Aren Jansen

multimodal learning (3) transformer architecture (1) representation learning (1) transfer learning (1) attention mechanism (1) multi-modal learning (1) sound source separation (1) diffusion model (1) autoregressive model (1) text embedding (1) latent diffusion (1) multimodal fusion (1) zero-shot generation (1) encoder-decoder architecture (1) triplet loss (1) late fusion (1) speech representation (1) audio generation (1) audio embedding (1) non-semantic speech (1)