HTMD-Net：一种混合掩蔽-去噪的时域单声道歌唱声分离方法
HTMD-Net: A Hybrid Masking-Denoising Approach to Time-Domain Monaural Singing Voice Separation
摘要：
深度学习的出现导致了用于单声道音乐源分离的深度神经网络架构的流行，直接在波形水平上操作的端到端方法越来越受到研究的关注。在这些方法中，将输入混合物变换为学习的潜在空间，以及将软掩模乘法应用于潜在混合物，实现了最佳性能，但易于将伪影引入源估计。为了缓解这个问题，在本文中，我们提出了一种混合的时域方法，称为HTMD-Net，结合了一个轻量级的掩蔽组件和去噪模块，基于跳过连接，以完善的源估计的掩蔽过程。在musdb 18数据集中对我们的方法进行的单声道歌唱声音分离任务的评估表明，与在相同条件下训练时纯粹基于掩蔽的方法相比，我们提出的方法具有竞争力的性能，特别是在无声段期间的行为方面，同时实现了更高的计算效率。
英文摘要：
The advent of deep learning has led to the prevalence of deep neural network architectures for monaural music source separation, with end-to-end approaches that operate directly on the waveform level increasingly receiving research attention. Among these approaches, transformation of the input mixture to a learned latent space, and multiplicative application of a soft mask to the latent mixture, achieves the best performance, but is prone to the introduction of artifacts to the source estimate. To alleviate this problem, in this paper we propose a hybrid time-domain approach, termed the HTMD-Net, combining a lightweight masking component and a denoising module, based on skip connections, in order to refine the source estimated by the masking procedure. Evaluation of our approach in the task of monaural singing voice separation in the musdb18 dataset indicates that our proposed method achieves competitive performance compared to methods based purely on masking when trained under the same conditions, especially regarding the behavior during silent segments, while achieving higher computational efficiency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
