Informed Group-sparse Representation For Singing Voice Separation

Abstract

Singing voice separation attempts to separate the vocal and instrumental parts of a music recording, which is a fundamental problem in music information retrieval. Recent work on singing voice separation has shown that the low-rank representation and informed separation approaches are both able to improve separation quality. However, low-rank optimizations are computationally inefficient due to the use of singular value decompositions. Therefore, in this paper, we propose a new linear-time algorithm called informed group-sparse representation, and use it to separate the vocals from music using pitch annotations as side information. Experimental results on the iKala dataset confirm the efficacy of our approach, suggesting that the music accompaniment follows a group-sparse structure given a pre-trained instrumental dictionary. We also show how our work can be easily extended to accommodate multiple dictionaries using the DSD100 dataset.

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keychan2018informed

Related papers

• Unsupervised Interpretable Representation Learning For Singing Voice Separation (2020)5.84
• Investigation Of Singing Voice Separation For Singing Voice Detection In Polyphonic Music (2020)5.84
• Revisiting Representation Learning For Singing Voice Separation With Sinkhorn Distances (2020)0.00
• Jointly Detecting And Separating Singing Voice: A Multi-task Approach (2018)7.81
• A Preliminary Investigation On Flexible Singing Voice Synthesis Through Decomposed Framework With Inferrable Features (2024)0.00
• Medleyvox: An Evaluation Dataset For Multiple Singing Voices Separation (2022)10.63
• SVSGAN: Singing Voice Separation Via Generative Adversarial Network (2017)0.00
• A Recurrent Encoder-decoder Approach With Skip-filtering Connections For Monaural Singing Voice Separation (2017)9.41