BiSinger: Bilingual Singing Voice Synthesis

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhou, Huali, Lin, Yueqian, Shi, Yao, Sun, Peng, Li, Ming
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916084840398848
author Zhou, Huali
Lin, Yueqian
Shi, Yao
Sun, Peng
Li, Ming
author_facet Zhou, Huali
Lin, Yueqian
Shi, Yao
Sun, Peng
Li, Ming
contents Although Singing Voice Synthesis (SVS) has made great strides with Text-to-Speech (TTS) techniques, multilingual singing voice modeling remains relatively unexplored. This paper presents BiSinger, a bilingual pop SVS system for English and Chinese Mandarin. Current systems require separate models per language and cannot accurately represent both Chinese and English, hindering code-switch SVS. To address this gap, we design a shared representation between Chinese and English singing voices, achieved by using the CMU dictionary with mapping rules. We fuse monolingual singing datasets with open-source singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data. Experiments affirm that our language-independent representation and incorporation of related datasets enable a single model with enhanced performance in English and code-switch SVS while maintaining Chinese song performance. Audio samples are available at https://bisinger-svs.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2309_14089
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle BiSinger: Bilingual Singing Voice Synthesis
Zhou, Huali
Lin, Yueqian
Shi, Yao
Sun, Peng
Li, Ming
Audio and Speech Processing
Machine Learning
Sound
Although Singing Voice Synthesis (SVS) has made great strides with Text-to-Speech (TTS) techniques, multilingual singing voice modeling remains relatively unexplored. This paper presents BiSinger, a bilingual pop SVS system for English and Chinese Mandarin. Current systems require separate models per language and cannot accurately represent both Chinese and English, hindering code-switch SVS. To address this gap, we design a shared representation between Chinese and English singing voices, achieved by using the CMU dictionary with mapping rules. We fuse monolingual singing datasets with open-source singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data. Experiments affirm that our language-independent representation and incorporation of related datasets enable a single model with enhanced performance in English and code-switch SVS while maintaining Chinese song performance. Audio samples are available at https://bisinger-svs.github.io.
title BiSinger: Bilingual Singing Voice Synthesis
topic Audio and Speech Processing
Machine Learning
Sound
url https://arxiv.org/abs/2309.14089