Speech synthesis method and device, electronic equipment and storage medium

• Main Authors: ZHOU HONGBIN, HE TIANWEI, LU HENG, REN KAIMENG, HE WENDI, HE LAIPENG, TAN PENGFEI, YOU YUREN
• Format: Patent
• Language: Chinese; English
• Published: 05.09.2023
• Subjects: ACOUSTICS; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

The invention provides a speech synthesis method and device, electronic equipment and a storage medium, and the method comprises the steps: firstly obtaining personalized demand information and a to-be-converted text, and then carrying out the matching of the personalized demand information with a tone description list, a style description list and an emotion description list which are stored in advance, obtaining a timbre weight distribution vector, a style weight distribution vector and an emotion weight distribution vector; and finally, generating a synthetic audio by using the text to be converted, the tone weight distribution vector, the style weight distribution vector, the emotion weight distribution vector and the trained multi-dimensional speech synthesis model. Compared with the prior art, the method and the device have the advantages that the trained multi-dimensional speech synthesis model can be utilized to obtain the synthesized audio meeting the personalized demand information, a personalized T