Seminars

Past talks

Speaker: Rodrigo Borges
Date and time: Wednesday, May 4, 2016 - 12:00
Place: Auditório do CCSL, IME/USP
Abstract:

Music Recommender Systems are computational techniques for suggesting music to an specific user according to his personal interest. They operate under a big amount of music files and, depending on the information provided in its entry, may apply Collaborative Filtering, Context-Based or Content-based approaches.

Collaborative Filtering makes recommendations to the current user based on items that other users with similar tastes liked in the past. Contextual Music Recommendation refer to the situation of the user when listening to recommended tracks (e.g, time, mood, current activity, the presence of other people). Music Content can be understood as musical features computed directly from audio, or semantic inferred or predicted by machine learning techniques.

Differently from another recommender systems, as for books, movies or news, the music ones has specific characteristics: they allow recommendation of repeated items, and has a fast consumption time in comparison. These leads us to differentiate between parallel (albums) and serial (playlist) recommendation.

Preliminary feature extraction results are finally presented, retrieved from a temporary database containing popular Brazilian music.


(video presentation in portuguese)

Speaker: Fábio Goródscy
Date and time: Wednesday, April 6, 2016 - 12:00
Place: Auditório do CCSL
Abstract:

A tutorial about Web Audio API.

We are showing and  presenting some simple examples for explaining how Web Audio API works and how its structure is defined. You can see the examples here: https://github.com/fabiogoro/webaudio

During the presentation we show:

  • How to start Web Audio Objects
  • How to use the Oscillator to create sounds with different frequencies
  • How to control volume of the sound and its waveform
  • How to apply all of this to create a piano on the browser
  • And in the end: Using peer.js or PubNub to exchange Web Audio information through browsers

A live version of the tutorial is online at: http://webaudiotutorial.herokuapp.com/


Speaker: Antonio José Homsi Goulart
Date and time: Wednesday, March 30, 2016 - 12:00
Place: Auditório do CCSL
Abstract: In this seminar we will present Phase-Lock Loops systems, widely used for demodulation of frequency modulated signals. The basic idea behind the technique will be shown, along with recently proposed adaptations for fundamental tracking of audio signals. The efficiency of the system will be confirmed with audio examples, and audio effects based on the fundamental frequency of the input signal will also be discussed.


(video presentation in portuguese)

Speaker: Guilherme Feulo do Espirito Santo
Date and time: Wednesday, March 16, 2016 - 12:00
Place: Auditório do CCSL
Abstract:

This seminar is based in the article "A Tutorial on EEG Signal-processing: techniques for mental-state recognition in Brain-computer Interfaces" by Fabien Lotte, a chapter of the book "Guide to Brain-computer Music Interfacing" edited by Eduardo R. Miranda and Julien Castet.

The main stages in the development of Brain-computer Interfaces through Electroencephalography will be presented, with the description of the most used techniques for Feature Extraction an Feature Classification..


(video presentation in portuguese)

Speaker: Antonio Deusany de Carvalho Junior, ScD candidate at IME/USP
Date and time: Wednesday, March 9, 2016 - 12:00
Place: Auditório do CCSL, IME/USP
Abstract:

In this talk we will present many research projects developed from the collaboration between Computer Music and professionals from other areas like Musica, Engineering, Physics, and Medicine. The discussion will focus on the contributions that the Computer Music area provided to the researches and researchers, and we will discuss the interaction between the professionals that had to deal with different technical languages, methods, and scientific approaches in front of the problems to be solved.

The works discussed during this talk had the presenter as a member, and they comprise: musical installation using mobile devices and webservice; the use of mobile sensors during musical performances; a concert taking advantage of cloud computing and web audio; difficult airways evaluation from formant analysis of vowels pronounced by patients; the disgnostic of sleep apnea with mobile devices and sensors; and some works developed with the HardwareLivreUSP group including analog synthesizers and MIDI controllers connected to floppy disks. Some of these researches are in progress, but they already provided many interesting experiences that will be presented during this talk.


(video presentation in portuguese)

Pages

Subscribe to Upcoming talks Subscribe to Past talks