2026-04-19T21:31:42Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00234734 2025-01-19T09:42:35Z 1164:5159:11541:11627

Cross-lingual Singing Voice Conversion Leveraging Transformer-based ASR Encoder Cross-lingual Singing Voice Conversion Leveraging Transformer-based ASR Encoder Xinyuan, Zhao Daisuke, Saito Nobuaki, Minematsu Xinyuan, Zhao Daisuke, Saito Nobuaki, Minematsu ポスターセッション2 In this paper, we focus on singing voice conversion task, including monolingual and cross-lingual singing voice conversion. We proposed a method to modify MaskCycleGAN, a model designed for nonparallel speech conversion task, and applied the proposed model for the singing voice conversion task. The new model concatenates MaskCycleGAN with Whisper, a transformer-based ASR encoder that recognizes the content of the song. The experimental results demonstrated significant performance improvements over the original MaskCycleGAN in both monolingual and cross-lingual scenarios for the singing voice conversion task. technical report 情報処理学会 2024-06-07 application/pdf 研究報告音声言語情報処理（SLP） 47 2024-SLP-152 1 4 2188-8663 AN10442647 https://ipsj.ixsq.nii.ac.jp/record/234734/files/IPSJ-SLP24152047.pdf eng