Speech synthesis method and device, equipment and storage medium

The invention provides a speech synthesis method, device and equipment and a storage medium, and the method comprises the steps: obtaining a phoneme sequence corresponding to a target text, processing the phoneme sequence into a vector containing phoneme information and speaker information of a targ...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SONG FEIBAO, SONG RUI, CHEN LINGHUI, HU YU, JIANG YUAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention provides a speech synthesis method, device and equipment and a storage medium, and the method comprises the steps: obtaining a phoneme sequence corresponding to a target text, processing the phoneme sequence into a vector containing phoneme information and speaker information of a target speaker through a vector prediction model of a speech synthesis model, and taking the vector as a target vector, and processing the target vector through a speech synthesis module of the speech synthesis model to generate synthesized speech. According to the invention, the audio conversion model is obtained by training the single-language speech of the target speaker and the multi-language speech of the non-target speaker, so that a large amount of multi-language speech with the tone of the target speaker is obtained based on the audio conversion model and a large amount of multi-language speech of the non-target speaker. Therefore, a large number of multilingual voices with the timbre of the target speaker can