March 2014. This article provides an overview of approaches, challenges and applications for melody extraction from polyphonic music signals.

J. Salamon, E. Gómez, D. P. W. Ellis and G. Richard, “Melody Extraction from Polyphonic Music Signals: Approaches, Applications and Challenges“, IEEE Signal Processing Magazine, 31(2):118-134, Mar. 2014.

Abstract: Melody extraction algorithms aim to produce a sequence of frequency values corresponding to the pitch of the dominant melody from a musical recording. Over the past decade melody extraction has emerged as an active research topic, comprising a large variety of proposed algorithms spanning a wide range of techniques. This article provides an overview of these techniques, the applications for which melody extraction is useful, and the challenges that remain. We start with a discussion of ‘melody’ from both musical and signal processing perspectives, and provide a case study which interprets the output of a melody extraction algorithm for specific excerpts. We then provide a comprehensive comparative analysis of melody extraction algorithms based on the results of an international evaluation campaign. We discuss issues of algorithm design, evaluation and applications which build upon melody extraction. Finally, we discuss some of the remaining challenges in melody extraction research in terms of algorithmic performance, development, and evaluation methodology.

17 Feb 2014 - 13:00 | view