US 2019/0096386 A1 · METHOD AND APPARATUS FOR GENERATING SPEECH SYNTHESIS MODEL

Abstract

The present disclosure discloses a method and apparatus for generating a speech synthesis model. A specific embodiment of the method comprises: acquiring a text characteristic of a text and an acoustic characteristic of a speech corresponding to the text used for training a neural network corresponding to a speech synthesis model, fundamental frequency data in the acoustic characteristic of the speech corresponding to the text used for the training being extracted through a fundamental frequency data extraction model, and the fundamental frequency data extraction model being generated based on pre-training a neural network corresponding to the fundamental frequency data extraction model using the speech including each frame of speech having corresponding fundamental frequency data; and training the neural network corresponding to the speech synthesis model using the text characteristic of the text and the acoustic characteristic of the speech corresponding to the text.

Claims9

Dependent claims

A method for generating a speech synthesis model, comprising:

acquiring a text characteristic of a text and an acoustic characteristic of a speech corresponding to the text used for training a neural network corresponding to a speech synthesis model, fundamental frequency data in the acoustic characteristic of the speech corresponding to the text used for the training being extracted through a fundamental frequency data extraction model, and the fundamental frequency data extraction model being generated based on pre-training a neural network corresponding to the fundamental frequency data extraction model using the speech comprising each frame of speech having corresponding fundamental frequency data;
and
training the neural network corresponding to the speech synthesis model using the text characteristic of the text and the acoustic characteristic of the speech corresponding to the text.

An apparatus for generating a speech synthesis model, comprising:

at least one processor;
and
a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
acquiring a text feature of a text and an acoustic feature of speech corresponding to the text used for training a neural network corresponding to a speech synthesis model, fundamental frequency data in the acoustic feature of the speech corresponding to the text used for the training being extracted through a fundamental frequency data extraction model, and the fundamental frequency data extraction model being generated based on a neural network corresponding to the fundamental frequency data extraction model pre-trained using the speech comprising each frame of speech having corresponding fundamental frequency data;
and
training the neural network corresponding to the speech synthesis model using the text feature of the text and the acoustic feature of the speech corresponding to the text.

3 more elements

Dependencies are inferred from the claim text.

Method and apparatus for generating speech synthesis model

Life of this patent

Method and apparatus for generating speech synthesis model

Life of this patent

Abstract

Claims9