News and Events

Seminar by Bipin Indurkhya on Perceptual Similarity

Bipin Indurkhya, from the International Institute of Information Technology (Hyderabad, India) gives a seminar on June 14th at 3:30pm in room 52.321 on "Perceptual Similarity, Visual Metaphor and Creativity".

Abstract:
Researchers who study creativity in real-world situations have found that a primary hurdle facing human creativity is in stepping outside of our habitual conceptual association. A few techniques have been suggested to aid this process: making-the-familiar-strange and de-conceptualization, for example. The main objective of these techniques is to help the cognitive agent break the bond of conceptual association it has acquired culturally and through a lifetime of experiences. In this process, imagery, perceptual similarities, and visual metaphors play a key role, as we will demonstrate using several examples.
 
We are following a number of research veins to explore the role of imagery and visual metaphor in creativity and cognition, and in this talk I will present some of our results. In particular, we will present some experiments to compare and contrast mono-modal (text-text or image-image) vs. cross-modal (text-image) metaphors. We have also investigated how explicit imagery, presented before or after the metaphor, influences the comprehension of metaphor.
 
We have argued, and demonstrated, in our past research, that computer-based systems can be very helpful in stimulating creativity. For instance, we found that incorporating one familiar but unrelated object in a picture setting, or presenting unrelated pairs of objects to a cognitive agent, and asking them to make a story out of it, or to make sense of it in some other way, stimulates their creativity and imagination.
 
In another line of research, we are exploring the hypothesis that low-level perceptual similarity — that is, similarity based on low-level perceptual features like color, shape and texture — plays a key role in creation of novel conceptual associations. In other words, we are claiming that if the unrelated object that is introduced into a picture or paired with another object bears some low-level perceptual similarity with other objects in the picture, or with the paired object, it is likely to be more effective in stimulating creativity than a random unrelated object. We will present here the results of some of our preliminary experiments to explore this hypothesis.
 
As the similarity with respect to low-level perceptual features is determined algorithmically using image-based pattern matching, our approach can be used to design more effective computer-based creativity-support systems. We will present an outline of such architecture and mention a number of possible application domains for such systems.
11 Jun 2012 - 11:00 | view
Phonos concert: Final concert by students of the "Sound Creation Lab" (UPF)

The students from the Sound Creation Lab course at UPF, coordinated by Emilia Gómez and Justin Salamon, will give their final concert (as part of the Phonos concerts) next Wednesday June 13th at 12:30 in the Espai Polivalent in the Communication Campus of the UPF. Free entrance!

7 Jun 2012 - 09:53 | view
PhD Thesis proposals defenses

Gopal Koduri and Sertan Senturk, first year PhD students, will defend their PhD thesis proposals on Tuesday June 12th 2012 in room 55.410.

  • 09:30 - Gopala Krishna Koduri: "Similarity Measures in Indian Art Music Traditions"
  • 10:15 - Sertan Senturk: "Computational Characterization of Seyirs in Makam Music in Turkey"

The jury members are: Marcelo Bertalmio, Emilia Gomez, Xavier Serra

5 Jun 2012 - 15:41 | view
Upcoming research seminars

Title: Machine listening and learning for musical systems

Speaker: Nick Collins, University of Sussex

Host: Perfecto Herrera

Date: Thursday June 7th, 2012, 15:30pm

Location: room 52.321, Roc Boronat building

Abstract: Musical articial intelligences are playing an important role in new composition and performance systems. Critical to enhanced capabilities for such machine musicians will be listening facilities modeling human audition, and machine learning able to match the minimum 10000 hours or ten years of intensive practice of expert human musicians. Future musical agents will cope across multiple rehearsals and concert tours, or gather multiple commissions, potentially working over long musical lifetimes; they may be virtuoso performers and composers attributed in their own right, or powerful musical companions and assistants to human musicians.

In this presentation we'll meet a number of projects related to these themes. The concert system LL will be introduced, an experiment in listening and learning applied in works for drummer and computer, and electric violin and computer. Autocousmatic will be presented, an algorithmic composer for electroacoustic music which incorporates machine listening in its critic module. Large corpus content analysis work in music information retrieval shows great promise when adapted to concert systems and automated composers, and the SuperCollider library SCMIR will be demonstrated, alongside a new realtime polyphonic pitch tracker.

*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*

Title: Percussive/Harmonic/Singing Separation on Monaural Music Signals

Speaker: Pedro Vera Candeas and Francisco Jesús Cañadas Quesada, Universidad de Jaén

Host: Emilia Gómez

Date: Friday June 8th, 2012, 11:00am

Location: room 55.410, Tànger building

Abstract: This seminar is divided into two parts. In the first part, a brief review of current percussive/harmonic/singing separation techniques is presented. In the second part, a preliminary unsupervised algorithm for separating percussive, harmonic and singing voice components from monaural polyphonic signals is shown. The proposed algorithm, based on a modified Nonnegative Matrix Factorization (NMF) procedure, does not require any training stages to distinguish between percussive, harmonic and singing voice bases because useful information from percussive, harmonic and vocal sounds is integrated into the decomposition process. In this process, NMF is performed by assuming that harmonic sounds exhibit spectral sparseness and temporal smoothness, percussive sounds exhibit spectral smoothness and temporal sparseness while singing voice sounds is characterized by a source/filter model in which the constraint “only one source is active” is integrated. Promising results are obtained when the proposed approach was compared using commercial real-world signals.

4 Jun 2012 - 18:44 | view
Ph.D Positions 2012-2013

The Music Technology Group within the ICT Dept. at UPF seeks doctoral applications for 2012-13 from talented students with a strong interest in music computing research.

Candidates for PhD positions must hold an MsC degree or equivalent. Students will pursue doctoral studies in one of the research areas of the research group which include specific social networks around sound and music.

The PhD Program offers up to 2 research fellowships. Only candidates accepted to the PhD program are eligible for a fellowship. Hence, every fellowship application should be paired up with an admission application into the PhD program. Admission to the PhD DTIC program is handled by the university admission office, further details available here.

Application period: June 1st, 2012 to July 15th, 2012

Resolution period: notification will be published at the MTG website within 60 days from the end of the application period.

Type of Fellowships: Research grant which only includes research tasks in the frame of a project (not teaching assistance).

Monthly wage: 981.44€

Starting date: 1st of October, 2012.

How to apply:

  • Fulfill the application form properly signed
  • Submit the application form (in pdf format) by e-mail to mtg-info [at] llista [dot] upf [dot] edu


 

30 May 2012 - 10:11 | view
Participation to CIP 2012

Frederic Font is participating to the Third International Workshop on Cognitive Information Processing, which takes place in Bainoa (Spain) from May 28th to the 30th, 2012. Frederic is presenting the following paper:

28 May 2012 - 17:18 | view
Upcoming research seminars

Title: Adaptive Filtering for Music / Voice Separation Exploiting the Repeating Musical Structure

Speaker: Antoine Liutkus

Host: Jordi Janer

Date: Tuesday May 29th, 2012, 15:30pm

Location: room 55.410, Tànger building

*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*-*

Title: Audio Signal Analysis for Computational Music Listening

Speaker: Emilia Gómez

Date: Wednesday May 30th, 2012, 16:00pm

Location: room 55.410, Tànger building

 

27 May 2012 - 13:01 | view
Phonos concert: LEMAts

On Wednesday May 30th 2012 at 19:30h in the Espai Polivalent of the Communication Campus of the UPF, Phonos is organizing a concert of LEMAts (Laboratorio de Electrónica Musical de Andalucía de Taller Sonoro)

24 May 2012 - 14:07 | view
MAKE, PLAY, SHARE: The future of MusicTech

MTG is coorganizing, together with BMAT and Stromatolite Design Lab, a panel discussion in the frame of MIReS project which will take place at SonarPro next 14th June at 13.30 pm, just after the Companies' presentations at the Barcelona Music Hack Day.

The MIReS panel discussion intends to look into the future of the Music Industry from three perspectives: (i) Search & Discovery, (ii) Creativity and (iii) Rights Management. MIReS panel main aim is gathering first-hand feedback from relevant industry players which will serve as an input for the roadmap.

The list of panel speakers is as follows:

  • Alex Loscos, co-founder & CEO at BMAT
  • Scott Cohen, Founder and VP International at The Orchard
  • Hunter Williams, Senior Vice President Strategic Development/Distribution & Research Operations in SESAC
  • Michael Breidenbrücker, CEO at RjDj
  • Matthew Hawn, Vice President, Product at Last.fm
  • Michela Magas, innovation catalyst at Stromatolite Design Lab
  • Robert Kaye, founder and lead developer for MusicBrainz, and President and Executive Director of the MetaBrainz Foundation

Chaired by: Jamillah Knowles, BBC Outrider journalist

22 May 2012 - 12:58 | view
Master's projects exhibition at Sonar festival

MTG is organizing an exhibition at Sonar festival in order to promote the work of students that developed master's projects focused on audio. The works are the result of different masters from the UPF, including Sound and Music Computing, and Digital Arts from IdEC, and also a Phonos granted project (Prefall135).


One of the works that will be shown in the exhibition is The EyeHarp, by Zacharias Vamvakousis, currently PhD student in the MTG. The EyeHarp is an interesting instrument controlled by the movement of the eye, enabling to create music to those people with a motor disability.

 

All the projects will be displayed in the form of interactive installations, where music and sound will be central features. The exhibition will take place in the frame of the Sonar Pro section within Sonar Festival in Barcelona, from the 14th to 16th of June.

21 May 2012 - 19:35 | view
intranet