Corpus expansion and speech synthesis system construction method and device based on artificial intelligence

Abstract

The invention discloses a corpus expansion and speech synthesis system construction method and device based on artificial intelligence. The method comprises the following steps of according to a corpus in a small sample sound library, training and acquiring a WaveNet model; using the WaveNet model to generate a speech waveform corresponding to a given text; supplementing the corpus corresponding to the generated speech waveform to the small sample sound library and acquiring a large sample sound library; and using the corpus in the large sample sound library to construct a statistical parameter speech synthesis system. In the scheme, a speech synthesis effect can be increased, and manpower, material resources, time cost and the like are saved.

Description

【Technical field】 [0001] The invention relates to computer application technology, in particular to an artificial intelligence-based corpus expansion and speech synthesis system construction method and device. 【Background technique】 [0002] Artificial Intelligence (Artificial Intelligence), the English abbreviation is AI. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. [0003] In the speech synthesis technology, it is necessary to record the corpus for the speaker. The recording process needs to be carried out...

AI Technical Summary

Problems solved by technology

[0007] However, the above two methods will have certain problems in practical applications. For example, although the former method has a certain effect, after all, the acoustic characteristics such as frequency spectrum and fundamental frequency of the basic speaker and the target speaker have relatively large differences. In addition, it is difficult for some speakers with heavy accents to find a relatively matching speaker in the existing large-sample sound library, so the actual use effect is not ideal, and the speech synthesis effect is poor; although the method of hiring a voice substitute It can make up for the lack of corpus, but the cost of hiring voice replacements is often much higher than that of ordinary speakers, and it is also difficult to find voice replacements for stars with high timbre recognition. The process of finding voice replacements is quite a process. time consuming process

Images