Variational Embedding Capacity in Expressive End-to-End Speech Synthesis

A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method als...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Skerry-Ryan, Russell John Wyatt, Kao, David Teh-Hwa, Bagby, Thomas Edward, Shannon, Sean Matthew, Battenberg, Eric Dean, Mariooryad, Soroosh, Stanton, Daisy
Format: Patent
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A method for estimating an embedding capacity includes receiving, at a deterministic reference encoder, a reference audio signal, and determining a reference embedding corresponding to the reference audio signal, the reference embedding having a corresponding embedding dimensionality. The method also includes measuring a first reconstruction loss as a function of the corresponding embedding dimensionality of the reference embedding and obtaining a variational embedding from a variational posterior. The variational embedding has a corresponding embedding dimensionality and a specified capacity. The method also includes measuring a second reconstruction loss as a function of the corresponding embedding dimensionality of the variational embedding and estimating a capacity of the reference embedding by comparing the first measured reconstruction loss for the reference embedding relative to the second measured reconstruction loss for the variational embedding having the specified capacity.