RAVE

model·neural audio autoencoder·active·also: Realtime Audio Variational autoEncoder

Realtime Audio Variational autoEncoder for fast neural waveform synthesis and timbre transfer.

Verified facts

Official sitehttps://github.com/acids-ircam/RAVE
GeographyParis, France
arxiv2111.05011
dedupe risklow
discovery routeFrench and English official-source discovery
proposed subtypeneural_audio_autoencoder
evidence strengthstrong
recommended prompt05-models-and-apis
proposed entity typeModelAPI
classification rationaleThe cited evidence presents RAVE as a neural_audio_autoencoder materially relevant to AI and music.

Current

developed bySTMS
describes (by)RAVE: A variational autoencoder for fast and high-quality neural audio synthesis

Sources & changes

canonical_nameofficial source ↗
short_descriptionofficial source ↗
primary_geographyofficial source ↗
external_ids.arxivofficial source ↗
attributes.proposed_entity_typeofficial source ↗
attributes.proposed_subtypeofficial source ↗
attributes.classification_rationaleofficial source ↗
attributes.discovery_routeofficial source ↗
attributes.evidence_strengthofficial source ↗
attributes.recommended_promptofficial source ↗
attributes.dedupe_riskofficial source ↗

Is this yours? Claim this record →·See something wrong? Report a correction →