SMC Master Students' Project Defenses 2020
The oral presentations of the SMC Master Thesis 2019-2020 will take place online from July 1st to July 7th, 2020.
22.06.2020
This is the schedule for the thesis presentations of the Master in Sound and Music Computing by the students finishing this academic year. All the presentations will be done online through zoom at https://zoom.us/j/5911355273 and the sessions will be open to everyone.
July 1st, 2020
| Time | Student | Thesis title | Supervisor(s) |
| 9.30-10.00 |
Alexander Keijser
|
Learning music similarity using audio and textual input | Dmitry Bogdanov, Minz Won |
| 10.00-10.30 | Luis Joglar | Essentia in the browser | Dmitry Bogdanov |
| 10.30-11.00 | Jorge Marcos Fernández | Browsing Textural Sounds in FreeSound | Frederic Font |
| Break (30 mins) | |||
| 11.30-12.00 | Kohki Mametani | Learn sound representation using triplet loss | Xavier Favory, Frederic Font |
| 12.00-12.30 | Roberto Pérez Sánchez | Online Audio Editor in FreeSound | Frederic Font |
| 12.30-13.00 | Miguel Pérez Fernández | Harmonic compatibility for loops in electronic music | Antonio Ramires, Frederic Font |
July 2nd, 2020
| Time | Student | Thesis title | Supervisor(s) |
| 10.00-10.30 | Jorge Bustos | Audio-based album cover generation | Perfecto Herrera, Joan Serrà |
| 10.30-11.00 | Miguel García Casado | Computational Analysis of Arab-Andalusian Music Through Symbolic Pattern Recognition Algorithms | Xavier Serra, Andrés Ferraro |
| Break (30 mins) | |||
| 11.30-12.00 | Siyar Vurucu | Automatic Assessment of Rhythmic and Technique Quality of Guitar Attacks | Xavier Serra |
| 12.00-12.30 | Yiqun Liu | Evaluation of Music Recommender Systems | Philip Tovstogan |
| 12.30-13.00 | Enric Gusó Muñoz | Empirical study on loss functions for music source separation | Jordi Pons |
July 3rd, 2020
| Time | Student | Thesis title | Supervisor(s) |
| 11.30-12.00 | Thomas Nuttall | Transformers for Automated Drum Pattern Generation | Sergi Jordà, Behzad Haki |
| 12.00-12.30 | Blazej Kotowski | Dualization of rhythmic grooves | Sergi Jordà, Behzad Haki |
| break (150 minutes) | |||
| 15.00-15.30 | Tiange Zhu | Modelling Expressive Performance Deviations In Classical Guitar | Rafael Ramirez, Sergio Giraldo |
| 15.30-16.00 | Break (30 minutes) | ||
| 16.00-16.30 | Ignasi Nou Plana | Expressive performance modeling of hexaphonic guitar recordings | Sergio Giraldo, Rafael Ramirez |
| 16.30-17.00 | Christian Steinmetz | Towards end-to-end multitrack mixing with deep learning | Joan Serrà, Frederic Font |
July 6th, 2020
| Time | Student | Thesis title | Supervisor(s) |
| 9.30-10.00 | Ana Gabriela Pandrea |
End-to-End Music Emotion Recognition: Towards Language-Sensitive Models |
Juan Sebastián Gómez Cañón, Perfecto Herrera |
| 10.00-10.30 | Georges Naimeh | Content Based Record Label Classi cation for Electronic Music | Perfecto Herrera, Minz Won |
| 10:30-11:00 | Ningxiang Xie |
Automatic Music Transcription for Music Expressive Performance |
Rafael Ramirez, Sergio Giraldo |
| 11.30-12.00 | Pavlo Apisov | Singing Voice Conversion | Pritish Chandna, Jordi Bonada |
| 12.00-12.30 | Darius Petermann | SATB Voice Segregation For Monoaural Choir Recordings | Pritish Chandna, Jordi Bonada |
| 12.30-13.00 | Dougal Shakespeare | Exploring Gender Distribution in Music Recommender Systems | Lorenzo Porcaro, Emilia Gómez |
July 7th, 2020
| Time | Student | Thesis title | Supervisor(s) |
| 9.30-10.00 | Henry Hasti | Microphone array signal processing to perform musical blind source separation | Andrés Perez, Xavier Serra |
| 10.00-10.30 | Francesca Ronchini | Localization, Detection and Tracking of Overlapping Sound Sources using Convolutional Recurrent Neural Network (CRNN) | Andrés Perez, Daniel Arteaga |
| 10.30-11.00 | Myrsini Ioannou | An interactive environment for the automatic generation of chord progressions from melodic input | Ángel Faraldo, Frederic Font |
| break (30 mins) | |||
| 11.30-12.00 | Alia Morsi | Characterizing Complexity Levels of Keyboard Music Scores | Xavier Serra |
| 12.00-12.30 | Matthew Greenlees | Beat Tracking from Audio using Autoencoders and LSTM Networks | Aggelos Gkiokas |
| 12.30-13.00 | Jose David Bedoya Molina | Singing Enhancement for Low Quality Inputs | Jordi Janer, Merlijn Blaauw |