News and Events

2 PhD students join the MTG thanks to Industrial PhD program

Two PhD students are joining the MTG thanks to the industrial doctorate program from AGAUR, which supports collaboration between universities and industrial partners, in this case both from Barcelona. These students, although working at the company, will spend some time at the MTG and collaborating with researchers here.

Emilia Gómez is the academic supervisor of these projects, which are both linked to our research on audio processing and description:

  • "Music/Speech Detection in Broadcast Media Programs" in collaboration with BMAT, in particular with Emilio Molina (supervisor at BMAT). Blai Meléndez Català is our PhD fellow, and the goal of this project is to research on the task of audio segmentation and tagging in the context broadcast recordings.
  • "Immersive Audiovisual Production Enhacement based on 3D Audio", in collaboration with Eurecat, in particular with the audio-visual technologies group leaded by Adan Garriga (industry supervisor). This project is related to 3D audio for virtual reality applications, and Andrés Pérez is a new PhD student that will research on innovative production tools for creative industries.

There is some more info (in catalan or spanish) on the UPF web site.

23 Mar 2017 - 12:48 | view
Announcing the Riyaz music app and the creation of MusicMuni
MTG announces the release of the music education app Riyaz and the creation of the spin-off company responsible for its commercialization, MusicMuni Labs .
 
This is the result of the research done within the ERC funded project CompMusic, in which we developed technologies to foster learning and appreciation of Indian music forms, in particular, technologies to automatically evaluate how well a student is singing compared to a reference music lesson. Within the accompanying ERC proof of concept project CAMUT, we defined the exploitation plan of these technologies, developing Riyaz and creating MusicMuni Labs.
 
Riyaz is an android application to facilitate music learning for beginner to intermediate level music students by making their practice (riyaz in Hindi) more efficient. Riyaz offers hundreds of exercises along with singing lessons in Hindustani music and Carnatic music. It is also a personal vocal trainer, that listens to the singing user and provides precise feedback.
 
MusicMuni has been founded in Bengaluru (India) by two of the PhD students that developed the technologies being exploited, Sankalp Gulati and Gopala Krishna Koduri, together with Xavier Serra, director of the MTG. MusicMuni aims to catalyze and scale the music education and infotainment domains in ways accessible by and affordable to masses, by synergising the pedagogical knowledge with artificial intelligence, with a particular emphasis on learner engagement and automated evaluation.
 
 
More information:
Web of MusicMuni Labs: http://musicmuni.com/
Facebook page of Riyaz: https://www.facebook.com/RiyazApp/
 
20 Mar 2017 - 16:04 | view
Students from Lycée Français Barcelona visit the MTG

On March 17th, students of last course of Lycée Français visited the MTG to learn about the research in music technology. Juanjo Bosch, Emilia Gómez and Sergi Jordà presented the work that is being carried out in the Music Information Research Lab and Music and Multimodal Interaction Lab.

 

 

17 Mar 2017 - 20:07 | view
Participation to Cultural Innovation event

The MTG will participate in an event about cultural innovation organized by Culture Institute of Barcelona City Council, that will take place on March 10th 4PM at Canòdrom-Parque de Investigación Creativa (Barcelona).

Sonia Espí will introduce Freesound and participate in a debate about digital heritage.

 

8 Mar 2017 - 13:01 | view
Sónar Innovation Challenge 2017: Call for Creators
This year the MTG is once again collaborating with the Sónar+D festival to organize the Sónar Innovation Challenge (SIC).
 
SIC is a platform for the collaboration between innovative tech companies and the creative community (programmers, designers, artists) that aims to produce disruptive prototypes to be showcased in Sonar+D. The interaction between companies and creators happens through challenges proposed by the companies themselves. Challenges are open questions to the creative community, that can be approached from a technical and/or artistic perspective.
 
This year SIC proposes 6 challenges that span from intelligent DJ assistants and context-aware music flow, to VR, interface design and affective computing. The calendar of SIC:
  • March 6th - April 7th: Open Call for Creators. You can apply to one or more challenges from the website.
  • April 21st: Announcement of selected participants. A group of 5 creators will be assigned to each challenge. This means that you will work in the challenge collaborating with others.
  • May 1st - June 13th: You will have the chance to meet and work remotely with your team to plan the best solution for the challenge in collaboration with company mentors.
  • June 13th: Kick-off meeting @ Barcelona (place TBC)
  • June 14th-16th: working session & showcases @ Sonar+D (Barcelona)
  • June 17th: you will chill out and enjoy Sónar+D and Sónar Festival
The selection process will be based on the profile, motivation and previous experience of participants. Also, creators coming from abroad will receive a travel aid to help them cover mobility and accommodation expenses. 
 
7 Mar 2017 - 12:44 | view
Special Issue in IEEE Multimedia Magazine

Emilia Gómez has co-edited, in collaboration with Cynthia Liem (TU Delft, The Netherlands) and George Tzanetakis (University of Victoria, Canada), a Special Issue at IEEE Multimedia Magazine on the topic of Multimedia Technologies for Enriched Music Performance, Production, and Consumption. This special issue gathers state-of-the-art research on multimedia methods and technologies aimed at enriching music performance, production and consumption, and it is linked to the topic of the recently finished PHENICX project. This is the full reference to the editorial paper: 

Liem, C., Gómez, E., Tzanetakis, G. (2017), Multimedia Technologies  for Enriched Music Performance, Production and Consumption, IEEE Multimedia Magazine, 24(01), pp. 20-23. 

The full issue can be accessed here.

7 Mar 2017 - 11:52 | view
Participation to ICASSP 2017

Jordi Pons participates to the 42th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2017) which takes place in New Orleans, USA, on March 5-9, 2017. He presents the following paper done in the context of the Maria de Maeztu DTIC strategic program.

Jordi Pons and Xavier Serra. "Designing Efficient Architectures for Modeling Temporal Features with Convolutional Neural Networks."

6 Mar 2017 - 10:41 | view
OVAL by OVAL SOUND
9 Mar 2017
Alex Posada, co-founder of Oval Sound, will give a talk on their music tech startup and the Oval, the first digital Handpan ever developed. The talk will take place on Thursday, March 9th 2017, at 12:00h in room 55.410 of the Communication Campus.
 
OVAL by OVAL SOUND
 
Founded in 2014 by Ravid Goldschmidt and Alex Posada in Barcelona (Spain), OVAL SOUND is the music technology startup behind Oval, the first digital Handpan ever developed.
 
The Oval is a new electronic musical instrument designed from the ground-up to revolutionize music creation, learning and live performance. This next generation instrument has sensitive multi-gesture sensors to combine the expressiveness of an acoustic instrument, with the flexibility of modern digital synthesis. To take full advantage of each subtle gesture, the Oval comes with its own multi-platform synthesis and effects app which when paired together, create a truly immersive playing experience.
The Oval app supports both iOS and Android, and comes with custom high- quality sound libraries ready to play. Or if you're feeling adventurous, you can connect the Oval to your favorite MIDI-enabled music apps, synths and even lighting rigs - the possibilities are endless.
 
The project was launched via a crowdfunding campaign on Kickstarter, and to this day remains one of the most successful campaigns on the platform in 2015.
 
2 Mar 2017 - 10:28 | view
Seminar by Geraint Wiggins on Computational Creativity
2 Mar 2017

Geraint A. Wiggins, from Queen Mary University of London, gives a seminar on "Creativity, deep symbolic learning, and the information dynamics of thinking" on Thursday, March 2nd 2017, at 15:30h in room 55.309 of the Communication Campus of the UPF.

Abstract: I present a hypothetical theory of cognition which is based on the principle that mind/brains are information processors and compressors, that are sensitive to certain measures of information content, as defined by Shannon (1948). The model is intended to help explicate processes of anticipatory and creative reasoning in humans and other higher animals. The model is motivated by the evolutionary value of prediction in information processing in an information-overloaded world.
The Information Dynamics of Thinking (IDyOT) model brings together symbolic and non-symbolic cognitive architectures, by combining sequential modelling with hierarchical symbolic memory, in which symbols are grounded by reference to their perceptual correlates. This is achieved by a process of chunking, based on boundary entropy, in which each segment of an input signal is broken into chunks, each of which corresponds with a single symbol in a higher level model. Each chunk corresponds with a temporal trajectory in the complex Hilbert space given by a spectral transformation of its signal; each symbol above each chunk corresponds with a point in a higher space which is in turn a spectral representation of the lower space. Norms in the spaces admit measures of similarity, which allow grouping of categories of symbol, so that similar chunks are associated with the same symbol. This chunking process recurses “up” IDyOT’s memory, so that representations become more and more abstract.
It is possible to construct a Markov Model along a layer of this model, or up or down between layers. Thus, predictions may be made from any part of the structure, more or less abstract, and it is in this capacity that IDyOT is claimed to model creativity, at multiple levels, from the construction of sentences in everyday speech to the improvisation of musical melodies.
IDyOT’s learning process is a kind of deep learning, but it differs from the more familiar neural network formulation because it includes symbols that are explicitly grounded in the learned input, and its answers will therefore be explicable in these terms.
In this talk, I will explain and motivate the design of IDyOT with reference to various different aspects of music, language and speech processing, and to animal behaviour.

24 Feb 2017 - 18:13 | view
YoMo: Presentation of TELMI project in the Mobile World Congress

On February 27th at 1PM we will be presenting TELMI project in the Youth Mobile Festival (YoMo) which is part of the GSMA Mobile World Congress. This festival is aimed at students from 10 to 16 years old, and it's expected to have 15.000 students visiting the festival.

The presentation will be focused on how interactive technologies can help in instrument learning, we will show some demos and the participants will be able to try some prototypes.

Find here more details of the activity:
http://www.mwcyomo.com/en/activities/music-technology-artificial-intelli...

21 Feb 2017 - 17:46 | view
intranet