arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.02421eess.AS
收藏

任意声音的单次条件音频过滤

One-shot conditional audio filtering of arbitrary sounds

Beat Gfeller, Dominik Roblek, Marco Tagliasacchi

摘要:

我们考虑的问题,从一个单一的通道混合分离一个特定的声源,仅基于一个短样本的目标源。使用SoundFilter,一种波到波神经网络架构,我们可以训练一个模型,而不使用任何声音类标签。使用与源分离网络联合学习的调节编码器模型,训练的模型可以被“配置”为过滤任意声源,甚至是在训练期间没有看到的声源。在FSD 50 k数据集上进行评估,我们的模型对于两种声音的混合物获得了9.6 dB的SI-SDR改进。在Libripeech上训练时,我们的模型在从两个说话者的混合物中分离出一个声音时,实现了14.0 dB的SI-SDR改进。此外,我们表明,由条件编码器学习的表示在嵌入空间中将声学上相似的声音聚集在一起,即使它是在不使用任何标签的情况下训练的。

英文摘要:

We consider the problem of separating a particular sound source from a single-channel mixture, based on only a short sample of the target source. Using SoundFilter, a wave-to-wave neural network architecture, we can train a model without using any sound class labels. Using a conditioning encoder model which is learned jointly with the source separation network, the trained model can be "configured" to filter arbitrary sound sources, even ones that it has not seen during training. Evaluated on the FSD50k dataset, our model obtains an SI-SDR improvement of 9.6 dB for mixtures of two sounds. When trained on Librispeech, our model achieves an SI-SDR improvement of 14.0 dB when separating one voice from a mixture of two speakers. Moreover, we show that the representation learned by the conditioning encoder clusters acoustically similar sounds together in the embedding space, even though it is trained without using any labels.

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。

↑