Robin Algayres

speech synthesis (2) zero-shot learning (2) speech embedding (2) self-supervised learning (2) unsupervised learning (2) discrete representation (1) contrastive loss (1) siamese network (1) mean average precision (1) speech representation (1) speech segmentation (1) speech generation (1) spoken language model (1) word boundary detection (1) audio representation (1) self-supervised audio representation (1) zero-resource learning (1) rare word (1) abx discrimination (1) word distribution (1)