arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1808.08095cs.LGstat.ML
收藏

多场景深度学习多说话人声源分离

Multi-scenario deep learning for multi-speaker source separation

KU Leuven(鲁汶大学)

Jeroen Zegers, Hugo Van hamme

摘要:

用于多说话者声源分离的深度学习研究在过去几年中得到了推动。然而,大多数研究仅限于特定数量的发言者的混合,称为特定场景。虽然有些作品包括不同场景的实验,但将不同场景的数据结合起来或为多种场景创建单一模型的研究非常罕见。在这项工作中,它表明,一个特定的情况下的数据是相关的解决另一个方案。此外,它的结论是,一个单一的模型,在不同的情况下训练是能够匹配特定场景模型的性能。

英文摘要:

Research in deep learning for multi-speaker source separation has received a boost in the last years. However, most studies are restricted to mixtures of a specific number of speakers, called a specific scenario. While some works included experiments for different scenarios, research towards combining data of different scenarios or creating a single model for multiple scenarios have been very rare. In this work it is shown that data of a specific scenario is relevant for solving another scenario. Furthermore, it is concluded that a single model, trained on different scenarios is capable of matching performance of scenario specific models.

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。

↑