Voice synthesis method and device and computer readable storage medium

Abstract

The invention provides a voice synthesis method and device and a computer readable storage medium, and relates to the field of artificial intelligence, in particular to a voice synthesis technology inthe field of voice recognition. The method comprises the following steps: acquiring to-be-processed data of a first user, processing the to-be-processed data through the target model; and obtaining first data, wherein the target model is obtained by training a first sub-model of the basic acoustic model based on the personalized training data of the first user, sending the first data to the dataprocessing device, receiving a processing result, and obtaining the processing result by processing the first data by the data processing device based on a second sub-model of the basic acoustic model. Through the data processing method by combining the terminal and the data processing equipment, the requirements on the storage model and the operational capability of the data processing equipmentare reduced, so that the deployment and implementation cost of personalized speech synthesis is greatly reduced.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to a speech synthesis technology in the field of speech recognition, and more specifically, to a speech synthesis method, device and computer-readable storage medium. Background technique [0002] In recent years, speech synthesis technology has made great progress, and machine voice broadcasts have been widely used in smart mobile terminals, smart homes, car audio and other equipment. People's requirements for speech synthesis are no longer just "able to hear clearly", but have been transformed into "expressive power" and "full of personalization". Therefore, the personalized function of speech synthesis has gradually become the "black technology" declared by many products, and has become a highlight of product competitiveness. Personalized speech synthesis (text to speech, TTS) system, that is, a speech synthesis system that integrates user-customized features, wh...

AI Technical Summary

Problems solved by technology

[0003] However, due to the characteristics of personalized TTS itself, for example, personalized TTS needs to establish its acoustic model for each user. If a product has millions of users, it is necessary to provide millions of different acoustic models corresponding to the million users. Model, the storage of a large number of models requires a large amount of storage space. When using processing equipment such as servers for speech synthesis, there are high requirements for its configuration and computing power, which greatly increases the deployment cost of acoustic models. At the same time It also increases the difficulty of practical application

Images