The oral presentations of the SMC Master Thesis will take place in three different sessions on Tuesday June 19th, Thursday June 21st, and Friday June 29th in room 55.309. The defenses are public.
Tuesday June 19th (55.309)
|
|
|
|
| Time |
Student |
Topic |
Supervisor (s) |
| 9:30 |
Davide Busacca |
Improving a Time Stretching Technique based on Harmonic-Percussive Separation |
Baris Bozkurt |
| 9:50 |
Emir Demirel |
Automatic Scale estimation in monophonic jazz solos |
Baris Bozkurt |
| 10:10 |
Vsevolod Eremenko |
Automatic harmony analysis of jazz audio recordings |
Baris Bozkurt |
| 10:30 |
Rahul Agarwal |
Automatic Performance Score Alignment |
Baris Bozkurt |
| |
|
|
|
| |
|
|
|
Thursday June 21st (55.309)
|
|
|
|
| Time |
Student |
Topic |
Supervisor (s) |
| 11:30 |
Behzad Haki |
Drum & Bass Interlocking |
Sergi Jorda |
| 11:50 |
Tae Hun Kim |
Automatic Legato Player Interface for Pianists |
Sergi Jorda |
| 12:10 |
Pedro Lladó |
A machine learning approach for automatic assessment of timbre in violin music learning |
Sergio Giraldo, Rafael Ramírez |
| 12:30 |
Furkan Yesiler |
Automatic detection of phonation modes in singing |
Rafael Ramirez |
| |
|
|
|
| |
|
|
|
Friday June 29th (55.309)
|
|
|
|
| Time |
Student |
Topic |
Supervisor (s) |
| 9:30 |
Francesc Lluís Salvado |
A Wavenet for Source Separation |
Jordi Pons |
| 9:50 |
Philip Tovstogan |
Exploring music similarity with AcousticBrainz |
Dmitry Bodganov, Alastair Porter |
| 10:10 |
Vibhor Bajpai |
Evaluation of State of the Art in semantic annotation of large music collections |
Dmitry Bogdanov |
| 10:30 |
Lorenzo Romanelli |
Towards a computational representation of musical beauty |
Perfecto Herrera |
| 10:50 |
Martin Disley |
Computational Beauty of Music |
Perfecto Herrera |
| 15 minute break |
| 11:25 |
Aniel Rossi |
Acoustic event recognition using deep learning |
Eduardo Fonseca, Frederic Font |
| 11:45 |
Venkatesh Shenoy Kadandale |
Musical Instrument Recognition |
Frederic Font |
| 12:05 |
Marc Kaivon Jones |
Automatic classification of animal sounds |
Frederic Font |
| 12:25 |
Joaquin Jimenez |
Real-time multi-track mixing for live performance |
Frederic Font |
| 12:45 |
Manaswi Mishra |
Timbre Morphing for Synthesis in a note Dataset |
Xavier Serra |
