| Paper ID | AUD-7.1 |
| Paper Title |
LASAFT: LATENT SOURCE ATTENTIVE FREQUENCY TRANSFORMATION FOR CONDITIONED SOURCE SEPARATION |
| Authors |
Woosung Choi, Minseok Kim, Korea University, South Korea; Jaehwa Chung, Korea National Open University, South Korea; Soonyoung Jung, Korea University, South Korea |
| Session | AUD-7: Audio and Speech Source Separation 3: Deep Learning |
| Location | Gather.Town |
| Session Time: | Wednesday, 09 June, 13:00 - 13:45 |
| Presentation Time: | Wednesday, 09 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Audio and Acoustic Signal Processing: [AUD-SEP] Audio and Speech Source Separation |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Recent deep-learning approaches have shown that Frequency Transformation (FT) blocks can significantly improve spectrogram-based single-source separation models by capturing frequency patterns. The goal of this paper is to extend the FT block to fit the multi-source task. We propose the Latent Source Attentive Frequency Transformation (LaSAFT) block to capture source-dependent frequency patterns. We also propose the Gated Point-wise Convolutional Modulation (GPoCM), an extension of Feature-wise Linear Modulation (FiLM), to modulate internal features. By employing these two novel methods, we extend the Conditioned-U-Net (CUNet) for multi-source separation, and the experimental results indicate that our LaSAFT and GPoCM can improve the CUNet's performance, achieving state-of-the-art SDR performance on several MUSDB18 source separation tasks. |
