Topics
The four subject headings used across the archive, with the notes filed under each of them.
Dialogue
- What makes synthetic dialogue sound unrehearsed
Two synthetic voices can be individually convincing and still fail the moment they have to talk to each other. The difference is almost never the timbre.
Prosody
- Prosody is the harder half of speech
Getting the phonemes right is a solved-enough problem. Deciding which syllable carries the weight of a sentence is where synthesis still shows its seams.
Data & Practice
- How to read a speech model card
Model documentation is written to be skimmed and is most useful when it is not. A short guide to the sections that actually constrain what you can do.
- Preparing audio datasets for speech models
Most of the quality difference between two speech systems was decided during data preparation, long before either was trained.
Evaluation & Ethics
- Consent and provenance in voice cloning
A few seconds of reference audio is now enough to reproduce a speaking voice. The interesting questions are all about record-keeping.
- Evaluating speech systems without a leaderboard
Speech quality is a perceptual property, and perceptual properties resist the single number that comparison tables want.