Publications

@inproceedings{salvi2024listening,

title = {Listening Between the Lines: Synthetic Speech Detection Disregarding Verbal Content},

author = {D. Salvi and Temesgen S. B. and P. Bestagini and S. Tubaro},

year  = {2024},

date = {2024-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Workshop},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{leonzio2024water,

title = {Water Leak Detection via Domain Adaptation},

author = {Daniele Ugo Leonzio and Paolo Bestagini and Marco Marcon and Gian Paolo Quarta and Stefano Tubaro},

doi = {10.1109/ICASSP48485.2024.10447165},

year  = {2024},

date = {2024-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{singhyadav2024mdrt,

title = {Mdrt: Multi-Domain Synthetic Speech Localization},

author = {Amit Kumar Singh Yadav and Kratika Bhagtani and Sriram Baireddy and Paolo Bestagini and Stefano Tubaro and Edward J. Delp},

doi = {10.1109/ICASSP48485.2024.10446471},

year  = {2024},

date = {2024-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{cannas2024one,

title = {A One-Class Approach to Detect Super-Resolution Satellite Imagery with Spectral Features},

author = {E. D. Cannas and P. Beaus and P. Bestagini and F. Marques and S. Tubaro},

doi = {10.1109/ICASSP48485.2024.10446619},

year  = {2024},

date = {2024-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{giampiccolo2024mxrp90,

title = {Wave Digital Model of the MXR Phase 90 based on a Time-Varying Resistor Approximation of JFET Elements},

author = {Riccardo Giampiccolo and Samuele Del Moro and Claudio Eutizi and Mattia Massimi and Oliviero Massi and Alberto Bernardini},

year  = {2024},

date = {2024-01-01},

booktitle = {27th International Conference on Digital Audio Effects (DAFx24)},

pages = {89-96},

address = {Guildford, UK},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mezza2024freqdfdn,

title = {Modeling the Frequency-Dependent Sound Energy Decay of Acoustic Environments With Differentiable Feedback Delay Networks},

author = {Alessandro Ilic Mezza and Riccardo Giampiccolo and Alberto Bernardini},

year  = {2024},

date = {2024-01-01},

booktitle = {Proceedings of the 27th International Conference on Digital Audio Effects (DAFx)},

pages = {238-245},

address = {Guildford, UK},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{giampiccolo2024mimofdn,

title = {Differentiable MIMO Feedback Delay Networks for Multichannel Room Impulse Response Modeling},

author = {Riccardo Giampiccolo and Alessandro Ilic Mezza and Alberto Bernardini},

year  = {2024},

date = {2024-01-01},

booktitle = {Proceedings of the 27th International Conference on Digital Audio Effects (DAFx)},

pages = {278-285},

address = {Guildford, UK},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mezza2024benchddss,

title = {Benchmarking Music Demixing Models for Deep Drum Source Separation},

author = {Alessandro Ilic Mezza and Riccardo Giampiccolo and Alberto Bernardini and Augusto Sarti},

doi = {10.1109/IS262782.2024.10704147},

isbn = {9798350366525},

year  = {2024},

date = {2024-01-01},

urldate = {2024-10-08},

booktitle = {Proceedings of the 5th IEEE International Symposium on the Internet of Sounds (IS2)},

publisher = {IEEE},

address = {Erlangen, Germany},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mezza2023lars,

title = {LARS: An Open-Source VST3 Plug-In for Deep Drums Demixing with Pretrained Models},

author = {Alessandro Ilic Mezza and Riccardo Di Palma and Edoardo Morena and Alessandro Orsatti and Riccardo Giampiccolo and Alberto Bernardini},

year  = {2023},

date = {2023-11-01},

booktitle = {24th International Society for Music Information Retrieval Conference (ISMIR) - LBD Session},

address = {Milan, Italy},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mezza2023sdx,

title = {StemGMD: A Large-Scale Multi-Kit Audio Dataset for Deep Drums Demixing},

author = {Alessandro Ilic Mezza and Riccardo Giampiccolo and Alberto Bernardini and Augusto Sarti},

year  = {2023},

date = {2023-11-01},

booktitle = {2023 SDX Workshop},

address = {Milan, Italy},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{giampiccolo2023tubes,

title = {A Quadric Surface Model of Vacuum Tubes for Virtual Analog Applications},

author = {Riccardo Giampiccolo and Stefano D'Angelo and Alberto Bernardini and Augusto Sarti},

year  = {2023},

date = {2023-09-01},

booktitle = {International Conference on Digital Audio Effects (DAFx)},

pages = {296-303},

address = {Copenaghen, Denmark},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{massi2023bjt,

title = {Explicit Vector Wave Digital Filter Modeling of Circuits with a Single Bipolar Junction Transistor},

author = {Olivieri Massi and Riccardo Giampiccolo and Alberto Bernardini and Augusto Sarti},

year  = {2023},

date = {2023-09-01},

booktitle = {International Conference on Digital Audio Effects (DAFx)},

pages = {172-179},

address = {Copenaghen, Denmark},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{salvi2023are,

title = {Are you Really Alone? Detecting the use of Speech Separation Techniques on Audio Recordings},

author = {Davide Salvi and Mirco Pezzoli and Sara Mandelli and Paolo Bestagini and Stefano Tubaro},

doi = {10.1109/WIFS58808.2023.10374717},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE International Workshop on Information Forensics and Security (WIFS)},

pages = {1-6},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{salvi2023reliability,

title = {Reliability Estimation for Synthetic Speech Detection},

author = {Davide Salvi and Paolo Bestagini and Stefano Tubaro},

doi = {10.1109/ICASSP49357.2023.10095524},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{salvi2023towards,

title = {Towards Frequency Band Explainability in Synthetic Speech Detection},

author = {Davide Salvi and Paolo Bestagini and Stefano Tubaro},

doi = {10.23919/EUSIPCO58844.2023.10289804},

year  = {2023},

date = {2023-01-01},

booktitle = {European Signal Processing Conference (EUSIPCO)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{salvi2023synthetic,

title = {Synthetic Speech Detection through Audio Folding},

author = {Davide Salvi and Paolo Bestagini and Stefano Tubaro},

url = {https://doi.org/10.1145/3592572.3592844},

doi = {10.1145/3592572.3592844},

year  = {2023},

date = {2023-01-01},

booktitle = {ACM International Workshop on Multimedia AI against Disinformation},

publisher = {Association for Computing Machinery},

series = {MAD '23},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{singhyadav2023dsvae,

title = {DSVAE: Disentangled Representation Learning for Synthetic Speech Detection},

author = {Amit Kumar Singh Yadav and Kratika Bhagtani and Ziyue Xiang and Paolo Bestagini and Stefano Tubaro and Edward J. Delp},

doi = {10.1109/ICMLA58977.2023.00072},

year  = {2023},

date = {2023-01-01},

booktitle = {International Conference on Machine Learning and Applications (ICMLA)},

pages = {472-479},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{singhyadav2023ps3dt,

title = {PS3DT: Synthetic Speech Detection Using Patched Spectrogram Transformer},

author = {Amit Kumar Singh Yadav and Ziyue Xiang and Kratika Bhagtani and Paolo Bestagini and Stefano Tubaro and Edward J. Delp},

doi = {10.1109/ICMLA58977.2023.00075},

year  = {2023},

date = {2023-01-01},

booktitle = {International Conference on Machine Learning and Applications (ICMLA)},

pages = {496-503},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{bhagtani2023fgssat,

title = {FGSSAT : Unsupervised Fine-Grain Attribution of Unknown Speech Synthesizers Using Transformer Networks},

author = {Kratika Bhagtani and Amit Kumar Singh Yadav and Ziyue Xiang and Paolo Bestagini and Edward J. Delp},

doi = {10.1109/IEEECONF59524.2023.10476982},

year  = {2023},

date = {2023-01-01},

booktitle = {Asilomar Conference on Signals, Systems, and Computers},

pages = {1135-1140},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{liu2023bifpro,

title = {BiFPro: A Bidirectional Facial-data Protection Framework against DeepFake},

author = {Honggu Liu and Xiaodan Li and Wenbo Zhou and Han Fang and Paolo Bestagini and Weiming Zhang and Yuefeng Chen and Stefano Tubaro and Nenghai Yu and Yuan He and Hui Xue},

url = {https://doi.org/10.1145/3581783.3613752},

doi = {10.1145/3581783.3613752},

year  = {2023},

date = {2023-01-01},

booktitle = {ACM International Conference on Multimedia},

abstract = {The rapid progress of the DeepFake technique has caused severe privacy problems. Thus protecting facial data against DeepFake becomes an urgent requirement. Face protection can be regarded as a bidirectional process: Face-out-detection (FOD) and Face-in-forensics (FIF). For FOD, the detectability should be satisfied when using the protected face to replace other faces. For FIF, traceability should be guaranteed when the protected face is replaced by others. For this, we propose a Bidirectional Facial-data Protection Framework (BiFPro) to protect face data comprehensively. This framework is composed of three main parts: Watermarking embedding, Face-out-detection (FOD) and Face-in-forensics (FIF). For the FOD case, we ensure the vulnerability of the original face by embedding fragile watermarking. Once the protected facial image is used to replace other faces, the watermarking information will be corrupted in the synthesized face images which can be used to detect the authenticity of the protected facial images. As for the FIF case, we guarantee the traceability of the protected face image by embedding robust watermarking, with which the fake faces can be traced with the reserved watermarking even after the face is swapped. Experimental results demonstrate that our proposed BiFPro could generate the watermarking which is fragile to FOD and at the same time robust to FIF with an average watermark extraction success rate reaching more than 95% when defending against the four advanced DeepFake techniques. Finally, we hope this work can encourage more initiative countermeasures against DeepFake.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{leonzio2023robust,

title = {Robust Water Leak Detection and Localization with Graph Signal Processing},

author = {Daniele Ugo Leonzio and Paolo Bestagini and Marco Marcon and Gian Paolo Quarta and Stefano Tubaro},

doi = {10.1109/IECON51785.2023.10312656},

year  = {2023},

date = {2023-01-01},

booktitle = {Annual Conference of the IEEE Industrial Electronics Society (IECON)},

pages = {1-5},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{liu2023it,

title = {It Wasn’t Me: Irregular Identity in Deepfake Videos},

author = {Honggu Liu and Paolo Bestagini and Lin Huang and Wenbo Zhou and Stefano Tubaro and Weiming Zhang and Nenghai Yu},

doi = {10.1109/ICIP49359.2023.10222654},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE International Conference on Image Processing (ICIP)},

pages = {2770-2774},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{giganti2023super,

title = {Super-Resolution of BVOC Maps by Adapting Deep Learning Methods},

author = {Antonio Giganti and Sara Mandelli and Paolo Bestagini and Marco Marcon and Stefano Tubaro},

doi = {10.1109/ICIP49359.2023.10223169},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE International Conference on Image Processing (ICIP)},

pages = {1650-1654},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{giganti2023supera,

title = {Super-Resolution of Bvoc Emission Maps Via Domain Adaptation},

author = {Antonio Giganti and Sara Mandelli and Paolo Bestagini and Marco Marcon and Stefano Tubaro},

doi = {10.1109/IGARSS52108.2023.10281779},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE International Geoscience and Remote Sensing Symposium (IGARSS)},

pages = {738-741},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{xiang2023extracting,

title = {Extracting Efficient Spectrograms From MP3 Compressed Speech Signals for Synthetic Speech Detection},

author = {Ziyue Xiang and Amit Kumar Singh Yadav and Stefano Tubaro and Paolo Bestagini and Edward J. Delp},

url = {https://doi.org/10.1145/3577163.3595104},

doi = {10.1145/3577163.3595104},

isbn = {9798400700545},

year  = {2023},

date = {2023-01-01},

booktitle = {ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec)},

pages = {163–168},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

series = {IH&MMSec '23},

abstract = {Many speech signals are compressed with MP3 to reduce the data rate. In many synthetic speech detection methods the spectrogram of the speech signal is used. This usually requires the speech signal to be fully decompressed. We show that the design of MP3 compression allows one to approximate the spectrogram of the MP3 compressed speech efficiently without fully decoding the compressed speech. We denote the spectograms obtained using our proposed approach by Efficient Spectrograms (E-Specs). E-Spec can reduce the complexity of spectrogram computation by ~77.60 percentage points (p.p.) and save ~37.87 p.p. of MP3 decoding time. E-Spec bypasses the reconstruction artifacts introduced by the MP3 synthesis filterbank, which makes it useful in speech forensics tasks. We tested E-Spec in the synthetic speech detection, where a detector is asked to determine whether a speech signal is synthesized or recorded from a human. We examined 4 different neural network architectures to evaluate the performance of E-Spec compared to speech features extracted from the fully decoded speech signal. E-Spec achieved the best synthetic speech detection performance for 3 architectures; it also achieved the best overall detection performance across architectures. The computation of E-Spec is an approximation to Short Time Fourier Transform (STFT). E-Spec can be extended to other audio compression methods.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{leonzio2023water,

title = {Water Leak Detection and Localization Using Convolutional Autoencoders},

author = {Daniele Ugo Leonzio and Paolo Bestagini and Marco Marcon and Gian Paolo Quarta and Stefano Tubaro},

doi = {10.1109/ICASSP49357.2023.10095760},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{singhyadav2023assd,

title = {ASSD: Synthetic Speech Detection in the AAC Compressed Domain},

author = {Amit Kumar Singh Yadav and Ziyue Xiang and Emily R. Bartusiak and Paolo Bestagini and Stefano Tubaro and Edward J. Delp},

doi = {10.1109/ICASSP49357.2023.10095043},

year  = {2023},

date = {2023-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{cannas2022panchromatic,

title = {Panchromatic Imagery Copy-Paste Localization Through Data-Driven Sensor Attribution},

author = {E. D. Cannas and J. Horváth and S. Baireddy and P. Bestagini and E. J. Delp and S. Tubaro},

doi = {10.1109/ICASSP43922.2022.9746308},

year  = {2022},

date = {2022-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{conti2022deepfake,

title = {Deepfake Speech Detection Through Emotion Recognition: A Semantic Approach},

author = {Emanuele Conti and Davide Salvi and Clara Borrelli and Brian Hosler and Paolo Bestagini and Fabio Antonacci and Augusto Sarti and Matthew C. Stamm and Stefano Tubaro},

doi = {10.1109/ICASSP43922.2022.9747186},

year  = {2022},

date = {2022-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{xiang2022forensic,

title = {Forensic Analysis and Localization of Multiply Compressed MP3 Audio Using Transformers},

author = {Ziyue Xiang and Paolo Bestagini and Stefano Tubaro and Edward J. Delp},

doi = {10.1109/ICASSP43922.2022.9747639},

year  = {2022},

date = {2022-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{papa2022data,

title = {A Data-Driven Approach for Acoustic Parameter Similarity Estimation of Speech Recording},

author = {Mattia Papa and Clara Borrelli and Paolo Bestagini and Fabio Antonacci and Augusto Sarti and Stefano Tubaro},

doi = {10.1109/ICASSP43922.2022.9747043},

year  = {2022},

date = {2022-01-01},

booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{cuccovillo2022spectral,

title = {Spectral Denoising for Microphone Classification},

author = {Luca Cuccovillo and Antonio Giganti and Paolo Bestagini and Patrick Aichroth and Stefano Tubaro},

url = {https://doi.org/10.1145/3512732.3533586},

doi = {10.1145/3512732.3533586},

year  = {2022},

date = {2022-01-01},

booktitle = {International Workshop on Multimedia AI against Disinformation},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}