Collected sources and patterns will appear here. Add from search or the patterns library.
PhonemeSequence -> MelSpectrogram
Predict mel-spectrogram frames from phoneme sequences using a transformer-based acoustic model.
Problem it solves
Direct text-to-speech mapping has too high variance; dividing synthesis into intermediate acoustic features simplifies training.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.