English speech synthesis method and device

Abstract

The invention relates to an English speech synthesis method and device. The method comprises the steps of obtaining an English pronunciation library with pronunciation standards; constructing a presetEnglish synthesis model according to the English sound library of the pronunciation standard; obtaining a target English sound library recorded by the non-professionals; adjusting the preset Englishsynthesis model according to the target English sound library to obtain a target English synthesis model; and synthesizing a to-be-synthesized English text into English speech by using the target English synthesis model. According to the technical scheme of the invention, the target English synthesis model with higher synthesis naturalness can be obtained, so that the English speech with higher naturalness (namely normal speech speed, normal intonation and consistent tone) can be conveniently obtained later, English speech synthesis can be accurately carried out even in a Chinese and English mixed scene, and the consistency of Chinese and English synthesis tones is ensured.

Description

technical field [0001] The invention relates to the technical field of speech synthesis, in particular to an English speech synthesis method and device. Background technique [0002] At present, when building an English synthesis model, it is generally necessary to invite professional English pronunciation personnel to record the sound library, so as to use the pronunciation standard sound library to construct the English synthesis model, but the cost of professional English pronunciation personnel to record the sound library is very high, and , the English synthesis model constructed from this is relatively rigid and cannot be accurately synthesized. For example, in some scenarios that require mixed synthesis of Chinese and English, it is difficult to guarantee the synthesis of Chinese and English by using the English synthesis model constructed based on the sound library based on pronunciation standards. The tone is consistent. Contents of the invention [0003] The emb...

AI Technical Summary

Problems solved by technology

[0002] At present, when building an English synthesis model, it is generally necessary to invite professional English pronunciation personnel to record the sound library, so as to use the pronunciation standard sound library to build an English synthesis model, but the cost of professional English pronunciation personnel to record the sound library is very high, and , the English synthesis model constructed from this is relatively rigid and cannot be accurately synthesized. For example, in some scenarios that require mixed synthesis of Chinese and English, it is difficult to guarantee the synthesis of Chinese and English by using the English synthesis model constructed based on the sound library based on pronunciation standards. consistency of tone

Images