Rhythm-level prediction model generation method and apparatus, and rhythm-level prediction method and apparatus

Abstract

The invention provides a rhythm-level prediction model generation method and apparatus, and a rhythm-level prediction method and apparatus. The rhythm-level prediction model generation method comprises: generating an initial rhythm-level prediction model according to a precisely marking data set; collecting speech and corresponding text data, detecting feature information in the speech, and adding the feature information to a corresponding position of the text data; according to the initial rhythm-level prediction model, carrying out rhythm-level prediction on the text data with added feature information to obtain an initial rhythm-level prediction result; and according to the precisely marking data set and the initial rhythm-level prediction result, carrying out training to generate an updated rhythm-level prediction model, and applying the updated rhythm-level prediction model to rhythm-level prediction for speech synthesis. With the method, accuracy of the generated rhythm-level prediction model is improved and thus accuracy of the rhythm-level prediction is enhanced; and the voice synthesis effect is improved.

Description

technical field [0001] The invention relates to the technical field of speech processing, in particular to a method and device for generating a prosodic level prediction model and prosodic level prediction. Background technique [0002] Speech synthesis, also known as text-to-speech (TTS) technology, can convert any text information into a standard and smooth voice in real time, which is equivalent to installing an artificial mouth on the machine. A key step in speech synthesis is prosodic prediction, which can be subdivided into prosody level prediction, duration prediction, and pitch prediction. In the prosodic level prediction, the prosodic level prediction model generated in the training stage is used to predict the prosodic level of the input text after text processing, and the prosodic level prediction result is obtained, which will affect the effect of speech synthesis. [0003] In the prior art, the prosodic level prediction model is generated after training the tra...

AI Technical Summary

Problems solved by technology

However, since the fine-labeled data set requires professional annotation, the labeling cycle is long, and the investment required is large, the scale of the fine-labeled data set is often small, resulting in poor accuracy of the trained prosodic level prediction model, which affects the prosodic level. The accuracy of prediction affects the effect of speech synthesis

Images