Kevin Kilgour

representation learning (1) few-shot learning (1) transfer learning (1) feature extraction (1) embedding learning (1) speech processing (1) multimodal learning (1) multi-modal learning (1) keyword spotting (1) sound source separation (1) generative model (1) text embedding (1) generative model evaluation (1) reference-free evaluation (1) encoder-decoder architecture (1) low latency (1) speech embedding (1) speech translation (1) simultaneous translation (1) automatic translation (1)