Andros Tjandra

automatic speech recognition (6) speech recognition (4) unsupervised learning (3) text-to-speech synthesis (3) speech synthesis (3) attention mechanism (2) self-supervised learning (2) speaker recognition (2) semi-supervised learning (2) deep learning (1) language identification (1) knowledge distillation (1) low-rank adaptation (1) multimodal learning (1) disentangled representation (1) latent representation (1) vector quantization (1) sequence-to-sequence learning (1) machine translation (1) image generation (1)