Model
FastPitch
A TTS model based on the FastSpeech architecture that enhances pitch controllability by feeding pitch embeddings back to the decoder. It belongs to the explicit variance modeling paradigm.
Timeline (last 90 days)
Oct 19
SteerTTS adopts FastPitch-style explicit variance modeling: phonemes first pass through an encoder, three predictors for duration, pitch and energy each output control quantities, which are then aligned via a length regulator and finally decoded into 100-band log-mel spectra, handed to a frozen Vocos vocoder for waveform synthesis.
Unverified50%