Beijing Opera Synthesis Based on Straight Algorithm and Deep Learning

Speech synthesis is an important research content in the field of human-computer interaction and has a wide range of applications. As one of its branches, singing synthesis plays an important role. Beijing Opera is a famous traditional Chinese opera, and it is called Chinese quintessence. The singin...

Full description

Saved in:
Bibliographic Details
Main Authors: XueTing Wang, Cong Jin, Wei Zhao
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Advances in Multimedia
Online Access:http://dx.doi.org/10.1155/2018/5158164
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849413677863665664
author XueTing Wang
Cong Jin
Wei Zhao
author_facet XueTing Wang
Cong Jin
Wei Zhao
author_sort XueTing Wang
collection DOAJ
description Speech synthesis is an important research content in the field of human-computer interaction and has a wide range of applications. As one of its branches, singing synthesis plays an important role. Beijing Opera is a famous traditional Chinese opera, and it is called Chinese quintessence. The singing of Beijing Opera carries some features of speech but it has its own unique pronunciation rules and rhythms which differ from ordinary speech and singing. In this paper, we propose three models for the synthesis of Beijing Opera. Firstly, the speech signals of the source speaker and the target speaker are extracted by using the straight algorithm. And then through the training of GMM, we complete the voice control model to input the voice to be converted and output the voice after the voice conversion. Finally, by modeling the fundamental frequency, duration, and frequency separately, a melodic control model is constructed using GAN to realize the synthesis of the Beijing Opera fragment. We connect the fragments and superimpose the background music to achieve the synthesis of Beijing Opera. The experimental results show that the synthesized Beijing Opera has some audibility and can basically complete the composition of Beijing Opera. We also extend our models to human-AI cooperative music generation: given a target voice of human, we can generate a Beijing Opera which is sung by a new target voice.
format Article
id doaj-art-6f4c7cbba0ea45ad94d58811e42c767f
institution Kabale University
issn 1687-5680
1687-5699
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Advances in Multimedia
spelling doaj-art-6f4c7cbba0ea45ad94d58811e42c767f2025-08-20T03:34:04ZengWileyAdvances in Multimedia1687-56801687-56992018-01-01201810.1155/2018/51581645158164Beijing Opera Synthesis Based on Straight Algorithm and Deep LearningXueTing Wang0Cong Jin1Wei Zhao2College of Science and Technology, Communication University of China, Beijing, ChinaKey Laboratory of Media Audio & Video, Communication University of China, Beijing, ChinaCollege of Science and Technology, Communication University of China, Beijing, ChinaSpeech synthesis is an important research content in the field of human-computer interaction and has a wide range of applications. As one of its branches, singing synthesis plays an important role. Beijing Opera is a famous traditional Chinese opera, and it is called Chinese quintessence. The singing of Beijing Opera carries some features of speech but it has its own unique pronunciation rules and rhythms which differ from ordinary speech and singing. In this paper, we propose three models for the synthesis of Beijing Opera. Firstly, the speech signals of the source speaker and the target speaker are extracted by using the straight algorithm. And then through the training of GMM, we complete the voice control model to input the voice to be converted and output the voice after the voice conversion. Finally, by modeling the fundamental frequency, duration, and frequency separately, a melodic control model is constructed using GAN to realize the synthesis of the Beijing Opera fragment. We connect the fragments and superimpose the background music to achieve the synthesis of Beijing Opera. The experimental results show that the synthesized Beijing Opera has some audibility and can basically complete the composition of Beijing Opera. We also extend our models to human-AI cooperative music generation: given a target voice of human, we can generate a Beijing Opera which is sung by a new target voice.http://dx.doi.org/10.1155/2018/5158164
spellingShingle XueTing Wang
Cong Jin
Wei Zhao
Beijing Opera Synthesis Based on Straight Algorithm and Deep Learning
Advances in Multimedia
title Beijing Opera Synthesis Based on Straight Algorithm and Deep Learning
title_full Beijing Opera Synthesis Based on Straight Algorithm and Deep Learning
title_fullStr Beijing Opera Synthesis Based on Straight Algorithm and Deep Learning
title_full_unstemmed Beijing Opera Synthesis Based on Straight Algorithm and Deep Learning
title_short Beijing Opera Synthesis Based on Straight Algorithm and Deep Learning
title_sort beijing opera synthesis based on straight algorithm and deep learning
url http://dx.doi.org/10.1155/2018/5158164
work_keys_str_mv AT xuetingwang beijingoperasynthesisbasedonstraightalgorithmanddeeplearning
AT congjin beijingoperasynthesisbasedonstraightalgorithmanddeeplearning
AT weizhao beijingoperasynthesisbasedonstraightalgorithmanddeeplearning