FAD: 2.02FD: 26.18CLAP_MS: 0.37FD_openl3: 158.04
Papers with Code · CC BY-SA 4.0
Audio Generation
Audio generation (synthesis) is the task of generating raw audio such as speech.
<span style="color:grey; opacity: 0.6">( Image credit: MelNet )</span>
논문
FAD: 1.63FD: 21.99
FAD: 2.03FD: 10.10CLAP_MS: 0.43FD_openl3: 61.79
FD_openl3: 75.1CLAP_LAION: 0.488KL_passt: 1.15IS: 12.2
FAD: 1.80FD: 22.90
Log-Spectral Distance: 3.4
FAD: 0.77FD: 8.30CLAP_LAION: 0.71IS: 12.70
FAD: 3.13FD_openl3: 185.53KL_passt: 1.42
FAD: 1.96FD: 23.31
FAD: 2.18FD: 20.44
FAD: 7.75FD: 47.68
FD_openl3: 103.66CLAP_LAION: 0.41KL_passt: 2.89
Bits per byte: 40
Bits per byte: 1.97
FAD: 2.54FD: 17.19CLAP_LAION: 0.527IS: 11.04
FD_openl3: 110.62KL_passt: 2.70
FAD: 1.80FD: 11.75
FAD: 2.66FD: 18.32
SNR: 35.26
FAD: 1.37
Log-Spectral Distance: 1.5
CLAP_MS: 0.34FD_openl3: 78.24CLAP_LAION: 0.35KL_passt: 2.14
Human listening average results: 3.5
FAD: 1.21FD: 16.51CLAP_MS: 0.668
Log-Spectral Distance: 2
FAD: 1.59FD: 24.52