Анализ методов и моделей систем автоматической обработки синтеза речи

2022

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.54309/ijict.2020.2.2.019
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The article considers the current state of models and methods of speech synthesis. Their ad-vantages and disadvantages are presented, as well as metrics for the quality of speech synthesis. The method of speech synthesis by rules is based on a programmed knowledge of acoustic and linguistic limitations and does not directly use elements of human speech. В статьерассматривается современное состояние моделей и методов синтеза речи. Представлены их достоинства и недостатки, а также метрики качества синтеза речи. Метод синтеза речи по правилам базируется на запрограммированном знании акустических и лингвистических ограничений и не использует непосредственно элементы человеческой ре-чи.