ADOBE INC. (20250095631). POSITION-BASED TEXT-TO-SPEECH MODEL
POSITION-BASED TEXT-TO-SPEECH MODEL
Organization Name
Inventor(s)
Puneet Mathur of Sunnyvale CA US
Franck Dernoncourt of Spokane WA US
Quan Hung Tran of San Jose CA US
Jiuxiang Gu of Baltimore MD US
Ani Nenkova of Philadelphia PA US
Vlad Ion Morariu of Potomac MD US
Rajiv Bhawanji Jain of Falls Church VA US
Dinesh Manocha of Bethesda MD US
POSITION-BASED TEXT-TO-SPEECH MODEL
This abstract first appeared for US patent application 20250095631 titled 'POSITION-BASED TEXT-TO-SPEECH MODEL
Original Abstract Submitted
position-based text-to-speech model and training techniques are described. a digital document, for instance, is received by an audio synthesis service. a text-to-speech model is utilized by the audio synthesis service to generate digital audio from text included in the digital document. the text-to-speech model, for instance, is configured to generate a text encoding and a document positional encoding from an initial text sequence of the digital document. the document positional encoding is based on a location of the text encoding within the digital document. digital audio is then generated by the text-to-speech model that includes a spectrogram having a reordered text sequence, which is different from the initial text sequence, by decoding the text encoding and the document positional encoding.
- ADOBE INC.
- Puneet Mathur of Sunnyvale CA US
- Franck Dernoncourt of Spokane WA US
- Quan Hung Tran of San Jose CA US
- Jiuxiang Gu of Baltimore MD US
- Ani Nenkova of Philadelphia PA US
- Vlad Ion Morariu of Potomac MD US
- Rajiv Bhawanji Jain of Falls Church VA US
- Dinesh Manocha of Bethesda MD US
- G10L13/08
- G10L13/04
- G10L13/06
- G10L25/18
- CPC G10L13/08
(Ad) Transform your business with AI in minutes, not months
Trusted by 1,000+ companies worldwide
