In recent years, audio and video deepfake technology has advanced relentlessly, severely impacting people's reputation and reliability. Several factors have facilitated the growing deepfake threat. On the one hand, the hyper-connected society of social and mass media enables the spread of multimedia content worldwide in real-time, facilitating the dissemination of counterfeit material. On the other hand, neural network-based techniques have made deepfakes easier to produce and difficult to detect, showing that the analysis of low-level features is no longer sufficient for the task. This situation makes it crucial to design systems that allow detecting deepfakes at both video and audio levels. In this paper, we propose a new audio spoofing detection system leveraging emotional features. The rationale behind the proposed method is that audio deepfake techniques cannot correctly synthesize natural emotional behavior. Therefore, we feed our deepfake detector with high-level features obtained from a state-of-the-art Speech Emotion Recognition (SER) system. As the used descriptors capture semantic audio information, the proposed system proves robust in cross-dataset scenarios outperforming the considered baseline on multiple datasets.

Several methods for synthetic audio speech generation have been developed in the literature through the years. With the great technological advances brought by deep learning, many novel synthetic speech techniques achieving incredible realistic results have been recently proposed. As these methods generate convincing fake human voices, they can be used in a malicious way to negatively impact on today’s society (e.g., people impersonation, fake news spreading, opinion formation). For this reason, the ability of detecting whether a speech recording is synthetic or pristine is becoming an urgent necessity. In this work, we develop a synthetic speech detector. This takes as input an audio recording, extracts a series of hand-crafted features motivated by the speech-processing literature, and classify them in either closed-set or open-set. The proposed detector is validated on a publicly available dataset consisting of 17 synthetic speech generation algorithms ranging from old fashioned vocoders to modern deep learning solutions. Results show that the proposed method outperforms recently proposed detectors in the forensics literature.

No abstract

Underwater robots emit sound during operations which can deteriorate the quality of acoustic data recorded by on-board sensors or disturb marine fauna during in vivo observations. Notwithstanding this, there have only been a few attempts at characterizing the acoustic emissions of underwater robots in the literature, and the datasheets of commercially available devices do not report information on this topic. This work has a twofold goal. First, we identified a setup consisting of a camera directly mounted on the robot structure to acquire the acoustic data and two indicators (i.e., spectral roll-off point and noise introduced to the environment) to provide a simple and intuitive characterization of the acoustic emissions of underwater robots carrying out specific maneuvers in specific environments. Second, we performed the proposed analysis on three underwater robots belonging to the classes of remotely operated vehicles and underwater legged robots. Our results showed how the legged device produced a clearly different signature compared to remotely operated vehicles which can be an advantage in operations that require low acoustic disturbance. Finally, we argue that the proposed indicators, obtained through a standardized procedure, may be a useful addition to datasheets of existing underwater robots.

Manipulating speech audio recordings through splicing is a task within everyone's reach. Indeed, it is very easy to collect through social media multiple audio recordings from well-known public figures (e.g., actors, politicians, etc.). These can be cut into smaller excerpts that can be concatenated in order to generate new audio content. As a fake speech from a famous person can be used for fake news spreading and negatively impact on the society, the ability of detecting whether a speech recording has been manipulated is a task of great interest in the forensics community. In this work, we focus on speech audio splicing detection and localization. We leverage the idea that distinct recordings may be acquired in different environments, which are typically characterized by distinctive reverberation cues. Exploiting this property, our method estimates inconsistencies in the reverberation time throughout a speech recording. If reverberation inconsistencies are detected, the audio track is tagged as manipulated and the splicing point time instant is estimated.