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 2204.03594cs.SDcs.LGeess.AS
收藏

异构目标语音分离

Heterogeneous Target Speech Separation

MERL(三菱电机研究实验室)

Efthymios Tzinis, Gordon Wichern, Aswin Subramanian, Paris Smaragdis, Jonathan Le Roux

摘要:

我们介绍了一种新的单通道目标声源分离范例,其中感兴趣的声源可以使用非互斥概念(例如,响度、性别、语言、空间位置等)。我们提出的异构分离框架可以无缝地利用具有大分布偏移的数据集,并在各种概念下学习跨域表示。我们的实验表明,具有异构条件的训练分离模型有助于推广到具有看不见的域外数据的新概念,同时其性能也大大高于单域专家模型。值得注意的是,这样的训练导致新的更硬的声源分离判别概念的更鲁棒的学习,并且可以产生优于利用oracle源选择的置换不变训练的改进。我们分析了具有异构元数据的声源分离训练的内在行为,并提出了在具有挑战性的分离条件下缓解新出现的问题的方法。我们发布了所有数据集的制备配方集合,用于进一步促进这项具有挑战性的任务的研究。

英文摘要:

We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e.g., loudness, gender, language, spatial location, etc). Our proposed heterogeneous separation framework can seamlessly leverage datasets with large distribution shifts and learn cross-domain representations under a variety of concepts used as conditioning. Our experiments show that training separation models with heterogeneous conditions facilitates the generalization to new concepts with unseen out-of-domain data while also performing substantially higher than single-domain specialist models. Notably, such training leads to more robust learning of new harder source separation discriminative concepts and can yield improvements over permutation invariant training with oracle source selection. We analyze the intrinsic behavior of source separation training with heterogeneous metadata and propose ways to alleviate emerging problems with challenging separation conditions. We release the collection of preparation recipes for all datasets used to further promote research towards this challenging task.

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。

↑