Statements (50)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:technology
speech synthesis system |
| gptkbp:basedOn |
deep learning
concatenative synthesis formant synthesis neural network synthesis |
| gptkbp:canBe |
individuals
businesses developers voice selection volume control pitch adjustment speech rate |
| gptkbp:canBeOnDevice |
yes
|
| gptkbp:cloudBased |
yes
|
| gptkbp:commercialUse |
yes
|
| gptkbp:component |
gptkb:screen_readers
voice response systems |
| gptkbp:developedBy |
1950s
|
| gptkbp:enables |
accessibility for visually impaired users
hands-free device operation |
| gptkbp:format |
gptkb:public_speaker
gptkb:text audio |
| https://www.w3.org/2000/01/rdf-schema#label |
Text-to-Speech Systems
|
| gptkbp:integratesWith |
embedded systems
web applications computers mobile devices |
| gptkbp:notableExample |
gptkb:Apple_VoiceOver
gptkb:Google_Text-to-Speech gptkb:Amazon_Polly gptkb:IBM_Watson_Text_to_Speech Microsoft Azure TTS |
| gptkbp:openSource |
yes
|
| gptkbp:relatedTo |
natural language processing
speech recognition voice cloning speech-to-text systems |
| gptkbp:supportedBy |
multiple languages
various voices |
| gptkbp:usedFor |
converting text into spoken voice output
|
| gptkbp:usedIn |
gptkb:assistive_technology
language learning telecommunications navigation systems virtual assistants audiobook production |
| gptkbp:bfsParent |
gptkb:large_language_model
|
| gptkbp:bfsLayer |
5
|