do Nascimento Gomes, Rui

It is disclosed a visible light communication system that includes a plurality of emitter units (2), such as LEDs, installed within a communication environment, each capable of emitting data-encoded visible light signals to be received by at least a legitimate receiver unit (3). At least a controller unit (1) is configured to coordinate the operation of the emitter units (2), managing power levels and timing of signals to be transmitted by each emitter unit (2), in order to optimize the data transmission and security.

It is disclosed a method for enhancing security in visible light communication system, by employing constellation decomposition to provide physical layer security. By decomposing and transmitting signal constellations across multiple emitter units (2), that is, across multiple light sources, whose relative positions to a legitimate receiver unit (3) are known, the power and phase delay of each signal constellation are adjusted by a controller unit (1) to ensure that only legitimate receivers (3) are able to accurately reconstruct the transmitted data, thus preventing potential eavesdroppers.

It is an object of the present disclosure a method for generating a cybersecurity test recommendation. Central to the realisation of the test recommendation is the use of a knowledge base model (2) and an inference engine (3) to provide personalised cybersecurity test recommendations (c) to a system (1), based on system (a) and test parameters, in a more accurate and efficient way.

It is disclosed a method for operating a Text-to-Speech (TTS) framework (1) with an integrated Intonation-Aware Subsonic Harmonics (ISH) unit (2, 2.1, 2.2, 2.3, 2.4). Said method including a sequence of steps to generate and integrate inaudible subsonic frequencies (f.) with a synthesized speech waveform (g.), and to dynamically adjust them based on modulation parameters (e.) and contextual feedback (c.) derivable from the text inputted to the TTS system (1). This procedure influences prosodic features results in more natural-sounding, fluid, and expressive synthetic speech signal (h.).

It is disclosed a synthetic speech detection framework, based on breath-aware temporal discrepancy detection which is able to analyze the interplay between breathing patterns and phonetic production through five functional blocks, thereby significantly enhancing synthetic speech detection accuracy. These functional blocks include the Breathing-Speech Alignment Module (2), Breath-Speech Interaction Embeddings (3), Temporal Consistency Analyzer (4), Breath-Speech Coherence Module (5), and Deepfake Detection Classifier (6). By leveraging the physiological and phonetic cues that are difficult for synthetic speech generation models to replicate, the framework leverages physiological and phonetic cues, offering a robust solution to distinguish between organic and synthetic speech.

It is disclosed an Intonation-Aware Subsonic Harmonics (ISH) unit (2), adapted to be integrated into a Text-to-Speech (TTS) system (1). Said unit being comprised by an Intonation Learning Module (2.2), a Subsonic Harmonics Module (2.3), and a Contextual Feedback Module (2.3). More precisely, the Intonation Learning Module is able to learn the relationship between subsonic harmonic profiles and intonation patterns across various emotional and contextual scenarios. The Subsonic Harmonics Module generates and integrates inaudible subsonic frequencies with a synthesized speech waveform (g.), dynamically adjusting them based on the Intonation Learning Module's output and contextual feedback (c.) on contextual information derivable from the text inputted to the TTS system, given by the Contextual Feedback Module. This procedure influences prosodic features results in more natural-sounding, fluid, and expressive synthetic speech signal (h.)

It is disclosed a synthetic speech detection framework, based on breath-aware temporal discrepancy detection which is able to analyze the interplay between breathing patterns and phonetic production through five functional blocks, thereby significantly enhancing synthetic speech detection accuracy. These functional blocks include the Breathing-Speech Alignment Module (2), Breath-Speech Interaction Embeddings (3), Temporal Consistency Analyzer (4), Breath-Speech Coherence Module (5), and Deepfake Detection Classifier (6). By leveraging the physiological and phonetic cues that are difficult for synthetic speech generation models to replicate, the framework leverages physiological and phonetic cues, offering a robust solution to distinguish between organic and synthetic speech.

It is disclosed a method for generating an enhanced natural-sounding speech in a Text-to-Speech (TTS) system (1). Said method including a sequence of steps to be executed by an Intonation-Aware Subsonic Harmonics (ISH) unit (2, 2.1, 2.2, 2.3, 2.4), which is integrated with the TTS system (1), in order to generate and integrate inaudible subsonic frequencies (f.) with a synthesized speech waveform (g.), and to dynamically adjust them based on modulation parameters (e.) and contextual feedback (c.) derivable from the text inputted to the TTS system (1). This procedure influences prosodic features results in more natural-sounding, fluid, and expressive synthetic speech signal (h.)

It is disclosed a Text-to-Speech (TTS) system (1) with an Intonation-Aware Subsonic Harmonics (ISH) unit (2) integrated. Said unit (2) being comprised by an Intonation Learning Module (2.2), a Subsonic Harmonics Module (2.3), and a Contextual Feedback Module (2.3). More precisely, the Intonation Learning Module is able to learn the relationship between subsonic harmonic profiles and intonation patterns across various emotional and contextual scenarios. The Subsonic Harmonics Module generates and integrates inaudible subsonic frequencies with a synthesized speech waveform (g.), dynamically adjusting them based on the Intonation Learning Module's output and contextual feedback (c.) on contextual information derivable from the text inputted to the TTS system, given by the Contextual Feedback Module. This procedure influences prosodic features results in more natural-sounding, fluid, and expressive synthetic speech signal (h.)

The present application describes a system for generating three-dimensional content (e) from a multicamera two-dimensional video stream (a) of a sporting event.The system comprises a processor unit (2) comprising an object detection module (2.1), a tracking module (2.2), a transformation module (2.3) and an event data generator module (2.5), that are interoperatively coupled to each other. The system developed makes it possible to generate three-dimensional content (e) from two-dimensional video streams (a, b) more efficiently, taking into account the challenges that broadcasting a sporting event imposes.