Davide Salvi

Luigi Attorresi, Davide Salvi, Clara Borrelli et al.

The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work we present a novel approach for synthetic speech detection, exploiting the combination of two high-level semantic properties of the human voice. On one side, we focus on speaker identity cues and represent them as speaker embeddings extracted using a state-of-the-art method for the automatic speaker verification task. On the other side, voice prosody, intended as variations in rhythm, pitch or accent in speech, is extracted through a specialized encoder. We show that the combination of these two embeddings fed to a supervised binary classifier allows the detection of deepfake speech generated with both Text-to-Speech and Voice Conversion techniques. Our results show improvements over the considered baselines, good generalization properties over multiple datasets and robustness to audio compression.

Irene Amerini, Mauro Barni, Sebastiano Battiato et al.

AI-generated synthetic media, also called Deepfakes, have significantly influenced so many domains, from entertainment to cybersecurity. Generative Adversarial Networks (GANs) and Diffusion Models (DMs) are the main frameworks used to create Deepfakes, producing highly realistic yet fabricated content. While these technologies open up new creative possibilities, they also bring substantial ethical and security risks due to their potential misuse. The rise of such advanced media has led to the development of a cognitive bias known as Impostor Bias, where individuals doubt the authenticity of multimedia due to the awareness of AI's capabilities. As a result, Deepfake detection has become a vital area of research, focusing on identifying subtle inconsistencies and artifacts with machine learning techniques, especially Convolutional Neural Networks (CNNs). Research in forensic Deepfake technology encompasses five main areas: detection, attribution and recognition, passive authentication, detection in realistic scenarios, and active authentication. This paper reviews the primary algorithms that address these challenges, examining their advantages, limitations, and future prospects.

Daniele Mari, Davide Salvi, Paolo Bestagini et al.

Recent advances in deep learning and computer vision have made the synthesis and counterfeiting of multimedia content more accessible than ever, leading to possible threats and dangers from malicious users. In the audio field, we are witnessing the growth of speech deepfake generation techniques, which solicit the development of synthetic speech detection algorithms to counter possible mischievous uses such as frauds or identity thefts. In this paper, we consider three different feature sets proposed in the literature for the synthetic speech detection task and present a model that fuses them, achieving overall better performances with respect to the state-of-the-art solutions. The system was tested on different scenarios and datasets to prove its robustness to anti-forensic attacks and its generalization capabilities.

Viola Negroni, Davide Salvi, Daniele Ugo Leonzio et al.

In this paper, we introduce the concept of forensic similarity in the speech deepfake detection domain, which aims to determine whether two audio segments share the same underlying forensic traces. Our approach is inspired by prior work in the image domain. To transfer this idea to the audio domain, we propose a two-stage deep learning framework consisting of a Siamese-based feature extractor and a core decision module, referred to as the similarity network. The system goal to assess whether two speech samples originate from the same source by comparing their forensic characteristics. In practice, the model maps pairs of audio segments to a similarity score indicating whether they contain identical or different forensic traces. We evaluate the proposed method on the emerging task of source verification, demonstrating its ability to determine whether two speech samples were generated by the same model. In addition, we explore its applicability to audio splicing detection as a complementary use case. Experimental results show that the proposed approach generalizes well to previously unseen forensic traces, highlighting its robustness, flexibility, and practical relevance for digital audio forensics.

Viola Negroni, Davide Salvi, Alessandro Ilic Mezza et al.

Speech deepfakes pose a significant threat to personal security and content authenticity. Several detectors have been proposed in the literature, and one of the primary challenges these systems have to face is the generalization over unseen data to identify fake signals across a wide range of datasets. In this paper, we introduce a novel approach for enhancing speech deepfake detection performance using a Mixture of Experts architecture. The Mixture of Experts framework is well-suited for the speech deepfake detection task due to its ability to specialize in different input types and handle data variability efficiently. This approach offers superior generalization and adaptability to unseen data compared to traditional single models or ensemble methods. Additionally, its modular structure supports scalable updates, making it more flexible in managing the evolving complexity of deepfake techniques while maintaining high detection accuracy. We propose an efficient, lightweight gating mechanism to dynamically assign expert weights for each input, optimizing detection performance. Experimental results across multiple datasets demonstrate the effectiveness and potential of our proposed approach.

Viola Negroni, Davide Salvi, Paolo Bestagini et al.

Speech deepfake detection has recently gained significant attention within the multimedia forensics community. Related issues have also been explored, such as the identification of partially fake signals, i.e., tracks that include both real and fake speech segments. However, generating high-quality spliced audio is not as straightforward as it may appear. Spliced signals are typically created through basic signal concatenation. This process could introduce noticeable artifacts that can make the generated data easier to detect. We analyze spliced audio tracks resulting from signal concatenation, investigate their artifacts and assess whether such artifacts introduce any bias in existing datasets. Our findings reveal that by analyzing splicing artifacts, we can achieve a detection EER of 6.16% and 7.36% on PartialSpoof and HAD datasets, respectively, without needing to train any detector. These results underscore the complexities of generating reliable spliced audio data and lead to discussions that can help improve future research in this area.

Amit Kumar Singh Yadav, Kratika Bhagtani, Davide Salvi et al.

Methods that can generate synthetic speech which is perceptually indistinguishable from speech recorded by a human speaker, are easily available. Several incidents report misuse of synthetic speech generated from these methods to commit fraud. To counter such misuse, many methods have been proposed to detect synthetic speech. Some of these detectors are more interpretable, can generalize to detect synthetic speech in the wild and are robust to noise. However, limited work has been done on understanding bias in these detectors. In this work, we examine bias in existing synthetic speech detectors to determine if they will unfairly target a particular gender, age and accent group. We also inspect whether these detectors will have a higher misclassification rate for bona fide speech from speech-impaired speakers w.r.t fluent speakers. Extensive experiments on 6 existing synthetic speech detectors using more than 0.9 million speech signals demonstrate that most detectors are gender, age and accent biased, and future work is needed to ensure fairness. To support future research, we release our evaluation dataset, models used in our study and source code at https://gitlab.com/viper-purdue/fairssd.

Emma Coletta, Davide Salvi, Viola Negroni et al.

The rise of AI-driven generative models has enabled the creation of highly realistic speech deepfakes - synthetic audio signals that can imitate target speakers' voices - raising critical security concerns. Existing methods for detecting speech deepfakes primarily rely on supervised learning, which suffers from two critical limitations: limited generalization to unseen synthesis techniques and a lack of explainability. In this paper, we address these issues by introducing a novel interpretable one-class detection framework, which reframes speech deepfake detection as an anomaly detection task. Our model is trained exclusively on real speech to characterize its distribution, enabling the classification of out-of-distribution samples as synthetically generated. Additionally, our framework produces interpretable anomaly maps during inference, highlighting anomalous regions across both time and frequency domains. This is done through a Student-Teacher Feature Pyramid Matching system, enhanced with Discrepancy Scaling to improve generalization capabilities across unseen data distributions. Extensive evaluations demonstrate the superior performance of our approach compared to the considered baselines, validating the effectiveness of framing speech deepfake detection as an anomaly detection problem.

Davide Salvi, Sebastian Gonzalez, Fabio Antonacci et al.

We recently developed a neural network that receives as input the geometrical and mechanical parameters that define a violin top plate and gives as output its first ten eigenfrequencies computed in free boundary conditions. In this manuscript, we use the network to optimize several error functions, with the goal of analyzing the relationship between the eigenspectrum problem for violin top plates and their geometry. First, we focus on the violin outline. Given a vibratory feature, we find which is the best geometry of the plate to obtain it. Second, we investigate whether, from the vibrational point of view, a change in the outline shape can be compensated by one in the thickness distribution and vice versa. Finally, we analyze how to modify the violin shape to keep its response constant as its material properties vary. This is an original technique in musical acoustics, where artificial intelligence is not widely used yet. It allows us to both compute the vibrational behavior of an instrument from its geometry and optimize its shape for a given response. Furthermore, this method can be of great help to violin makers, who can thus easily understand the effects of the geometry changes in the violins they build, shedding light on one of the most relevant and, at the same time, less understood aspects of the construction process of musical instruments.

Sebastian Gonzalez, Davide Salvi, Daniel Baeza et al.

Of all the characteristics of a violin, those that concern its shape are probably the most important ones, as the violin maker has complete control over them. Contemporary violin making, however, is still based more on tradition than understanding, and a definitive scientific study of the specific relations that exist between shape and vibrational properties is yet to come and sorely missed. In this article, using standard statistical learning tools, we show that the modal frequencies of violin tops can, in fact, be predicted from geometric parameters, and that artificial intelligence can be successfully applied to traditional violin making. We also study how modal frequencies vary with the thicknesses of the plate (a process often referred to as {\em plate tuning}) and discuss the complexity of this dependency. Finally, we propose a predictive tool for plate tuning, which takes into account material and geometric parameters.