QS-TTS: A Semi-Supervised Text-to-Speech Framework

doi:doi:10.57702/w1p4v02n

QS-TTS: A Semi-Supervised Text-to-Speech Framework

Followers: 0

Organization

No Organization

There is no description for this organization

License

No License Provided

Export

DCAT(rdf/xml) DCAT(xml) DCAT(N3) DCAT(ttl) DCAT(jsonld) DataCite CSL DublinCore BibTex

QS-TTS: A Semi-Supervised Text-to-Speech Framework

QS-TTS is a semi-supervised TTS framework based on VQ-S3RL to effectively utilize more unlabeled speech audio to improve TTS quality while reducing its requirements for supervised data.

BibTex:

Before browse our site, please accept our cookies policy