arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.07908cs.SDeess.AS
收藏

用于声源分离的卷积音频模型的神经网络替代方案

Neural Network Alternatives to Convolutive Audio Models for Source Separation

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Adobe Research(Adobe 研究院)

Shrikant Venkataramani, Y. Cem Subakan, Paris Smaragdis

摘要:

卷积非负矩阵分解模型使用具有时间维度的频率模板对给定的音频频谱图进行分解。在本文中,我们提出了一个卷积自动编码器模型,作为一个神经网络替代卷积NMF。利用神经网络赋予的建模灵活性,我们还探讨了在编码器中使用递归神经网络的想法。在TIMIT语音数据集上的实验结果表明,卷积结构在BSSeval指标上显著提高了分离性能。

英文摘要:

Convolutive Non-Negative Matrix Factorization model factorizes a given audio spectrogram using frequency templates with a temporal dimension. In this paper, we present a convolutional auto-encoder model that acts as a neural network alternative to convolutive NMF. Using the modeling flexibility granted by neural networks, we also explore the idea of using a Recurrent Neural Network in the encoder. Experimental results on speech mixtures from TIMIT dataset indicate that the convolutive architecture provides a significant improvement in separation performance in terms of BSSeval metrics.

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。

↑