News and Events

Participation to AdMIRe 2012

Justin Salamon, Martin Haro, Mohamed Sordo and Xavier Serra participate to the 4th International Workshop on Advances in Music Information Research: "The Web of Music" (AdMIRe 2012) that takes place in Lyon on April 17th 2012, as part of the 21st International World Wide Web Conference (WWW 2102). The articles presented are:

14 Apr 2012 - 10:56 | view
Sounds of Barcelona in a EU contest

Our Sounds of Barcelona project is participating in a EU contest for best innovations related to technological iniciatives with an educational and social impact. The  project Sons de Barcelona was created as an educational initiative around Freesound.org, running workshops in schools to foster interest in music technologies among the students community by using the Freesound ideas and technologies. You can find more information about the contest entry in: http://engageawards.com/entry/68

If you think that Sounds of Barcelona is a good initiative worth promoting, please vote for it.

4 Apr 2012 - 09:35 | view
Freesound survey

As part on our research work in understanding the Freesound community for improving the platform that suports it, we are conducting a small survey to better understand the user's motivations for using Freesound. The survey and the user responses are in the Freesound Forum.

21 Mar 2012 - 10:35 | view
Phonos Concert: with Carlos Vaquero
On Tuesday March 20th 2012 at 19:30h in the Espai Polivalent of the Communication Campus of the UPF, Phonos is organizing a concert with Carlos Vaquero.
15 Mar 2012 - 15:50 | view
Seminar by Andre Holzapfel on beat tracking

Andre Holzapfel, from INESC Porto, gives a talk entitled "Selective sampling for beat tracking evaluation" on Friday March 2nd at 4pm in room 55.410.

Abstract: An approach is presented that identifies music samples which are difficult for current state-of-the-art beat trackers. In order to estimate this difficulty even for examples without ground truth, a method motivated by selective sampling is applied. This method assigns a degree of difficulty to a sample based on the mutual dis-agreement between the output of various beat tracking systems. On a large beat annotated dataset we show that this mutual agreement is correlated with the mean performance of the beat trackers evaluated against the ground truth, and hence can be used to identify difficult examples by predicting poor beat tracking performance. Towards the aim of advancing future beat tracking systems, we form a new dataset containing a high proportion of challenging music examples based on our method. We analyze the relations between perceptual difficulty and difficulty for automatic beat tracking using these data, and propose which signal properties are characterized by the highest potential of improvement of automatic beat tracking.

24 Feb 2012 - 09:58 | view
Phonos: Concert Michal Rataj & Ladislav Železný
On Wednesday February 29th 2012 at 19:30h in the Espai Polivalent of the Communication Campus of the UPF, Phonos is organizing a concert of Michal Rataj & Ladislav Železný.
23 Feb 2012 - 15:40 | view
Mohamed Sordo defends his PhD thesis on February 27th
Mohamed Sordo defends his PhD thesis entitled "Semantic Annotation of Music Collections: A Computational Approach" on Monday 27th of February 2012 at 11:00h in room 55.309.

The members of the jury's defense are:  Rafael Ramirez (UPF), Josep Lluis Arcos (IIIA-CSIC), Markus Schedl (Johannes Kepler University Linz).

Thesis abstract: Music consumption has changed drastically in the last few years. With the arrival of digital music, the cost of production has substantially dropped. The expansion of the World Wide Web has helped to promote the exploration of many more music content. Online stores, such as iTunes or Amazon, own music collections in the order of millions of songs. Accessing these large collections in an effective manner is still a big challenge.

In this dissertation we focus on the problem of annotating music collections with semantic words, also called tags. The foundations of all the methods used in this dissertation are based on techniques from the fields of information retrieval, machine learning, and signal processing. We propose an automatic music annotation algorithm that uses content-based audio similarity to propagate tags among songs. The algorithm is evaluated extensively using multiple music collections of varying size and quality of the data, including a large music collection of more than a half million songs, annotated with social tags derived from a music community. We assess the quality of our proposed algorithm by comparing it with several state of the art approaches. We also discuss the importance of using evaluation measures that cover different dimensions; per–song and per–tag evaluation. Our proposal achieves state of the art results, and has ranked high in the MIREX 2011 evaluation campaign. The obtained results also show some limitations of automatic tagging, related to data inconsistencies, correlation of concepts and the difficulty to capture some personal tags with content information. This is more evident in music communites, where users can annotate songs with any free text word. In order to tackle these issues, we present an in-depth study of the nature of music folksonomies. We concretely study whether tag annotations made by a large community (i.e. a folksonomy) correspond with a more controlled, structured vocabulary by experts in the music and the psychology fields. Results reveal that some tags are clearly defined and understood both by the experts and the wisdom of crowds, while it is difficult to achieve a common consensus on the meaning of other tags. Finally, we extend our previous work to a wide range of semantic concepts. We present a novel way to uncover facets implicit in social tagging, and classify the tags with respect to these semantic facets. The latter findings can help to understand the nature of social tags, and thus be beneficial for further improvement of semantic tagging of music.

Our findings have significant implications for music information retrieval systems that assist users to explore large music collections, digging for content they might like.

20 Feb 2012 - 10:08 | view
Seminar by Volker Hohmann on hearing device technology

Volker Hohmann, from the University of Oldenburg in Germany, gives a talk on "Trends in Hearing Device Technology" on Tuesday February 21st 2012 at 12:00pm in room 55.410.

Abstract: Currently about 18% of the European population suffers from hearing loss and this percentage is steadily increasing due to the demographic aging trend. Hearing loss is associated with minor to severe limitations in acoustic communication and therefore limits participation in social life. Most complaints allude to difficulties in understanding speech in noisy and reverberant environments, limited communication over the phone, and almost all hearing impaired report problems with perceiving and enjoying music. Due to the technological progress of the last decades, hearing devices have improved significantly, and the ever-growing computational capabilities of digital hearing devices offers a promising future. Still, the current technology does not allow a complete hearing loss rehabilitation: In mild hearing losses, an individual audio amplification would be helpful to alleviate most communication problems, but current consumer technology such as TVs, mobile phones, MP3 players and public announcement systems does not support even basic individualized audio amplification. In cases of mild to moderate hearing losses, which are commonly treated with acoustic hearing aids, the challenge is to provide a sufficient improvement in the signal-to-noise ratio to restore speech communication in acoustically challenging situations and to individually modify music with the aim of making music consumption enjoyable again. In the less frequent cases of severe to profound hearing losses or deafness, which are usually treated with cochlear implants (a biomedical device that activates the acoustic nerve electrically by implanted electrodes), all previously mentioned communication problems are more pronounced. This calls for further research into device technology and improved signal processing. In my talk, I will give an overview of the current technology of hearing devices and discuss the major research challenges and promising approaches for a further improvement of the rehabilitation of hearing loss.

Biography: Volker Hohmann received the doctorate degree in Physics (Dr. rer. nat.) from the University of Göttingen, Germany in 1993. Since then, he has been a faculty member of the Physics Institute at the University of Oldenburg, Germany, and member of the Medical Physics Group (head: B. Kollmeier). He is active in undergraduate and graduate teaching in Physics, and his research expertise is in Acoustics and Digital Signal Processing with applications to signal processing in speech processing devices, e. g., Hearing Aids. In the private sector, he is head of R&D at HoerTech gGmbH, a leading non-profit research institute in the field of audiological and acoustical developments related to hearing systems. He was a guest researcher at Boston University, Boston, USA in 2000 and at the Technical University of Catalonia, Barcelona, Spain in 2008/2009. Dr. Hohmann obtained the Habilitation (maximum academic degree in Germany) in Applied Physics in 2007 and received the Lothar-Cremer price of the German acoustical society (DEGA) in 2008 for outstanding contributions to audiological acoustics and signal processing.

17 Feb 2012 - 18:44 | view
Phonos: Barcelona Laptop Orchestra Concert

On Thursday February 23rd 2012 at 19:30h in the Espai Polivalent of the Communication Campus of the UPF, Phonos is organizing a concert of the Barcelona Laptop Orchestra.

16 Feb 2012 - 17:19 | view
2nd CompMusic Workshop: call for participation

Dates: July 12th-13th, 2012
Venue: Bahçeşehir Üniversitesi, Istanbul
Scientific committee: Xavier Serra, Preeti Rao, Hema Murthy, Bariş Bozkurt
More info: http://compmusic.upf.edu

CompMusic is a research project funded by the European Research Council and coordinated by Xavier Serra from the Music Technology Group of the Universitat Pompeu Fabra in Barcelona (Spain). It aims to advance in the automatic description of music, reducing the gap between audio signal features and semantically meaningful music concepts by taking a culture-specific perspective. It focuses on the study of five art-music traditions around the world: Hindustani and Carnatic (India), Turkish-makam, Andalusian (Arab countries) and Han (China).

This second workshop will cover all the topics of relevance to CompMusic, bringing together the researchers already working in the project plus researchers willing to contribute to the specific problems identified. We are specially interested in musicological contributions from any of the identified cultures. A selection of the articles presented in the workshop will be published as a special issue in the Journal of New Music Research.

All proposed papers should relate to one of the five art-music traditions in aspects like: general musicological studies; culture specific semantic analysis; melodic and rhythmic analysis; culture specific music similarity; or community profiling.

Interested participants should send an abstract of the proposed papers to xavier [dot] serra [at] upf [dot] edu (Xavier Serra) before March 30th 2012.

13 Feb 2012 - 17:31 | view
intranet