Deep learning speech synthesis uses Deep Neural Networks (DNN) to produceartificial speech from text (text-to-speech) or spectrum (vocoder).The deep neural networks are trained using a large amount of recorded speech and, in the case ofa text-to-speech system, the associated labels and/or input text. Some DNN-based speech synthesizers are approaching the naturalness of the human voice.
Property | Value |
---|---|
dbo:abstract |
|
dbo:soundRecording | |
dbo:thumbnail | |
dbo:wikiPageExternalLink | |
dbo:wikiPageID |
|
dbo:wikiPageLength |
|
dbo:wikiPageRevisionID |
|
dbo:wikiPageWikiLink |
|
dbp:description |
|
dbp:filename |
|
dbp:title |
|
dbp:wikiPageUsesTemplate | |
dcterms:subject | |
rdf:type | |
rdfs:comment |
|
rdfs:label |
|
owl:sameAs | |
prov:wasDerivedFrom | |
foaf:depiction | |
foaf:isPrimaryTopicOf | |
is dbo:wikiPageRedirects of | |
is dbo:wikiPageWikiLink of | |
is foaf:primaryTopic of |