This three-day intensive School will delve into the cutting-edge realm of speech and audio processing, with a particular focus on advancing human-machine interaction. Attendees will gain hands-on experience with state-of-the-art deep learning architectures, feature extraction techniques, and evaluation metrics. The curriculum will cover a wide range of topics, including end-to-end speech recognition, audio signal processing, and speech synthesis. Participants will have the opportunity to explore emerging trends such as multimodal learning and explainable AI. By combining theoretical knowledge with practical applications, this school aims to equip attendees with the skills and knowledge necessary to develop innovative speech and audio-based solutions.