HMM-based song synthesizing method and device

Abstract

The invention discloses an HMM-based song synthesizing method and device. According to the method and device, a text-to-speech conversion technology is applied; an HTS (hidden Markov model-based speech synthesis system) is adopted; the STRAIGHT algorithm is used; an HMM-based speaker-related acoustic model for song synthesis and the melody control model of songs are built; speaker adaptive training is performed; and therefore, the HMM-based lyrics-to-song real-time conversion personalized speech synthesis device can be realized. With the device of the invention adopted, the research content of speech synthesis is enriched, synthesized speech is more expressive and can better express emotions; opportunities for learning technical operation such as song production and music processing can be provided for music lovers; and the available social resources of people can be increased. The method and device have a certain practical value and important significance.

Description

technical field [0001] The present invention relates to the fields of human-computer interaction technology, text-to-speech conversion technology, speech synthesis technology, etc., and specifically relates to an HMM-based song synthesis method and device. Background technique [0002] With the continuous innovation and improvement of information technology, many music multimedia applications in terms of human-computer interaction have gradually entered our daily life, such as computer song ordering, composing, modifying singing voices, and listening to and recognizing songs on mobile phones. How to make the computer more humanized and able to "sing" like human beings, that is to say, the computer can automatically generate beautiful and pleasant singing voices has become a new demand if the numbered notation and lyrics are known. With the rapid development of multimedia technology in the field of entertainment, it also provides a broader application space for this technolog...

AI Technical Summary

Problems solved by technology

[0007] In view of the above-mentioned defects of the prior art, the present invention aims to solve the problems in the background art that there are few studies on the synthesis of Chinese singing voices, the sound quality of the synthesis is not high, and the operation is time-consuming and labor-intensive, etc., and provides a music processing solution for those who need music processing. Method and device for realizing personalized song synthesis based on HMM

Images