Speech synthesis method and device, electronic equipment and storage medium

• Main Authors: TU QINGHUA, CHEN JUNHONG
• Format: Patent
• Language: Chinese; English
• Published: 08.11.2022
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The invention discloses a speech synthesis method and device, electronic equipment and a storage medium. The method comprises the steps of determining a word segmentation tag, a position category and an original tone of each character in a to-be-processed text; querying a preset rhythm mapping rule table according to the position category, the word segmentation tag and the original tone, and mapping the original tone into a rhythm value according to a query result; training the acoustic model by taking each rhythm value as a front-end text feature, and obtaining a trained acoustic model; generating acoustic features corresponding to the to-be-processed text based on the trained acoustic model; converting the acoustic features into audio corresponding to the to-be-processed text based on a vocoder; wherein the word segmentation label represents the position of each character in the word segmentation and whether each character is a single word, and the position category represents the position of each character