Authors
- Ryosuke Sawata
- Naoya Takahashi
- Stefan Uhlich*
- Shusuke Takahashi*
- Yuki Mitsufuji
* External authors
Venue
- EURASIP
Date
- 2024
The whole is greater than the sum of its parts: improving music source separation by bridging networks
Stefan Uhlich*
Shusuke Takahashi*
* 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
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…
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…
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…
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.