News and Events

Seminar by Gautham Mysore on Non-negative Hidden Markov Modeling of Audio

When and where? Thursday, Oct 4, 2012, 3:30pm, 52.321

Host: Xavier Serra (MTG)

Title: Non-negative Hidden Markov Modeling of Audio

Abstract:
Non-negative spectrogram factorization techniques have become quite popular in the last decade as they are effective in modeling the spectral structure of audio. They have been extensively used for applications such as source separation and denoising. These techniques however fail to account for non-stationarity and temporal dynamics, which are two important properties of audio. In this talk, I will introduce the non-negative hidden Markov model (N-HMM) and the non-negative factorial hidden Markov model (N-FHMM) to model single sound sources and sound mixtures respectively. They jointly model the spectral structure and temporal dynamics of sound sources, while accounting for non-stationarity. I will also discuss the application of these models to various applications such as source separation, denoising, and content based audio processing, showing why they yield improved performance when compared to non-negative spectrogram factorization techniques.

2 Oct 2012 - 17:49 | view
Big participation of MTG researchers at ISMIR 2012

12 papers discussing research done at the MTG are being presented at the 13th International Society for Music Information
Retrieval Conference, that takes place in Porto from October 8th to the 12th 2012. These are:

 

2 Oct 2012 - 10:07 | view
New graduate students at the MTG

This academic year 2012-2013, 19 students are starting the SMC Master, 7 students are doing the second year of the Master, and 4 students are starting the PhD.

First year Master students: Robert Clouth (UK), Jakab Pilaszanovich (Hungary), Jose Javier Valero (Spain), Filippo Morelli (Italy), Úrbez Capablo Riazuelo (Spain), Jie Chen (China), António Humberto Sá Pinto (Portugal), Gabriel Meseguer (Spain), Dara Dabiri (Iran), Ken Chen (China), William Thomas Marley (Irland), Oriol Romaní Picas (Spain), Adrià Casas Gimeno (Spain), Toshinao Ruike (Japan), Roger Rios Bubiras (Spain), Aram Estiu Graugés (Spain), Raquel Victoria Baez Fernández (Spain), Macià Forteza Crespí (Spain), Nadine Kroher (Austria).

Second year Master students: Aluizio Neto (Brazil), Enric Giné  (Spain), Felipe L. Navarro (Spain), Hector Floria (Spain), Jakue Lopez (Spain), Varun Jewalikar (India), Hector Parra (Spain).

PhD students: Juanjo Bosch (Spain), Sankalp Gulati (India), Ajay Srinivasamurthy  (India), Sergio Giraldo (Colombia).

23 Sep 2012 - 18:37 | view
UPF Social Council awards

The resolution of the 2012 Social Council Awards was published yesterday in the course of the opening ceremony of the Academic Course 2012-2013. We are very proud to announce that the following MTG members were awarded:

  • Award in recognition to Quality and innovation in teaching: Emilia Gómez and Justin Salamon
  • Award in recognition to the track-record in Technology Transfer: Jordi Bonada

Congratulations to the winners!!!

 

18 Sep 2012 - 19:33 | view
Gert Lanckriet, from UCSD, visits the MTG

He will meet MTG researchers and give a seminar at our department. Everyone is invited!


***

Gert Lanckriet, University of California, San Diego 

Wednesday, Sep 26, 2012, 12pm, 52.421

Host: Emilia Gómez (MTG)>

Title: Music Recommendation with Multi-Modal Metric Learning to Rank

<Abstract:
A revolution in music production, distribution and consumption made millions of songs available to virtually anyone on the planet, through the Internet. To allow users to retrieve the desired content from this nearly infinite pool of possibilities, algorithms for automatic music indexing and recommendation are a must.

In this talk, I will discuss two aspects of automated content-based music analysis for music search and recommendation: i) automated music tagging for semantic retrieval, and ii) a query-by-example paradigm for content-based music recommendation, wherein a user queries the system by providing a song, and the system responds with a list of relevant or similar song recommendations (e.g., playlist generation for online radio).

Query-by-example applications ultimately depend on the notion of similarity between items to produce high-quality results. Current state-of-the-art systems employ collaborative filter methods to represent musical items, effectively comparing items in terms of their constituent users. While collaborative filter techniques perform well when historical data is available for each item, their reliance on historical data impedes performance on novel or unpopular items. To combat this problem, we rely on content-based similarity, which naturally extends to novel items, but is typically out-performed by collaborative filter methods. In this talk, I will present a method for optimizing content-based similarity by learning from a sample of collaborative filter data. Finally, I will discuss how such algorithms may be adapted to improve recommendations if a variety of information besides musical content is available as well (e.g., music video clips, web documents and/or art work describing musical artists).

Biography:
Gert Lanckriet received a Master's degree in Electrical Engineering from the Katholieke Universiteit Leuven, Leuven, Belgium, in 2000 and the M.S. and Ph.D. degrees in Electrical Engineering and Computer Science from the University of California, Berkeley in 2001 respectively 2005. In 2005, he joined the Department of Electrical and Computer Engineering at the University of California, San Diego, where he heads the Computer Audition Lab. He was awarded the SIAM Optimization Prize in 2008 and is the recipient of a Hellman Fellowship, an IBM Faculty Award, an NSF CAREER Award and an Alfred P. Sloan Foundation Research Fellowship. In 2011, MIT Technology Review named him one of the 35 top young technology innovators in the world (TR35). His research focuses on the interplay of convex optimization, machine learning and applied statistics, with applications in computer audition and music information retrieval

18 Sep 2012 - 18:38 | view
VoctroLabs awarded by SIMO

Voctro Labs, our third spin-off company, was one of 14 start-ups winners of the 7th edition of 'Vivero 2012 award', organized by SIMO network. This award will allow Voctro to have a stand at the fair of the same name (SIMO) which takes place from 25 to 27 September in Madrid IFEMA Exhibition.

Voctro Labs has been recognized for their work in the development of audio and voice processing technologies applied to the entertainment sector. With this appointment Voctro Labs can earn 9,000 euros (a Special Prize awarded by Fundetec).

12 Sep 2012 - 10:10 | view
The MTG takes part in "Programa Professors i Ciència" (Fundació Catalunya Caixa)

The MTG collaborates in the "Programa Professors i Ciència" (Teachers & Science program), funded by Fundació Catalunya Caixa.

The program offers high-school teachers the opportunity of taking part in scientific specialization courses at research centers in Catalonia. In this way, the program aims to bring research closer to educational institutions at the secondary level. The MTG organizes a course on sound & nature that will take place in November.

 

7 Sep 2012 - 12:44 | view
Junior software engineer position at the MTG-UPF

This position will involve working together with researchers at the MTG-UPF in Barcelona to (1) maintain a multiplatform software infrastructure related to audio signal processing and music information processing and (2) implement novel algorithms for processing and interacting with music related data.

Required skills/qualifications:

  • Bachelor degree in Computer Science or similar educational qualification

  • Proficiency in both written and spoken English
  • Proficiency in Python and C/C++

  • Familiarity with concepts of audio signal processing and machine learning
  • Experience in working with databases and large datasets
  • Demonstrated ability to write maintainable, well-documented software and documentation

Preferred skills/experience:

  • Experience with Git (or other VSC) and Octave/Matlab
  • Passion for music and audio
  • 
Participation in open source software projects

 
ABOUT MTG-UPF:

The Music Technology Group of the Universitat Pompeu Fabra is a leading research group with more than 40 researchers, carrying out research on topics such as audio signal processing, sound and music description, musical interfaces, sound and music communities, and performance modeling. The MTG wants to contribute to the improvement of the information and communication technologies related to sound and music, carrying out competitive research at the international level and at the same time transferring its results to society. To that goal, the MTG aims at finding a balance between basic and applied research while promoting interdisciplinary approaches that incorporate knowledge from both scientific/technological and humanistic/artistic disciplines. For more information on MTG-UPF please visit http://mtg.upf.edu
 


HOW TO APPLY?

Interested people should send a resume as well as an introduction letter to mtg-info [at] llista [dot] upf [dot] edu (subject: Junior%20software%20engineer%20position)
 
31 Aug 2012 - 11:09 | view
MTG article in Nature's Scientific Reports

Joan Serrà and Martín Haro are coauthors of an article that has been published in the on-line journal Scientific Report that is part of Nature. The article is on "Measuring the evolution of contemporary western popular music"

Summary of article:

A quantitative analysis of songs in the Million Song Dataset reveals a number of emerging patterns in the evolution of contemporary popular music. The study, published in Scientific Reports , suggests that over the past 50 years pop songs have become louder, their pitch has become more restricted and their timbre more homogenized.

Like language, music is an important form of cultural expression, but the long-term variations of the underlying patterns remain poorly understood. Joan Serrà and colleagues studied the Million Song Dataset, which includes descriptions of the pitch, timbre and loudness of musical recordings from 1955 to 2010, spanning a variety of genres, from pop and rock to hip hop. They report several statistical patterns and metrics characterizing the general usage of pitch, timbre and loudness in contemporary western pop music. Many of these patterns have remained stable over a period of more than 50 years, suggesting a tendency towards conventionalism in the creation of this type of music. But the authors also observed three important trends in the evolution of popular music: the restriction of pitch sequences, the homogenization of timbre and an increasing average loudness.

The authors suggest this means that an old tune rerecorded using modern techniques that allow for increased loudness and with slightly simpler chord progressions and new instrument sonorities could be perceived as novel and fashionable. The development of further historical music databases could allow the quantification of major transitions in the history of music and the discovery of more subtle evolving characteristics of particular genres or artists."
 

26 Jul 2012 - 19:53 | view
Voctro Labs 'Best digital inniciative of the year' by Generació Digital (Catalunya Radio)

"Generació Digital" (a "Catalunya Radio" program about Technology and Video Games) celebrated their 10th anniversary last week. With this occasion, they organized a party at Fabrica Moritz in Barcelona and a contest for the best mobile application, videogame and digital initiative in 2011. Voctro Labs, our third spin-off company recently established, got awarded with the prize for the "Best digital initiative of the year" especially for the release of Bruno & Clara, the first Spanish Virtual Singers. It's really good news as there were a lot of other good candidates for the prize, so we expect that this mention will open doors for the future!

This is a blog post with some pictures of the event and an small interview to Voctro Labs in yesterday's Radio program (in catalan) is available here (minute 38:10)

23 Jul 2012 - 12:27 | view
intranet