Improved Singing Voice Separation With Chromagram-based Pitch-aware Remixing

Abstract

Singing voice separation aims to separate music into vocals and accompaniment components. One of the major constraints for the task is the limited amount of training data with separated vocals. Data augmentation techniques such as random source mixing have been shown to make better use of existing data and mildly improve model performance. We propose a novel data augmentation technique, chromagram-based pitch-aware remixing, where music segments with high pitch alignment are mixed. By performing controlled experiments in both supervised and semi-supervised settings, we demonstrate that training models with pitch-aware remixing significantly improves the test signal-to-distortion ratio (SDR)

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keyyuan2022improved

Related papers

• SVSGAN: Singing Voice Separation Via Generative Adversarial Network (2017)0.00
• Self-remixing: Unsupervised Speech Separation Via Separation And Remixing (2022)6.77
• Improving Singing Voice Separation Using Deep U-net And Wave-u-net With Data Augmentation (2019)10.35
• Singing Voice Separation: A Study On Training Data (2019)10.07
• Singaug: Data Augmentation For Singing Voice Synthesis With Cycle-consistent Training Strategy (2022)7.16
• Informed Group-sparse Representation For Singing Voice Separation (2018)7.16
• Jointly Detecting And Separating Singing Voice: A Multi-task Approach (2018)7.81
• A Data-driven Approach To Smooth Pitch Correction For Singing Voice In Pop Music (2018)0.00