Speech Recognition, Synthesis, and Streaming
Follow audio from waveform to transcript and back to speech, with runnable examples of features, CTC, endpointing, latency budgets, WER, and redaction.
-
-
Image and Video Generation
Control signals, temporal consistency, evaluation metrics and statistics, watermarks, signed manifests and layered safety controls for diffusion-based image and video generators.
-
Multimodal Models and Cross-Modal Alignment
A language model reads vectors, not pixels or waveforms. See how encoders, contrastive alignment, and connectors bridge the gap, and how to test whether the input is really used.