Authors

* External authors

Venue

Date

Share

The whole is greater than the sum of its parts: improving music source separation by bridging networks

Ryosuke Sawata

Naoya Takahashi

Stefan Uhlich*

Shusuke Takahashi*

Yuki Mitsufuji

* External authors

EURASIP

2024

Abstract

This paper presents the crossing scheme (X-scheme) for improving the performance of deep neural network (DNN)-based music source separation (MSS) with almost no increasing calculation cost. It consists of three components: (i) multi-domain loss (MDL), (ii) bridging operation, which couples the individual instrument networks, and (iii) combination loss (CL). MDL enables the taking advantage of the frequency- and time-domain representations of audio signals. We modify the target network, i.e., the network architecture of the original DNN-based MSS, by adding bridging paths for each output instrument to share their information. MDL is then applied to the combinations of the output sources as well as each independent source; hence, we called it CL. MDL and CL can easily be applied to many DNN-based separation methods as they are merely loss functions that are only used during training and do not affect the inference step. Bridging operation does not increase the number of learnable parameters in the network. Experimental results showed that the validity of Open-Unmix (UMX), densely connected dilated DenseNet (D3Net) and convolutional time-domain audio separation network (Conv-TasNet) extended with our X-scheme, respectively called X-UMX, X-D3Net and X-Conv-TasNet, by comparing them with their original versions. We also verified the effectiveness of X-scheme in a large-scale data regime, showing its generality with respect to data size.

Related Publications

Weighted Point Cloud Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric

ICLR, 2025
Toshimitsu Uesaka, Taiji Suzuki, Yuhta Takida, Chieh-Hsin Lai, Naoki Murata, Yuki Mitsufuji

In typical multimodal contrastive learning, such as CLIP, encoders produce onepoint in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity structure of a huge amount of instances in…

Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

ICLR, 2025
Shang-Fu Chen, Chieh-Hsin Lai, Dongjun Kim*, Naoki Murata, Takashi Shibuya, Wei-Hsiang Liao, Shao-Hua Sun, Yuki Mitsufuji, Ayano Hiranaka

Controllable generation through Stable Diffusion (SD) fine-tuning aims to improve fidelity, safety, and alignment with human guidance. Existing reinforcement learning from human feedback methods usually rely on predefined heuristic reward functions or pretrained reward model…

Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

ICLR, 2025
Saurav Jha, Shiqi Yang*, Masato Ishii, Mengjie Zhao*, Christian Simon, Muhammad Jehanzeb Mirza, Dong Gong, Lina Yao, Shusuke Takahashi*, Yuki Mitsufuji

Personalized text-to-image diffusion models have grown popular for their ability to efficiently acquire a new concept from user-defined text descriptions and a few images. However, in the real world, a user may wish to personalize a model on multiple concepts but one at a ti…

  • HOME
  • Publications
  • The whole is greater than the sum of its parts: improving music source separation by bridging networks

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.