论文标题
音乐乐器表演的条件源分离
Conditioned Source Separation for Music Instrument Performances
论文作者
论文摘要
在音乐源分离中，每件作品的来源数量可能有所不同，一些来源可能属于同一仪器家族，从而共享了音节特征并使来源更加相关。这导致了源分离问题的其他挑战。本文提出了一种同时发出多种乐器的源分离方法，并探讨了除了音频流以外的其他信息可以提高源分离的质量。我们在主要源分离网络的不同级别探索条件技术，并利用两种额外的数据模式，即混合物中的仪器的存在或不存在以及相应的视频流数据。
In music source separation, the number of sources may vary for each piece and some of the sources may belong to the same family of instruments, thus sharing timbral characteristics and making the sources more correlated. This leads to additional challenges in the source separation problem. This paper proposes a source separation method for multiple musical instruments sounding simultaneously and explores how much additional information apart from the audio stream can lift the quality of source separation. We explore conditioning techniques at different levels of a primary source separation network and utilize two extra modalities of data, namely presence or absence of instruments in the mixture, and the corresponding video stream data.
