Sequence to sequence transformations for speech synthesis via recurrent neural networks

Sequence to sequence transformations for speech synthesis via recurrent neural networks

A system eliminates alignment processing and performs TTS functionality using a new neural architecture. The neural architecture includes an encoder and a decoder. The encoder receives an input and encodes it into vectors. The encoder applies a sequence of transformations to the input and generates...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hall, David Leo Wright, Klein, David, Gillick, Lawrence, Maas, Andrew, Wegmann, Steven, Roth, Daniel
Format: Patent
Sprache:eng
Schlagworte:
ACOUSTICS
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A system eliminates alignment processing and performs TTS functionality using a new neural architecture. The neural architecture includes an encoder and a decoder. The encoder receives an input and encodes it into vectors. The encoder applies a sequence of transformations to the input and generates a vector representing the entire sentence. The decoder takes the encoding and outputs an audio file, which can include compressed audio frames.