arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.00286cs.SDcs.AIcs.LGeess.AS
收藏

Jointist:通过联合训练同时提高多乐器转录和音乐声源分离

Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training

Singapore University of Technology and Design(新加坡科技设计大学);Gaudio Lab(Gaudio实验室);Bytedance(字节跳动)

Kin Wai Cheuk, Keunwoo Choi, Qiuqiang Kong, Bochen Li, Minz Won, Ju-Chiang Wang, Yun-Ning Hung, Dorien Herremans

摘要:

在本文中,我们介绍了Jointist,一个乐器感知的多乐器框架,能够转录,识别和分离多个乐器从音频剪辑。Jointist由一个乐器识别模块组成,该模块调节其他两个模块:一个转录模块,输出乐器特定的钢琴卷,以及一个声源分离模块,利用乐器信息和转录结果。转录和声源分离模块的联合训练有助于提高这两项任务的性能。仪器模块是可选的,可由人类用户直接控制。这使得Jointist成为一个灵活的用户可控框架。我们具有挑战性的问题制定使得该模型在现实世界中非常有用,因为现代流行音乐通常由多种乐器组成。然而,它的新颖性需要一个新的视角来评估这样一个模型。在我们的实验中,我们从多个方面评估了所提出的模型,为多仪器转录提供了一个新的评估视角。我们的主观听力研究表明,Jointist在流行音乐上实现了最先进的性能,优于现有的多乐器转录模型,如MT3。我们对几个下游任务进行了实验,发现所提出的方法将转录提高了1个百分点以上(ppt),声源分离5 SDR,下拍检测1.8 ppt,和弦识别1.4 ppt,和关键估计1.4个百分点,当利用从Jointist获得的转录结果时。演示可在\url{https://jointist.github.io/Demo}上获得。

英文摘要:

In this paper, we introduce Jointist, an instrument-aware multi-instrument framework that is capable of transcribing, recognizing, and separating multiple musical instruments from an audio clip. Jointist consists of an instrument recognition module that conditions the other two modules: a transcription module that outputs instrument-specific piano rolls, and a source separation module that utilizes instrument information and transcription results. The joint training of the transcription and source separation modules serves to improve the performance of both tasks. The instrument module is optional and can be directly controlled by human users. This makes Jointist a flexible user-controllable framework. Our challenging problem formulation makes the model highly useful in the real world given that modern popular music typically consists of multiple instruments. Its novelty, however, necessitates a new perspective on how to evaluate such a model. In our experiments, we assess the proposed model from various aspects, providing a new evaluation perspective for multi-instrument transcription. Our subjective listening study shows that Jointist achieves state-of-the-art performance on popular music, outperforming existing multi-instrument transcription models such as MT3. We conducted experiments on several downstream tasks and found that the proposed method improved transcription by more than 1 percentage points (ppt.), source separation by 5 SDR, downbeat detection by 1.8 ppt., chord recognition by 1.4 ppt., and key estimation by 1.4 ppt., when utilizing transcription results obtained from Jointist. Demo available at \url{https://jointist.github.io/Demo}.

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。

↑