paper-with-me

홈 › Papers

Why does music source separation benefit from cacophony?

2024-02-28 · Chang-Bin Jeon, Gordon Wichern, François G. Germain, Jonathan Le Roux

In music source separation, a standard training data augmentation procedure is to create new training samples by randomly combining instrument stems from different songs. These random mixes have mismatched characteristics compared to real music, e.g., the different stems do not have consistent beat or tonality, resulting in a cacophony. In this work, we investigate why random mixing is effective when training a state-of-the-art music source separation model in spite of the apparent distribution shift it creates. Additionally, we examine why performance levels off despite potentially limitless combinations, and examine the sensitivity of music source separation performance to differences in beat and tonality of the instrumental sources in a mixture.

📄 PDF Abstract BibTeX arXiv:2402.18407

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationMusic Source Separation

Similar Papers 제목 키워드 기반

Unsupervised Source Separation By Steering Pretrained Music Models

2021-10-25 · Ethan Manilow, Patrick O'Reilly, Prem Seetharaman, Bryan Pardo

We showcase an unsupervised method that repurposes deep models trained for music generation and music tagging for audio source separation, without any retraining. An audio generation model is conditioned on an input mixt…

Audio GenerationAudio Source SeparationMusic GenerationMusic Tagging+1

A Hands-on Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation

2021-06-16 · Martin Strauss, Jouni Paulus, Matteo Torcoli, Bernd Edler

This paper describes a hands-on comparison on using state-of-the-art music source separation deep neural networks (DNNs) before and after task-specific fine-tuning for separating speech content from non-speech content in…

Music Source SeparationTransfer Learning

A Knowledge-Driven Approach to Music Segmentation, Music Source Separation and Cinematic Audio Source Separation

2026-02-25 · Chun-wei Ho, Sabato Marco Siniscalchi, Kai Li, Chin-Hui Lee arxiv

We propose a knowledge-driven, model-based approach to segmenting audio into single-category and mixed-category chunks with applications to source separation. "Knowledge" here denotes information associated with the data…

Music Source SeparationAudio Source Separation

Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction

2017-10-31 · Daniel Stoller, Sebastian Ewert, Simon Dixon

The state of the art in music source separation employs neural networks trained in a supervised fashion on multi-track databases to estimate the sources from a given mixture. With only few datasets available, often exten…

Audio Source SeparationData AugmentationMusic Source Separation

Music Source Separation in the Waveform Domain

2019-11-27 · Alexandre Défossez, Nicolas Usunier, Léon Bottou, Francis Bach

Source separation for music is the task of isolating contributions, or stems, from different instruments recorded individually and arranged together to form a song. Such components include voice, bass, drums and any othe…

Audio GenerationAudio SynthesisData AugmentationMulti-task Audio Source Seperation+2