HiFi-GAN

GPTKB entity

Statements (29)
Predicate Object
gptkbp:instanceOf gptkb:convolutional_neural_network
speech synthesis model
gptkbp:application speech synthesis
text-to-speech
gptkbp:architecture gptkb:convolutional_neural_network
gptkbp:author Jaehyeon Kim
Jaekyoung Bae
Jungil Kong
gptkbp:firstPublished 2020
https://www.w3.org/2000/01/rdf-schema#label HiFi-GAN
gptkbp:input mel-spectrogram
gptkbp:language gptkb:Python
gptkbp:license gptkb:MIT_License
gptkbp:notableFor low computational cost
fast inference speed
high-fidelity audio synthesis
gptkbp:openSource true
gptkbp:output audio waveform
gptkbp:publishedIn gptkb:NeurIPS_2020
gptkbp:relatedTo gptkb:WaveGlow
gptkb:Parallel_WaveGAN
gptkb:MelGAN
gptkbp:repository https://github.com/jik876/hifi-gan
gptkbp:usedIn speech synthesis research
voice cloning
TTS systems
gptkbp:bfsParent gptkb:NeMo_TTS
gptkb:WaveRNN
gptkbp:bfsLayer 7