SMC Master Students' Project Defenses 2023
The oral presentations of the SMC Master Thesis 2022-2023 will take place from July 10th to 13th, 2023 in room 52.427
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 at UPF’s room 52.427 and online through zoom at https://zoom.us/j/5911355273. The sessions will be open to everyone.
July 10th
Time |
Student |
Thesis title |
Supervisor(s) |
| 10:30 |
Oriol Colomé Font |
Uncovering underlying high-level musical content in the temporal domain |
Carl Thomé, Carlos Lordelo |
| 11:00 |
Abhishek Choubey |
Evaluation of drum rhythm-space in a music production environment |
Daniel Gómez, Sergi Jordà |
| 11:30 | Peter Clark |
Tap to Drums: Extending Monophonically Tapped Rhythms to Polyphonic Drum Pattern Generation |
Daniel Gómez, Sergi Jordà |
| 12:30 | Nicholas Evans | Deploying the GrooveTransformer drum generator to an embedded environment | Behzad Haki, Sergi Jordà |
| 13:00 | Patricio Ovalle | Modelling rhythmic compatibility in multi-part music | Daniel Gómez, Sergi Jordà |
July 11th
Time |
Student |
Thesis title |
Supervisor(s) |
| 10:00 |
Ahmet Oğuz Öztürk |
Applying Audio Detection Algorithms on Sounds on Freesound Website |
Dmitry Bogdanov |
| 10:30 |
Alberto Barrera |
Pultec EQ1A Modelling with Wave Digital Filters |
Xavier Lizarraga |
| 11:00 |
Christos Plachouras |
A Toolkit for Reproducible Music Audio Representation Evaluation |
Dmitry Bogdanov, Pablo Alonso |
| 12:00 |
Francesco Papaleo |
Neural Audio Effect Modelling Strategies for a Spring Reverb |
Xavier Lizarraga |
| 12:30 |
Recep Oğuz Araz |
Freesound Deep Similarity |
Dmitry Bogdanov, Pablo Alonso |
| 13:00 |
Dilip Harish |
Language Based Audio Retrieval for Freesound |
Benno Weck, Frederic Font |
July 12th
Time |
Student |
Thesis title |
Supervisor(s) |
|
10:00 |
Adithi Shankar Sivasankar |
Vocal Source Separation for Carnatic Music |
Genis Plaja, Xavier Serra |
|
10:30 |
Ben Olsen |
Applying Computer Vision Foundation Models to Music Source Separation |
Genis Plaja, Marius Miron |
|
11:00 |
Iván Fernández Cocaño |
Expanding the evaluation of Audio Matching applying Audio Querying strategies |
Alia Morsi |
|
12:00 |
Qingyuan Liu |
Leakage Removal for Music Learning Scenario |
Marius Miron, Alia Morsi |
|
12:30 |
María Pérez Rodríguez |
Intonation and Vibrato Analysis in the context of Violin Education and Galician fiddle |
Nazif Can Tamer |
|
13:00 |
Samuel Cantor |
Piano Performance Analysis using Technique Information Extracted from Videos |
Pedro Ramoneda, Nazif Can Tamer |
July 13th
Time |
Student |
Thesis title |
Supervisor(s) |
| 10:00 |
Matteo Fabbri |
Data-driven real-time Neural Audio Synthesis for Procedural Audio |
Lonce Wyse |
| 10:30 |
Mireia de Gracia Forés |
A mobile application with machine learning and music therapy principles for post-stroke upper-limb motor recovery |
Rafael Ramírez |
| 11:00 |
Nikita Bashaev |
ABRSM automatic grade evaluation |
Rafael Ramírez |
| 11:30 |
Raquel Lucena |
Digital music interfaces for motor rehabilitation: a motion capture and machine learning approach |
Rafael Ramírez |
| 12:30 |
Thomas Le Roux |
Multimodal analysis: Lip reading in singing |
Rafael Ramírez, Lonce Wyse |
| 13:00 |
Quoc Duong Nguyen |
Automatic score-to-score music generation |
Pedro Ramoneda, Carlos Hernández |
| 13:30 |
Santiago Diana |
Diffusion inspired training strategy for Source Separation in the frequency domain |
Genis Plaja, Marius Miron |
| 14:00 |
Julian Lenz |
Expressive Parameters for Realtime Deep Learning Rhythm Generation Systems |
Behzad Haki, Sergi Jordà |