Class

Status: see individual classes below

Slides

• 2026-03-10 Neural speech processing (vocoders; audio codecs; representation learning)
  • Download the slides for the class on 2026-03-10 (post-class version)
• 2026-03-17 Large Speech Language Models
  • Download the slides for the class on 2026-03-17 (pre-class version)
• 2026-03-24 Beyond Text-to-Speech (cloning, conversion, anonymisation,…)
  • Status: slides not ready

Demo pages

• Example audio codec: SoundStream
• Example Large Speech Language Models:
  • VALL-E
  • Parler
• Shannon Text Generator
  • This is just a character N-gram trained on a small amount of text, not an LLM!
  • Try training it on natural language from different domains, or even with Python code.
• Example speech editing model: VoiceCraft
• Example Voice Conversion models:
  • DualVC 3 (ASR+TTS-style architecture, but using an SSL model instead of explicit ASR, and configured to be causal to enable real-time use)
  • StreamVC (audio codec-based)