PoDAR disentangles audio signal power from semantic content in latents using power augmentation and consistency objectives, yielding 2x faster convergence and gains of 0.055 speaker similarity and 0.22 UTMOS when applied to Stable Audio VAE with F5-TTS.
Common voice: A massively-multilingual speech corpus
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
eess.AS 2roles
dataset 1polarities
use dataset 1representative citing papers
MLS is a new large-scale multilingual speech corpus derived from LibriVox with 44.5k hours of English and 6k hours across seven other languages, plus baseline ASR and LM models.
citing papers explorer
-
PoDAR: Power-Disentangled Audio Representation for Generative Modeling
PoDAR disentangles audio signal power from semantic content in latents using power augmentation and consistency objectives, yielding 2x faster convergence and gains of 0.055 speaker similarity and 0.22 UTMOS when applied to Stable Audio VAE with F5-TTS.
-
MLS: A Large-Scale Multilingual Dataset for Speech Research
MLS is a new large-scale multilingual speech corpus derived from LibriVox with 44.5k hours of English and 6k hours across seven other languages, plus baseline ASR and LM models.