News and Events

Seminar by P. Toiviainen, G. Peeters, J.P. Bello and F. Gouyon
19 Sep 2013

Petri Toiviainen (University of Jyväskylä), Geoffroy Peeters (IRCAM), Juan Pablo Bello (NYU) and Fabien Gouyon (INESC Porto) will give a seminar on their current research on Thursday September 19th at 15:00h in room 55.410.

More info:

18 Sep 2013 - 10:49 | view
Justin Salamon defends his PhD thesis
20 Sep 2013

Justin Salamon defends his PhD thesis entitled "Melody Extraction from Polyphonic Music Signals" on Friday 20th of September 2013 at 10:00h in room 55.390.

The jury members of the defense are: Geoffroy Peeters (IRCAM), Fabien Gouyon (INESC-Porto), Juan Bello (NYU).

Abstract:  Music was the first mass-market industry to be completely restructured by digital technology, and today we can have access to thousands of tracks stored locally on our smartphone and millions of tracks through cloud-based music services. Given the vast quantity of music at our fingertips, we now require novel ways of describing, indexing, searching and interacting with musical content. In this thesis we focus on a technology that opens the door to a wide range of such applications: automatically estimating the pitch sequence of the melody directly from the audio signal of a polyphonic music recording, also referred to as melody extraction. Whilst identifying the pitch of the melody is something human listeners can do quite well, doing this automatically is highly challenging. We present a novel method for melody extraction based on the tracking and characterisation of the pitch contours that form the melodic line of a piece. We show how different contour characteristics can be exploited in combination with auditory streaming cues to identify the melody out of all the pitch content in a music recording using both heuristic and model-based approaches. The performance of our method is assessed in an international evaluation campaign where it is shown to obtain state-of-the-art results. In fact, it achieves the highest mean overall accuracy obtained by any algorithm that has participated in the campaign to date. We demonstrate the applicability of our method both for research and end-user applications by developing systems that exploit the extracted melody pitch sequence for similarity-based music retrieval (version identification and query-by-humming), genre classification, automatic transcription and computational music analysis. The thesis also provides a comprehensive comparative analysis and review of the current state-of-the-art in melody extraction and a first of its kind analysis of melody extraction evaluation methodology.

17 Sep 2013 - 15:59 | view
ONA, a catalan virtual singer at La Mercè
20 Sep 2013 - 24 Sep 2013

This week the first catalan virtual singer ONA will perform at Parc de la Ciutadella for the festivities of the saint patron of Barcelona (La Mercè). She will sing and dance together with other virtual singers (Bruno & Clara). People from the audience can get to the stage and control the performance of the virtual characters live using a kinect sensor. In addition, Ona will sing short poems selected from the tweets sent with hash tags #OnaEstiu #OnaFesta #OnaCiutat and #OnaFutur, which correspond to summer, party, city and future subjects.

Voctro Labs is preparing the concert and providing the virtual singers. You can check the following link for more details (in catalan).

16 Sep 2013 - 10:04 | view
José R. Zapata defends his PhD thesis
19 Sep 2013

José R. Zapata defends his PhD thesis entitled "Comparative Evaluation and Combination of Automatic Rhythm Description Systems" on Thursday 19th of September 2013 at 16:00h in room 55.410.

The jury members of the defense are: Fabien Gouyon (INESC-Porto), Juan Bello (NYU), Xavier Serra (UPF).

Abstract: The automatic analysis of musical rhythm from audio, and more specifically tempo and beat tracking, is one of the fundamental open research problems in Music Information Retrieval (MIR) research. Automatic beat tracking is a valuable tool for the solution of other MIR problems, as it enables beat-synchronous analysis of music for tasks such as: structural segmentation, chord detection, music similarity, cover song detection, automatic remixing and interactive music systems. Even though automatic rhythm description is a relatively mature research topic in MIR and various algorithms have been proposed, tempo estimation and beat tracking remain an unsolved problem. Recent comparative studies of automatic rhythm description systems suggest there has been little improvement in the state of the art over the last few years. In this thesis, we describe a new method for the extraction of beat times with a confidence value from music audio, based on the measurement of mutual agreement between a committee of beat tracking systems. Additionally, we present an open source variant of the approach which only requires a single beat tracking model and uses multiple onset detection functions for the mutual agreement. The method can also be used identify music samples that are challenging for beat tracking without the need for ground truth annotations. Using the proposed method, we compile a new dataset that consists of pieces that are dicult for state-of-the-art beat tracking algorithms. Through an international evaluation framework we show that our method yields the highest AMLc and AMLt accuracies obtained in this evaluation to date. Moreover, we compare our method to 20 reference systems using the largest existing annotated dataset for beat tracking and show that it outperforms all the other systems under all the evaluation criteria used. In the thesis we also conduct an extensive comparative evaluation and combination of automatic rhythm description systems. We evaluate 32 tempo estimation and 16 beat tracking state-of-the-art systems in order to identify their characteristics and investigate how they can be combined to improve performance. Finally, we propose and evaluate the use of voice suppression algorithms for music signals with predominant vocals in order to improve the performance of existing beat tracking methods.

16 Sep 2013 - 09:10 | view
Agustin Martorell defends his PhD thesis
19 Sep 2013

Agustín Martorell defends his PhD thesis entitled "Modelling tonal context dynamics by temporal multi-scale analysis" on Thursday 19th of September 2013 at 10:00h in room 55.410.

The jury members of the defense are: Petri Toiviainen (University of Jyväskylä), Geoffroy Peeters (IRCAM), Sergi Jordà (UPF).

Abstract: This work explores the multidimensional, ambiguous and temporal characteristics of tonality from a holistic perspective. The approach relies on interfacing pitch-spaces with time vs. time-scale descriptions. In this combined representation, the spatial and temporal hierarchies of tonality are evidenced simultaneously and in relation to each other. A visual exploration method is proposed for the analysis of tonal context in music works, using a simple model of tonal induction. A geometrical colouring solution, based on the topology of the pitch-space, approaches the perceptual correlation between the tonal properties and the visual representation. A relational taxonomy is proposed for describing tonal ambiguity, which leads to extending the method for the analysis of music based on tonal systems beyond the major-minor paradigm. Two perceptual studies are approached from this descriptive framework. The first study evidences the impact of time-scale in a simple model of tonal induction, and analyses the mathematical artefacts introduced by evaluations in scaled spaces. In the second study, a model of contextual instability is proposed and discussed in relation to the modelling of tonal tension. The analysis and representation methods are then generalised, through a set-class theoretical domain, in order to be applied with any pitch-based music.

16 Sep 2013 - 08:55 | view
6 PhD thesis defenses in 15 days!!!
In the next 15 days we have the defense of six PhD thesis done at the MTG!!!
September 6th - Dmitry Bogdanov: "From Music Similarity to Music recommendation: Computational Approaches based on Audio and Metadata Analysis"
September 9th - Ricard Marxer: "Audio Source Separation for Music in Low-latency and High-latency Scenarios" 
September 10th - Saso Musevic: "Non-stationary Sinusoidal Analysis" 
September 19th -  Agustin Martorell: "Modelling Tonal Context Dynamics by Temporal Multi-scale Analysis"
September 19th  - Jose R. Zapata: "Comparative Evaluation and Combination of Automatic Rhythm Description Systems"
September 20th - Justin Salamon: "Melody Extraction from Polyphonic Music Signals"
6 Sep 2013 - 16:27 | view
Saso Musevic defends his PhD thesis on September 10th
10 Sep 2013
Saso Musevic defends his PhD thesis entitled "Non-stationary sinusoidal analysis" on Tuesday 10th of September 2013 at 11:00h in room 55.309.

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

Abstract: Many types of everyday signals fall into the non-stationary sinusoids category. A large family of such signals represent audio, including acoustic/electronic, pitched/transient instrument sounds, human speech/singing voice, and a mixture of all: music. Analysis of such signals has been in the focus of the research community for decades. The main reason for such intense focus is the wide applicability of the research achievements to medical, financial and optical applications, as well as radar/sonar signal processing and system analysis. Accurate estimation of sinusoidal parameters is one of the most common digital signal processing tasks and thus represents an indispensable building block of a wide variety of applications. Classic time-frequency transformations are appropriate only for signals with slowly varying amplitude and frequency content - an assumption often violated in practice. In such cases, reduced readability and the presence of artefacts represent a signi ficant problem. Time and frequency resolution cannot be increased arbitrarily due to the well known time-frequency resolution trade-o ff by Heisenberg. The main objective of this thesis is to revise and improve existing methods, and to propose several new approaches for the analysis of non-stationary sinusoids. This dissertation substantially contributes to the existing sinusoidal analysis algorithms: a) it critically evaluates and disseminates in great detail current analysis methods, b) provides signi ficant improvements for some of the most promising existing methods, c) proposes several new approaches for analysis of the existing sinusoidal models and d) proposes a very general and flexible sinusoidal model together with a fast, direct estimator.

6 Sep 2013 - 16:19 | view
Seminar by Axel Roebel and Emmanuel Vincent
9 Sep 2013

Axel Roebel from IRCAM and Emmanuel Vincent from Inria Nancy will give a seminar on Monday 9th of September 2013 at 16:00h in room 55.309

Axel will present an overview of the research carried out during the last five years at the Analysis-Synthesis team at IRCAM.
Emmanuel will introduce his recent work on symbolic music modeling with interpolated probabilistic models.

Axel Roebel is the head of the Analysis-Synthesis team at IRCAM
Emmanuel Vincent is an experienced research scientist at Inria Nancy - Grand Est

6 Sep 2013 - 15:33 | view
Agreement for students exchange with IIT-Madras

The negotiation of the partnership agreement between the MTG and the Department of Science and Engineering at  IIT-Madras (Chennai, India) ended last July and it is related to the collaboration previously established between both groups over the performance of the CompMusic project. This project is funded by the European Research Council (ERC) and lead by Prof. Xavier Serra and it aims to advance in the automatic description of music by taking a culture specific approach. It focuses on five non occidental music traditions belonging to China, India, North Africa and Turkey. Two of them, the Hindustani and the Carnatic have the origin in the north of India and the south of India respectively.

According to the agreement clauses, both institutions will exchange students with the idea to keep a constant flux of visitors between them. Faculty members from both institutions have committed themselves to supervise the students that will participate in a research program of common interest for the two groups.

Student Exchange Conditions

This specific agreement may be also renewed and it will actually remain in effect until 2018. Moreover, it will cover the participation of students that are pursuing a research project as part of their degree (B. Tech, M. Tech, M. Sc., PhD or equivalent)
Each part agreed to accept up to three students per academic year and each participant may not spend more than one academic year in the exchange program. Although the host institution will reserve the right to make final judgment on the admission of the shortlisted candidates, following the agreement terms, the participant students will be selected by the home institution.

Next steps

The idea that MTG has is to replicate this exchange agreement with the different institutions taking part in the CompMusic project, such as the Indian Institute of Technology in Bombay or the Bahçeşehir Üniversitesi in Turkey.

The initiative promoted by MTG-UPF faculty and research members launches a new academic and research collaboration program that it will not just enhance the student exchange, but also the culture enrichment and the science knowledge in the music technology field.

6 Sep 2013 - 11:54 | view
Emilia Gómez, Perfecto Herrera and Paco Gómez, editors of a JNMR Special Issue

The goal of this special issue is to gather relevant, high-quality research on computational methods and applications in ethnomusicology. The papers included here deal with different musical facets such as pitch, pulse and tempo, and voice timbre. They address different musical repertoires, from Central-African to Basque folk music. They also cover a broad area: tools, including data collections, methodology and Ethnomusicology core-problems.

The list of articles include:

5 Sep 2013 - 08:47 | view