Voice synthesis method and device, computer readable medium and electronic equipment

Abstract

The invention relates to a voice synthesis method and device, a computer readable medium and electronic equipment. The method comprises the steps that voice feature information of a multilingual textand language feature vectors of all languages in the multilingual text are acquired, and the voice feature information comprises phonemes, tones, segmented words and rhythm boundaries; and voice synthesis is performed according to the voice feature information and the language feature vector to obtain first audio information corresponding to the multilingual text. Therefore, the accuracy and understandability of the first audio data are improved, and a user can quickly understand the text content corresponding to the first audio data. In addition, pause can be carried out at the natural rhythmboundary during speech synthesis, so that the naturalness and fluency of the first audio information can be improved. Besides, the voice synthesis method can realize smooth conversion of different languages, supports voice synthesis of texts of various languages, and does not limit specific languages, namely, has wide applicability.

Description

technical field [0001] The present disclosure relates to the technical field of speech synthesis, and in particular, to a speech synthesis method, device, computer readable medium and electronic equipment. Background technique [0002] Nowadays, readers use speech synthesis (also known as text to speech (Text to Speech, TTS), which can convert text information into speech and read it in real time, which is equivalent to installing an artificial mouth on the machine) to read the text. There are more and more functions. At the present stage, when the text reading system reads the text aloud, each word usually takes the same reading time, and pauses for a little longer at the punctuation marks in the text. In this way, the text reading system can only read the text content sequentially, and cannot pause according to the text content. In this way, it is difficult for the user to understand the corresponding text content based on the voice read aloud. Especially when the text ...

AI Technical Summary

Problems solved by technology

In this way, the text reading system can only read the text content in sequence, and cannot pause according to the text content

In this way, it is difficult for the user to understand the corresponding text content based on the spoken voice

Especially when the text is multilingual, due to the need for cross-lingual mixed reading, there is often a problem that the language conversion is not smooth enough, which undoubtedly increases the difficulty for users to understand the text content based on the spoken voice

Images