Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
text-to-speech model
|
| gptkbp:application |
speech synthesis
|
| gptkbp:author |
Y. Ren, Y. Hu, X. Tan, T. Qin, S. Zhao, Z. Zhao, T. Liu
|
| gptkbp:availableOn |
gptkb:GitHub
|
| gptkbp:basedOn |
gptkb:Tacotron_2
|
| gptkbp:canBe |
gptkb:WaveGlow
gptkb:HiFi-GAN |
| gptkbp:citation |
ICASSP 2021
FastPitch: Parallel Text-to-speech with Pitch Prediction |
| gptkbp:developedBy |
gptkb:NVIDIA
|
| gptkbp:firstPublished |
2021
|
| https://www.w3.org/2000/01/rdf-schema#label |
FastPitch
|
| gptkbp:input |
phoneme sequence
|
| gptkbp:language |
English
|
| gptkbp:notableFeature |
fast inference
fast training controllable pitch |
| gptkbp:openSource |
true
|
| gptkbp:output |
mel-spectrogram
|
| gptkbp:relatedTo |
FastSpeech
|
| gptkbp:uses |
non-autoregressive architecture
|
| gptkbp:bfsParent |
gptkb:NeMo_TTS
|
| gptkbp:bfsLayer |
7
|