ASSDJul 14, 2021

Multi-Task Audio Source Separation

arXiv:2107.06467v11 citations
Originality Incremental advance
AI Analysis

This addresses audio source separation for applications like speech enhancement and music processing, but it is incremental as it builds on existing deep learning methods.

The paper tackles the problem of separating speech, music, and noise from monaural audio mixtures by proposing a multi-task model in the complex domain, which shows significant performance advantages over existing separation models.

The audio source separation tasks, such as speech enhancement, speech separation, and music source separation, have achieved impressive performance in recent studies. The powerful modeling capabilities of deep neural networks give us hope for more challenging tasks. This paper launches a new multi-task audio source separation (MTASS) challenge to separate the speech, music, and noise signals from the monaural mixture. First, we introduce the details of this task and generate a dataset of mixtures containing speech, music, and background noises. Then, we propose an MTASS model in the complex domain to fully utilize the differences in spectral characteristics of the three audio signals. In detail, the proposed model follows a two-stage pipeline, which separates the three types of audio signals and then performs signal compensation separately. After comparing different training targets, the complex ratio mask is selected as a more suitable target for the MTASS. The experimental results also indicate that the residual signal compensation module helps to recover the signals further. The proposed model shows significant advantages in separation performance over several well-known separation models.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes