Rafael Delgado

DTec is a Spanish SME with strong R&D on speech and audio technologies. Our solutions in the market include: Voice Biometrics, Deepfake AI Voice Cloning Detection, Audio Watermarking, Robust Speech Recognition and Advanced AI Noise Filtering. These technologies have a wide range of applications including: Forensic acoustics for police applications., Deepfake AI Voice Cloning detection against impersonation in fraud and fake news., Speaker authentication resistant to deepfake spoofing attacks., Source tracking against leaks of confidential recordings plus audio integrity verification., Audio filtering and speech isolation in noisy environments, for improved understanding or performance optimization of recognition engines. In addition, our exclusive know-how in audio signal processing and analysis gives us the capacity to develop related new technologies: sentiment analysis, stress level assessment from the voice signal, gender and age estimation or automatic identification of vessels from hidrophones.