Proposals

Audio
Field
Contact
Title
With Discussant
Description
Music informaticsSarti, Mezza, ComanducciAudio prediction for Networked Music Performance yesIn recent years, live music performances over the Internet have become a reality. However, the inevitable network packets loss is still affecting the experience in a significant way, causing abrupt interruptions and glitches in the audio stream. In this respect, we aim at developing new deep learning-based techniques that would tackle this issue by predicting the next few milliseconds of audio, while ensuring the high quality and seamlessness of the reconstructed music signal.
Musical acousticsAntonacci, GonzalezEffect of arching in the vibrational response of violin top plates (or full violins)yes Recently, we have studied how the outline, thickness and material parameters affect the vibrational response of free violin top plates. The objective of this thesis is to study the effect of the arching profile in the vibrational response. For a short thesis it would be to reproduce the results of our last paper including the arching, for a longer thesis we would study the complete violin not only the top plate.
Musical acousticsAntonacci, GonzalezSimulating the bridge admittance of complete violins in Comsol
yesBridge admittance (the frequency response function measured at the bridge) is one of the easiest and most informatives experiments that are currently done with violins. The objective of this thesis is to simulate this measurement in Comsol for a data set of 2000 virtual violins and study the correlations between the violin parameters and the bridge admittance.
Musical acousticsAntonacci, GonzalezDesign and production of 3D printed / CNC luthier toolsyesLuthier tools are exremely specialised and expensive. This project looks into creating open source designs for luthier specific tools that can be 3D printed or carved from solid material with a CNC.
Acoustic Scenes and EventsSarti, MezzaDetection of anomalous sounds in domestic environmentsyesThe objective is the development of intelligent systems capable of monitoring a domestic environment to detect acoustic anomalies. The idea is to learn a suitable "normal state" for the monitored soundscape and to track the deviations thereof with minimal or no supervision.
Audio signal processing
Sarti, BernardiniVirtual Analog Modeling, Audio Circuit Emulation, Physical Modeling Sound Synthesis through Wave Digital Filtersyes
Audio signal processing
Sarti, Giampiccolo, BernardiniImplementation of Wave Digital scattering matrices absorbing controlled sources yesIn the Wave Digital domain, topological scattering junctions can absorb certain non-reciprocal elements. The thesis concerns the derivation of formulas for the efficient computation of their scattering matrices, such that they can be exploited for Virtual Analog applications.
Audio signal processing
Sarti, Giampiccolo, BernardiniModeling Nonlinear Functions with Hysteresis in the Wave Digital DomainyesEfficiently modeling hysteretic curves is still today an open field of research. The aim of the thesis is to model such multivariate functions in the Wave Digital domain. Possible applications range from circuit simulation to Virtual Analog modeling (e.g., nonlinear modeling of audio transformers).
Musical acousticsOlivieri, Gonzalez, AntonacciTowards white-box data-driven methods for Near-field Acoustic HolographyyesNear-field Acoustic Holography (NAH) is a powerful technique to study the velocity field on vibrating objects in a contactless way (e.g., without accelerometer sensors). Recently, we developed a fully data-driven approach for NAH with Convolutional Neural Networks which can increase the performances of previous state-of-the-art methods. The goal of this thesis is to investigate and understand what the networks learned, in order to transform the current black box methodology towards a white box one.
Image and Video
Field
Contact
Title
With Discussant
Description
Image/video forensicsBestagini, Bonettini
Detect and localize image and video manipulations
yesImages and videos can be manipulated in many different ways (e.g., object insertion and removal, local retouching, laundering operations, etc.). We are interested in developing methods to detect and localize possible editing operations on images and videos.
Image/video forensicsBestagini, Bonettini
Distinguish original videos from DeepFakesyesDeepFake videos can be maliciously spread online. We are interested in developing techniques to detect whether a video is a DeepFake or not, why a detector says a video is fake, and understand which DeepFake generation software has been used to create a video.
Image/video forensicsBestagini, MandelliAssess the authenticity of satellite imagesyesSatellites can acquire visual data with different sensors. We are interested in developing techniques that verify whether an overhead image has been edited or not.
Image/video forensicsBestagini, MandelliForensic analysis of scientific imagesyesScientific publications in the life science area typically contain charcateristic kinds of images to showcase the achieved results (e.g., western blots, microscopy acquisitions, etc.). As these images differ from natural photographs, we are interested in developing novel techniques to detect possible scientific image forgery operations.
Image/video processingMarcon, BonettiniAnalysis of hyperspectral X-ray images for food quality assessmentyesX-ray acquisitions are beneficial in food contaminant analysis as they can detect both metallic and non-metallic objects. The goal of a thesis in this field is to develop processing techniques that help dealing with X-ray acquisition in food contaminant detection applications (e.g., denoising, detection, segmentation, etc.).
Image/video processingBestaginiAnalysis of badminton match videosyesGiven a set of videos taken with a fixed camera placed behind a badminton player, extract and analyse salient pieces of information in an automatci fashion (e.g., player position in time, hits, misses, etc.).
Geophysics
Contact
Title
With Discussant
Description
Tubaro, Lipari, PicettiImproving Full Waveform Inversion with CNNsyesFull Waveform Inversion reconstructs the subsurface velocities from a set of measurements. It is very expensive, time-consuming and prone to a number of tips and tricks for avoiding local minima, numerical instability and optimization errors.
Tubaro, Lipari, PicettiDenoising and Interpolation of seismic data through CNNsyesThe amount of data is constantly increasing and the areas of interest are more and more complex to analyze. Moreover, they require a subsurface mapping at increasingly higher resolution and higher fidelity. Can CNNs help this process?
Tubaro, Lipari, PicettiMachine Learning guided Seismic InterpretationyesHuman experts visually inspects seismic images looking for subsurface features. On the other hand, Machine Learning techniques have proven to be effective in image segmentation (i.e., recognizing objects and targets from a set of pixels). Can we merge these two worlds?
Tubaro, Lipari, PicettiPhysics-aware Transfer LearningyesCan a neural network learn Physics?

Currently on-going

Expand list
Field
Supervisor
Topic
Student(s)
Space-time audioAntonacciPerceptual evaluation of sound field reconstructionMiriam Papagno
Video forensicsBestagini, BonettiniDeepfake video detectionBingyang Hu
Audio forensicsBestaginiAudio splicing detection exploiting acquisition tracesDaniele Ugo Leonzio
Audio forensicsBestaginiMicrophone identification from speech recordingsAntonio Giganti
Audio forensicsBestagini, Borrelli, SalviSynthetic speech detection based on sentiment analysisEmanuele Conti
Audio forensicsBestagini, BorrelliSynthetic speech detection in noisy conditionsEleonora Landini
Multimedia forensicsBestagini, MandelliDevice source attribution in modern scenarios: from audio to videoDavide Dal Cortivo
Audio forensicsBestagini, MandelliTime-scaling detection in audio recordingsMichele Pilia
Audio forensicsBestagini, BorrelliSpeech clarity parameters estimation in reverberant environmentsMattia Papa
Space-time audioAntonacci, BorraParametric Virtual Miking using Distributed Microphone ArraysMarco Langè
Space-time audioAntonacci, Borrelli, BorraBeamforming and Speaker Identification through Deep Neural Networks Matteo Scerbo
Space-time audioAntonacci, Pezzoli, Borra, BernardiniRoom Impulse Response Interpolation with Deep PriorDavide Perini
Space-time audioAntonacci, Comanducci3D audio with irregular microphone setups using deep learningDavide Mori
Music informaticsZanoni, ComanducciMusic Style transfer based on the analysis of the complexityDavide Gioiosa
Space-time audioSarti, Borra3D sound field rendering with loudspeaker array.Francesco Pino
Audio Signal ProcessingSarti, Giampiccolo, BernardiniMultithreaded Implementation of Scattering Iterative MethodsAntonino Natoli

Past (from 2017)

Expand list
Field
Supervisor
Title
Student(s)
Link
AcousticsAntonacciData-driven interpolation of FRFMatteo Acerbi
Audio forensicsAntonacciClosed and open set classification of real and AI synthesised speechMichelangelo Medori
Space-time audioAntonacci, ComanducciInterpreting Deep Neural Networks Models for Acoustic Source Localization using Layer-wise Relevance PropagationAlessandro Montalihttps://www.politesi.polimi.it/handle/10589/169239
Musical AcousticsAntonacciModal analysis and optimization of the top plate of string instruments through a parametric control of their shapeSalvi Davidehttps://www.politesi.polimi.it/handle/10589/166557
Musical AcousticsAntonacci An approach for Near-field Acoustic Holography based on Convolutional AutoencodersOlivieri Marcohttps://www.politesi.polimi.it/handle/10589/167039
Music informaticsSarti, Borrelli, ComanducciCellular music : a novel music-generation platform based on an evolutionary paradigmMatteo Manzolinihttps://www.politesi.polimi.it/handle/10589/167291
Music informaticsSarti, BorrelliMusic emotion detection. A framework based on electrodermal activities.Gioele Pozzihttps://www.politesi.polimi.it/handle/10589/152931
Audio ProcessingSarti, ComanducciAudio frame reconstruction from incomplete observations using Deep Learning techniquesSchils Minh Cédrichttps://matheo.uliege.be/handle/2268.2/10138
Audio ForensicsAntonacciAn approach to room volume estimation from single-channel speech signals based on neural networksCastelnuovo Carlohttps://www.politesi.polimi.it/handle/10589/164749
Audio ForensicsBestaginiAudio Splicing Detection and Localization Based on Acoustic CuesCapoferri Davidehttps://www.politesi.polimi.it/handle/10589/164950
Space-time audioAntonacci, Borra, BernardiniAnalysis of Uniform Linear Arrays of Differential MicrophonesBertuletti Ivanhttps://www.politesi.polimi.it/handle/10589/154604
Music InformaticsSarti, ComanducciTechniques for mitigating the impact of latency in
Networked Music Performance (NMP) through adaptive metronomes
Battello Riccardohttps://www.politesi.polimi.it/handle/10589/152923
Audio processingSarti, BernardiniWave Digital Modeling and Simulation of Nonlinear Electromagnetic CircuitsGiampiccolo Riccardohttps://www.politesi.polimi.it/handle/10589/153994
Audio processingSarti, BernardiniAntiderivative Antialiasing in Nonlinear Wave Digital FiltersAlbertini Davidehttps://www.politesi.polimi.it/handle/10589/152934
Audio processingSarti, BernardiniWave Digital Implementation of Nonlinear Audio Circuits based on the Scattering Iterative MethodProverbio Alessandrohttps://www.politesi.polimi.it/handle/10589/152323
Audio processingAntonacciA system for super resolution vibrometric analysis through convolutional neural networksCampagnoli Chiarahttps://www.politesi.polimi.it/handle/10589/152613
Audio processingAntonacciDevelopment of a low-cost platform for acoustic and vibrometric analysis on lutherie products, with a special focus on the estimation of the elastic parameters of the tonewoodVilla Lucahttps://www.politesi.polimi.it/handle/10589/150531
ForensicsBestaginiConvolutional and recurrent neural networks for video tampering detection and localizationCannas Edoardo Danielehttps://www.politesi.polimi.it/handle/10589/149900
Audio processingBestaginiDNN based post-filtering for quality improvement of AMR-WB decoded speechGupta Kishanhttps://www.politesi.polimi.it/handle/10589/151000
Music information retrievalSartiMusical instrument recognition: a transfer learning approachMolgora Andreahttps://www.politesi.polimi.it/handle/10589/147383
Music information retrievalSartiUnsupervised domain adaptation for deep learning based acoustic scene classificationMezza Alessandro Ilichttps://www.politesi.polimi.it/handle/10589/145573
Image and videoMarconUpper body postural assessment for common dentistry visual aidsTrotta Emiliohttps://www.politesi.polimi.it/handle/10589/145563
Music information retrievalAntonacciAn investigation of piano transcription algorithm for jazz musicMarzorati Giorgiohttps://www.politesi.polimi.it/handle/10589/144745
Image and videoTubaroReal-time tracking of electrode during deep-brain surgeryDilauro Valeriohttps://www.politesi.polimi.it/handle/10589/144685
Image and videoMarconAnalytical estimation of the error on the radius of industrial pipesLazzarin Sarahttps://www.politesi.polimi.it/handle/10589/144394
Image and videoMarcon3D reconstruction from stereo video acquired from odontoiatric microscopeSpatafora Leonardohttps://www.politesi.polimi.it/handle/10589/143780
Space-time audioSartiA geometrical method of 3D sound spatialization for virtual reality applicationsIamele Jacopohttps://www.politesi.polimi.it/handle/10589/143770
Image and videoMarconDenoising and classification of hyperspectral X-ray images for food quality assessmentRe Marcohttps://www.politesi.polimi.it/handle/10589/142922
Image and videoMarconA computer vision approach for assessment of dental bracket removalBehnami Arezoohttps://www.politesi.polimi.it/handle/10589/142362
GeophysicsBestaginiLandmine detection on GPR data employing convolutional autoencoderTesta Giuseppehttps://www.politesi.polimi.it/handle/10589/142106
Music information retrievalSartiAutomatic playlist generation using recurrent neural networkIrene Rosilde Tatianahttps://www.politesi.polimi.it/handle/10589/142101
ForensicsBestaginiA study on Bagging-Voronoi algorithm for tampering localizationCereghetti Corinne Elenahttps://www.politesi.polimi.it/handle/10589/141725
Audio processingSartiStudio sull'implementazione degli algoritmi per il musical instruments ed il sound reinforcement basato su un processore multicoreAretino Michelehttps://www.politesi.polimi.it/handle/10589/139079
Music information retrievalSartiA personalized metric for music similarity using Siamese deep neural networksSala Federicohttps://www.politesi.polimi.it/handle/10589/139078
Space-time audioAntonacciConvolutional neural networks applied to space-time audio processing applicationsComanducci Lucahttps://www.politesi.polimi.it/handle/10589/139077
Music information retrievalSartiLearning a personalized similarity metric for musical contentCarloni Lucahttps://www.politesi.polimi.it/handle/10589/139076
Space-time audioCancliniDenoising in the spherical harmonic domain of sound scenes acquired by compact arraysBorrelli Clarahttps://www.politesi.polimi.it/handle/10589/139075
Space-time audioAntonacciSimulazione di sistemi complessi. Case study : l'altoparlante a trombaMoscara Francescohttps://www.politesi.polimi.it/handle/10589/139074
Music information retrievalSartiBeat tracking using recurrent neural network : a transfer learning approachFiocchi Davidehttps://www.politesi.polimi.it/handle/10589/139073
Space-time audioSarti, BernardiniSteerable differential microphone arraysLovatello Jacopohttps://www.politesi.polimi.it/handle/10589/139072
Music information retrievalSartiPython-based framework for managing a base of complex data for music information retrievalAvocone Giuseppehttps://www.politesi.polimi.it/handle/10589/138449
Space-time audioAntonacciA plenacoustic approach to sound scene manipulationPicetti Francescohttps://www.politesi.polimi.it/handle/10589/138430
Music information retrievalSartiIndividual semantic modeling for music information retrievalAnsidei Pietrohttps://www.politesi.polimi.it/handle/10589/137160
Music information retrievalSartiChord sequences : evaluating the effect of complexity on preferenceFoscarin Francescohttps://www.politesi.polimi.it/handle/10589/136448
Space-time audioAntonacciReconstruction of the soundfield in arbitrary locations using the distributed ray space transformPezzoli Mircohttps://www.politesi.polimi.it/handle/10589/136447
Space-time audioSartiA method for HRTF personalization : weighted sparse representation synthesis of HRTFsZhu Mohttps://www.politesi.polimi.it/handle/10589/135952
Image and videoMarconSistema per il rilevamento automatico di contaminanti alimentari basato su immagini iperspettraliRamoni Francescohttps://www.politesi.polimi.it/handle/10589/135891
Image and videoMarconPostural assessment in dentistry by computer visionPignatelli Nicolahttps://www.politesi.polimi.it/handle/10589/135030
Space-time audioAntonacciRobust parametric spatial audio processing using beamforming techniquesMilano Guendalinahttps://www.politesi.polimi.it/handle/10589/134609
Music information retrievalSartiAudio features compensation based on coding bitrateTavella Maria Stellahttps://www.politesi.polimi.it/handle/10589/134607
Space-time audioAntonacciEstimation of singing voice quality through microphone in air and contact microphoneLandini Robertahttps://www.politesi.polimi.it/handle/10589/134604
ForensicsBestaginiJPEG-based forensics through convolutional neural networksBonettini Nicolòhttps://www.politesi.polimi.it/handle/10589/133727
Audio processingSarti, BernardiniModeling nonlinear 3-terminal devices in the wave digital domainVergani Alessio Emanuelehttps://www.politesi.polimi.it/handle/10589/133184
ForensicsBestaginiAnalysis of different footprints for JPEG compression detectionChen Kehttps://www.politesi.polimi.it/handle/10589/132721