Mark Hamilton

contrastive learning (1) semantic segmentation (1) self-supervised learning (1) speech synthesis (1) speech recognition (1) audio-visual learning (1) cross-modal retrieval (1) sound localization (1) multimodal alignment (1) dual encoder (1) neural text-to-speech (1) audio-visual alignment (1) audiobook generation (1) voice customization (1) emotional intonation (1) multi-modal representation (1) multi-head aggregation (1)