Twenty-four new theses, carried out and finished during the academic year 2022-2023 in the Master in Sound and Music Computing, are now available:

• Abhishek Choubey: Evaluation of Drum Rhythmspace in a Music Production Environment
• Adithi Shankar Sivasankar: Vocal Source Separation for Carnatic Music
• Ahmet Oğuz ÖZTÜRK: Applying Audio Problem Detection Algorithms to Sounds on Freesound Web Platform
• Alberto Barrera Herrero: Pultec EQP-1A Modeling with Wave Digital Filters
• Benjamin Olsen: Applying Computer Vision Foundation Models to Audio Source Separation
• Christos Plachouras: Beyond Benchmarks: A Toolkit for Music Audio Representation Evaluation
• Francesco Papaleo: Neural Audio Effect Modelling Strategies for a Spring Reverb
• Iván Fernández Cocaño: Expanding the evaluation of Audio to Score Matching applying Audio Querying strategies
• Julian Lenz: Disentangle and Deploy: Generative Rhythmic Tools for Musicians
• María Pérez Rodríguez: Intonation Analysis in the context of Violin Education
• Matteo Fabbri: Neural Texture Sound Synthesis with physically-driven continuous controls using synthetic-to-real unsupervised Domain Adaptation
• Mireia de Gracia Forés: A mobile application based on machine learning and music therapy principles for post-stroke upper-limb motor recovery
• Nicholas Evans: Deploying the Groove Transformer to an Embedded Environment
• Nikita Bashaev: Transfer learning for automatic ABRSM grade evaluation
• Oriol Colomé Font: Uncovering underlying high-level musical content in the time domain
• Patricio Ovalle: Rhythmic Accompaniment Generation with Transformer Neural Networks
• Peter Clark: Tap to Drums: Extending Monophonically Tapped Rhythms to Polyphonic Drum Pattern Generation
• Qingyuan Liu: Comparison of algorithms for removing leakage in music learning scenario
• Quốc Dương Nguyễn: Automatic score-to-score music generation
• Raquel Lucena Peris: Digital music interfaces for motor rehabilitation: a motion capture and machine learning approach
• Recep Oğuz Araz: Semantic Sound Similarity with Deep Embeddings for Freesound
• Samuel Cantor: Piano Performance Analysis Using Technique Information Extracted from Videos
• Santiago Diana: Diffusion inspired training strategy for Source Separation in the frequency domain
• ​​​​​​Thomas Le Roux: Where is the beat: introducing ’AV-PhonemeBeatSync’, a multimodal singing dataset aiming at understanding coarticulation and rhythm in singing