Robert Gmyr

multimodal learning (2) self-supervised learning (2) federated learning (2) multi-task learning (1) attention mechanism (1) data augmentation (1) voice conversion (1) speech recognition (1) text generation (1) autoregressive generation (1) text summarization (1) gradient aggregation (1) automatic speech recognition (1) speaker embedding (1) speaker verification (1) synthetic data generation (1) acoustic model (1) hierarchical optimization (1) generative model (1) denoising autoencoder (1)