MR-SVS: Singing Voice Synthesis with Multi-Reference Encoder
원문 초록
Multi-speaker singing voice synthesis is to generate the singing voice sung by different speakers. To generalize to new speakers, previous zero-shot singing adaptation methods obtain the timbre of the target speaker with a fixed-size embedding from single reference audio. However, they face several challenges: 1) the fixed-size speaker embedding is not powerful enough to capture full details of the target timbre; 2) single reference audio does not contain sufficient timbre information of the target speaker; 3) the pitch inconsistency between different speakers also leads to a degradation in the generated voice. In this paper, we propose a new model called MR-SVS to tackle these problems. Specifically, we employ both a multi-reference encoder and a fixed-size encoder to encode the timbre of the target speaker from multiple reference audios. The Multi-reference encoder can capture more details and variations of the target timbre. Besides, we propose a well-designed pitch shift method to address the pitch inconsistency problem. Experiments indicate that our method outperforms the baseline method both in naturalness and similarity.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis
TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control
GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challenge
CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection
Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt
토론
이 논문과 연결된 포럼 글이 아직 없습니다.