News and Events

Ricard Marxer defends his PhD thesis on September 9th
9 Sep 2013

Ricard Marxer defends his PhD thesis entitled "Audio Source Separation for Music in Low-latency and High-latency Scenarios" on Monday 9th of September 2013 at 11:00h in room 55.309.

The jury members of the defense are: Axel Roebel (IRCAM), Emmanuel Vincent (INRIA), Oscar Camara (UPF).

Abstract: The source separation problem in digital signal processing consists in finding the original signals that were mixed together into a set of mixture signals. Solutions to this problem have been extensively studied for the speci fic case of musical signals, however their application to real-world practical situations remains infrequent. There are two main obstacles for their widespread adoption depending on the scenario. The main limitation in some cases is their high latency and computational requirements. In other cases the quality of the results is still unacceptable. There has been extensive work on improving the quality of music separation, but few studies have been devoted to the development of low-latency and low computational cost separation of monaural music signals. We propose speci fic methods to address these issues in each of these scenarios independently. First, we focus on methods with low computational cost and low latency. We propose the use of Tikhonov regularization as a method for spectrum decomposition in the low-latency context. We compare it to existing techniques in pitch and multipitch estimation and tracking tasks, which are a crucial step in many separation methods. We then use the proposed spectrum decomposition method in low-latency music separation tasks targeting singing voice, bass and drums. Second, we develop methods that achieve improved separation results with respect to existing state-of-the-art methods at the cost of greater computational cost and higher latency. We propose several high-latency and computationally complex methods that improve the separation of singing voice, by modeling components that are often not accounted for, such as breathiness and the consonants. Finally we explore the use of temporal correlations and human annotations to enhance the separation of drums and complex polyphonic music signals.

5 Sep 2013 - 09:26 | view
Dmitry Bogdanov defends his PhD thesis on September 6th
6 Sep 2013

Dmitry Bogdanov defends his PhD thesis entitled "From music similarity to music recommendation: Computational approaches based on audio and metadata analysis" on Friday 6th of September 2013 at 11:00h in room 55.309.

The jury members of the defense are: Markus Schedl (Johannes Kepler University), Josep Lluis Arcos (IIIA-CSIC), Emilia Gómez (UPF).

Abstract: The amount of music available digitally is overwhelmingly increasing. Vast amounts of music are available for listeners, and require automatic organization and filtering. In this context, user modeling, which consists in customization and adaptation of systems to the user's specific needs, is a challenging fundamental problem. A number of music applications are grounded on user modeling to provide users a personalized experience. In the present work we focus on user modeling for music recommendation, and propose a preference elicitation technique in conjunction with different recommendation approaches. We develop algorithms for computational understanding and visualization of music preferences. Our approaches employ algorithms from the fields of signal processing, information retrieval, machine learning, and are grounded in cross-disciplinary research on user behavior and music. Firstly, we consider a number of preference elicitation strategies, and propose a user model starting from an explicit set of music tracks provided by this user as evidence of his/her preferences. The proposed strategy provides a noise-free representation of music preferences. Secondly, we study approaches to music similarity, working solely on audio content. We propose a novel semantic measure which benefits from automatically inferred high-level description of music. Moreover, we complement it with low-level timbral, temporal, and tonal information and propose a hybrid measure. The proposed measures show significant improvement, compared to common music similarity measures, in objective and subjective evaluations. Thirdly, we propose distance-based and probabilistic recommendation approaches working with explicitly given preference examples. Both content-based and metadata-based approaches are considered. The proposed methods employ semantic and hybrid similarity measures as well as they build semantic probabilistic model of music preference. Further filtering by metadata is proposed to improve results of purely content-based recommenders. Moreover, we propose a lightweight approach working exclusively on editorial metadata. Human evaluations show that our approaches are well-suited for music discovery in the long tail, and are competitive with metadata-based industrial systems. Fourthly, to provide insights on the nature of music preferences, we create regression models explaining music preferences of our participants and demonstrate important predictors of their preference from both acoustical and semantic perspectives. The obtained results correlate with existing research on music cognition. Finally, we demonstrate a preference visualization approach which allows to enhance user experience in recommender systems.

3 Sep 2013 - 09:47 | view
Presentation of DREANSS dataset at DAFX'2013

The 16th International Conference on Digital Audio Effects DAFx 2013 is held in Maynooth, September 2-5 2013. MTG researchers Ricard Marxer and Jordi Janer participate with four papers related to different works on Audio Source Separation (voice breathiness, voice fricatives, bass and drums).

A new dataset of audio recordings manual annotations will be published during DAFX'13. DREANSS (DRum Event ANnotations for Source Separation) aims to help develop research in source separation methods for polyphonic audio music mixtures containing drums.

2 Sep 2013 - 10:05 | view
Participation to SSW8

Xavier Serra and Martí Umbert participate to the 8th ISCA Speech Synthesis Workshop (SSW8) that takes place in Barcelona from August 31st to  September 2nd, 2013. Xavier gives a keynote on "Singing voice synthesis in the context of music technology research" and Martí presents a paper on "Systematic database creation for expressive singing voice synthesis control".

  • Martí Umbert, Jordi Bonada, Merlijn Blaauw: "Systematic database creation for expressive singing voice synthesis control"
    Abstract: Systematic database creation for expressive singing voice synthesis control In the context of singing voice synthesis, the generation of the synthesizer controls is a key aspect to obtain expressive performances. In our case, we use a system that selects, transforms and concatenates units of short melodic contours from a recorded database. This paper proposes a systematic procedure for the creation of such database. The aim is to cover relevant style-dependent combinations of features such as note duration, pitch interval and note strength. The higher the percentage of covered combinations is, the less transformed the units will be in order to match a target score. At the same time, it is also important that units are musically meaningful according to the target style. In order to create a style-dependent database, the melodic combinations of features to cover are identified, statistically modeled and grouped by similarity. Then, short melodic exercises of four measures are created following a dynamic programming algorithm. The Viterbi cost functions deal with the statistically observed context transitions, harmony, position within the measure and readability. The final systematic score database is formed by the sequence of the obtained melodic exercises.
  • Xavier Serra: "Singing voice synthesis in the context of music technology research"
    Abstract: The synthesis of the singing voice has always been very much tied to speech synthesis. Since the initial work of Max Mathews with Kelly and Lochbaum at Bell Labs in the 1950s many engineers and musicians have explored the potential of speech processing techniques in music applications. After reviewing some of this history I will present the work done in my research group to develop synthesis engines that could sound as natural and expressive as a real singer, or choir, and whose inputs could be just the score and the lyrics of the song. Some of this research is being done in collaboration with Yamaha and has resulted in the Vocaloid software synthesizer. In the talk I want to make special emphasis on the specificities of the music context and thus on the technical requirements needed for the use of a synthesis techology in music applications.


30 Aug 2013 - 11:46 | view
Participation to SMAC/SMC 2013

Emilia Gómez, Enric Guaus, Jordi Bonada, Martí Umbert, Esteban Maestre and Xavier Serra participate at the SMAC/SMC join conference that takes place from July 30th to August 3rd 2013 in Stockholm (Sweden).

Xavier gives a keynote on "Exploiting Domain Knowledge in Music Information Research" which relates to the CompMusic project. Esteban presents his work on "Digital Modeling of Bridge Driving-point Admittances from Measurements on Violin-family Instruments" that he did during his stay at Stanford. Emilia has an invited paper to talk about the new PHENICX project: "PHENICX: Performances as Highly Enriched and Interactive Concert Experiences" and she also teaches in the summer school. Enric present a research done at the ESMUC on "Observed differences in rhythm between performances of classical and jazz violin students", and Jordi and Martí present a poster on "Generating Singing Voice Expression Contours Based on Unit Selection".

25 Jul 2013 - 12:37 | view
Galata Electroacoustic Orchestra

The MTG participates in the Galata Electroacoustic Orchestra project, a European Erasmus Intensive Programme coordinated by Conservatorio Niccolò Paganini. The institutions partnering in this project are Istanbul Bilgi Üniversitesi (Istanbul), Istanbul Teknik Üniversitesi (Istanbul), Universitat Pompeu Fabra (Barcelona) and Conservatorio Statale di Musica “G.P. da Palestrina” (Cagliari)

The GEO IP project (Galata Electroacoustic Orchestra) is inspired by the historical relations between Genova and Istanbul. The first edition of GEO is taking place in Genova between the 15th and 26th of July, 2013.

A total of 7 MTG PhD students and SMC master students are participating in workshops, labs and lectures about traditional music of the three involved countries (Turkey, Spain and Italy), focused on ethnomusicological, technological, performing and compositional disciplines.

The general objectives of GEO IP are:
- To create the Galata Electroacoustic Orchestra, a small group orchestra based on an idea of live collective composition;
- To merge of the Western Classical tradition of score based music and the Improvisational techniques, in particular of Turkish Maqam Music.

The project also includes a final concert of the Galata Electroacoustic Orchestra at old port of Genova on Friday 26th at 9PM.

23 Jul 2013 - 17:25 | view
Master thesis presentations

On June 25th, 26th, 27th and 28th 2013, there are the presentations of the thesis of the Sound and Music Computing Master that have been carried out during the academic year 2012-2013. The presentations take place in room 55.410 of the Tanger building.

Tuesday 25th June 2013

  • 12:15h. JAKUE LÓPEZ ARMENDÁRIZ: “Informed Source Separation for Multiple Instruments of Similar Timbre” (Supervisor: Jordi Janer)
  • 12:45h. ENRIC GINE: “Signal extraction and digital processing of historical mechanical recordings” (Supervisor: Jordi Janer)

Wednesday 26th June 2013

  • 10:00h. JAKAB PILASZANOVICH: “Generating a Tonal Recommendation System Based on Audio Files for the Reactable” (supervisor: Sergi Jordà)
  • 10:30h. WILLIAM MARLEY: “Gestural Processing in the Reactable as a method of Machine Improvisation” (supervisor: Sergi Jordà)
  • 11:00h. MACIÀ FORTEZA CRESPÍ: “An EEG-based Emotion-driven Music Control System” (supervisor: Rafael Ramirez)
  • 11:30. ALUIZIO BARBOSA DE OLIVEIRA: “Understanding your brain through sound: A customizable, multi-parametric auditory display technique for theta-alpha neurofeedback training” (Supervisor: Sergi Jordà)
  • 12:00h. ROBERT CLOUTH: “Mobile Augmented Reality as a Control Mode for Real-time Music Systems” (Supervisor: Sergi Jordà)
  • 12:30h. NADINE KROHER: “The Flamenco Cante: Automatic Characterization of Flamenco Singing by Analyzing Audio Recordings” (Supervisors: Rafael Ramirez and Emilia Gómez)

Thursday 27th June 2013

  • 10:00h. RAQUEL VICTORIA BAEZ FERNANDEZ: “Using infrared motion capture data to measure the bow pressing force in string quartet performance” (Supervisor: Esteban Maestre)
  • 10:30h. JIE CHEN: “Gesture Analysis and Recognition in String Quartet Performance” (Supervisor: Esteban Maestre)
  • 11:00h. KAINAN CHEN: “Characterization of Pitch Intonation in Beijing Opera Singing” (Supervisor: Xavier Serra)
  • 11:30h. HÉCTOR FLORÍA RODRÍGUEZ: “Expressive speech synthesis for a RadioDJ using Vocaloid and HMM's” (Supervisor: Jordi Bonada)
  • 12:00h. VARUN JEWALIKAR: “Improving automatic phonetic segmentation for creating singing voice synthesizer corpora” (Supervisor: Jordi Bonada)
  • 12:30h. HECTOR PARRA: “Study of robust pitch estimation with de-reverberation techniques” (Supervisor: Jordi Janer)

Friday 28th June 2013

  • 10:00h. FILIPPO MORELLI: “The bad and the good singer: query analysis and reformulation for audio to audio Query by Humming” (Supervisor: Emilia Gómez)
  • 10:30h. FELIPE NAVARRO: “Life Soundtrack Recovery for Alzheimer's disease patients” (Supervisors: Emilia Gómez and Perfecto Herrera)
  • 11:00h. JOSE JAVIER VALERO MAS: “Measuring similarity of automatically extracted melodic pitch contours for audio-based query by humming of polyphonic music collections” (Supervisor: Emilia Gómez)
  • 11:30h. GABRIEL MESEGUER: Automatic content-based detection of influences in the history of progressive rock music” (Supervisors: Joan Serrà and Perfecto Herrera)
  • 12:00h. DARA DARIBI: “Using clickthrough data to improve Freesound search” (Supervisor: Xavier Serra)
17 Jun 2013 - 15:56 | view
Seminar by Julio José Carabias on audio to score alignment
13 Jun 2013

Julio José Carabias Orti from University of Jaén will give a seminar titled "RealTime Audio to Score Alignment System using Spectral Factorization and Online Time Warping" on Thursday, June 13th, at 15.30 in room 52.321.

In this work, we present a realtime score follower based on spectral factorization and online Dynamic Time Warping (DTW). The presented system has two separated stages, preprocessing and alignment. On the first one, we convert the score into a reference audio signal using a MIDI synthesizer software and we analyze the provided information in order to obtain the spectral patterns (i.e. basis functions) associated to each combination of notes. These basis functions are learned from the synthetic MIDI signal using a method based on NMF with Beta-divergence where the gains are initialized as the ground- truth transcription inferred from the MIDI. On the second stage, a realtime signal decomposition method with fixed basis functions per combination of notes is used over the magnitude spectrogram of the input signal resulting in a distortion matrix that can be interpreted as the cost of the matching for each combination of notes at each frame. Finally, two online DTW approaches are proposed to find the path with the minimum cost and then determine the real duration of the MIDI states. Our system has been compared to other state-of the-art systems obtaining reliable results.


Julio José Carabias-Orti received the M.Sc. degree in computer science and the Doctor of Science degree from the University of Jaen, Jaen, Spain, in 2006 and 2011, respectively. He is currently working as a research fellow at the Telecommunication Engineering Department, University of Jaen. His research topics include automatic music transcription, sound source separation, factorization algorithms and machine learning.


7 Jun 2013 - 11:48 | view
Emilia Gómez gives a keynote speech at FMA workshop

Emilia Gómez has been invited to give a keynote speech at the 3rd International Workshop on Folk Music Analysis (FMA) that takes place in Amsterdam, Netherlands, June 6 and 7, 2013. The talk is on "Computer-Assisted Transcription and Description of Music Recordings".

The FMA 2013 is a forum to present and discuss ongoing research in the area of computational ethnomusicology.

5 Jun 2013 - 20:05 | view
Big participation at Sonar Festival 2013

As in the last few years, the MTG has an active participation in a number of activities at Sonar Festival in Barcelona. For this year’s edition, that will be held from June 13th to 15th, 2013 at Fira de Montjuïc, the MTG will drive several activities in the frame of the Sonar+D section, having a more relevant presence than in previous editions.


Music Hack Day (MHD) – Thursday, June 13th at 9AM to Friday 14th at 6PM: This edition of  MHD presents a special Neuro track (N+MHD) which aims at developing new applications interfacing music with the brain and other physiological signals. During the event, 24 amazing technologies (like Google glasses among others) will be presented and made available for 100 hackers. This MHD will happen thanks to the goodwill of 15 tech companies that are sponsoring the event.

Market Lab – Thursday, June 13th to Saturday 15th (everyday 12PM to 10PM): Exhibition of four interactive installations of students of UPF and Phonos grant:

Zoom Interactivo by Patricia Sanz and León David Cobo (CDSIM students)

Electro Bichos(CDSIM students)

Funambulista by Eva Domènech (MUAD student)

RdEs: Sonic Emergency Distributed Network by Oscar Martin (Phonos grant for creation)

Rethink the Music Innovation Summit – Thursday, June 13th from 4PM to 7PM– Panels Level 2: Sergi Jordà will be participating on this panel about the innovation in the music industry.

Barcelona Laptop Orchestra concert – Thursday, June 13th at 5PM – Sonar Complex: Live show performing with tablets.

Meet the Expert – Thursday, June 13th from 5PM to 7PM: Enric Guaus, researcher and teacher of the MTG and ESMUC will be participating in a Meet the Expert session.

Barcelona Laptop Orchestra demo – Friday, June 14th from 5PM to 5:30PM – Hands on Area: demo-workshop on how to make music with tablets.

Sinte ZA! MTG – Saturday, June 15th at 5PM – Hands on Area: The SMC student Hector Parra partners with the band ZA! to show the results of his master thesis in a demo-show.


Some MTG former members or collaborators also participate in Sonar+D activities:

Smplr – Thursday, June 13th to Saturday 15th (everyday 12PM to 10PM) – App Bar: by Marcos Alonso (former MTG researcher)

Billaboop: Vidibox – Thursday 13th at 5PM, Friday 14th at 3PM and Saturday 15th at 4PM – Hands on area: by Amaury Hazan (former MTG PhD student)

Motors & Music - Thursday 13th at 6:30PM, Friday 14th at 6:30PM and Saturday 15th at 6:30PM – Workshops area: this workshop was part of TEI’2013.

Creative Technologies Café – Friday 14th at 5PM – Panels Level 2: with Miguel García Risueño (former SMC student)

And more coming soon.

4 Jun 2013 - 18:27 | view