Vendor / paper demo
LJSpeech (Merlin) · Merlin baseline from the FastSpeech demo page, sample 1.
I will quote an extract from the reverend gentleman's own journal.
CSTR / Nagoya Institute of Technology · 2002–16 · HMM / DNN parametric
Statistical parametric TTS: predict vocoder features (often with HMMs, later DNNs), then filter. The buzzy, muffled colour is the vocoder, not a bad speaker. This clip is the Merlin baseline from the FastSpeech demo page.
The pre-neural baseline every 2017–2019 paper had to beat.
Vendor / paper demo
LJSpeech (Merlin) · Merlin baseline from the FastSpeech demo page, sample 1.
I will quote an extract from the reverend gentleman's own journal.