Analyse-resynthèse de la parole Modélisation des signaux de parole Auto-encodeurs variationnels dynamiques Speech emotion recognition Deep generative models Image-retrieval Time-domain analysis Transfer Learning Facial action coding system Disentangled representation learning Speech generation Synthetic data Action Units Variational autoencoder Magnetic heads Representation learning Multi-speaker conversational speech Data mining Deep Clus-tering Dynamical variational autoencoders Time series analysis Noise measurement Decentralized Control and Large-Scale Systems Speech analysis-resynthesis Unsupervised domain adaptation Generative Adversarial Network Databases Multimodal and dynamical data Machine learning Feature extraction Inference algorithms Deep generative modeling Audiovisual speech processing Reverse correlation Recording Self-supervised learning ITU-T P835 listening test Metric Learning Speech spectrograms GAN Machine learning algorithms Masked autoencoder Training Cyber security in networked control systems Interactive genetic algorithm Source-filter model Vector-quantized variational autoencoder Speech signals modeling CHiME challenge Multi-stream Learning Spectrogrammes de parole Data augmentation Distributed constrained control and MPC Features fusion First-person hand activity recognition Speech enhancement