Muskits-espnet: A Comprehensive Toolkit For Singing Voice Synthesis In New Paradigm

Abstract

This research presents Muskits-ESPnet, a versatile toolkit that introduces new paradigms to Singing Voice Synthesis (SVS) through the application of pretrained audio models in both continuous and discrete approaches. Specifically, we explore discrete representations derived from SSL models and audio codecs and offer significant advantages in versatility and intelligence, supporting multi-format inputs and adaptable data processing workflows for various SVS models. The toolkit features automatic music score error detection and correction, as well as a perception auto-evaluation module to imitate human subjective evaluating scores. Muskits-ESPnet is available at https://github.com/espnet/espnet.

Stats

• citations3
• S2 citations—
• github stars9824
• HF likes0
• heat score12.50
• arxiv keywu2024muskits

Code

• espnet/espnet—

Related papers

• Muskits: An End-to-end Music Processing Toolkit For Singing Voice Synthesis (2022)5.02
• NNSVS: A Neural Network-based Singing Voice Synthesis Toolkit (2022)13.83
• Singing Voice Data Scaling-up: An Introduction To Ace-opencpop And Ace-kising (2024)15.48
• Everyone-can-sing: Zero-shot Singing Voice Synthesis And Conversion With Speech Reference (2025)0.00
• Sifisinger: A High-fidelity End-to-end Singing Voice Synthesizer Based On Source-filter Model (2024)4.52
• Visinger2+: End-to-end Singing Voice Synthesis Augmented By Self-supervised Learning Representation (2024)4.52
• Espnet-codec: Comprehensive Training And Evaluation Of Neural Codecs For Audio, Music, And Speech (2024)9.03
• Cssinger: End-to-end Chunkwise Streaming Singing Voice Synthesis System Based On Conditional Variational Autoencoder (2024)0.00