非负矩阵分解
分歧(语言学)
乘法函数
计算机科学
算法
矩阵分解
基质(化学分析)
音频信号
人工神经网络
代表(政治)
人工智能
语音识别
数学
语音编码
物理
数学分析
哲学
政治
量子力学
特征向量
复合材料
材料科学
法学
语言学
政治学
作者
Hiroki Tanji,Takahiro Murakami
出处
期刊:IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
[Institute of Electronics, Information and Communications Engineers]
日期:2023-07-01
卷期号:E106.A (7): 962-975
标识
DOI:10.1587/transfun.2022eap1098
摘要
The design and adjustment of the divergence in audio applications using nonnegative matrix factorization (NMF) is still open problem. In this study, to deal with this problem, we explore a representation of the divergence using neural networks (NNs). Instead of the divergence, our approach extends the multiplicative update algorithm (MUA), which estimates the NMF parameters, using NNs. The design of the extended MUA incorporates NNs, and the new algorithm is referred to as the deep MUA (DeMUA) for NMF. While the DeMUA represents the algorithm for the NMF, interestingly, the divergence is obtained from the incorporated NN. In addition, we propose theoretical guides to design the incorporated NN such that it can be interpreted as a divergence. By appropriately designing the NN, MUAs based on existing divergences with a single hyper-parameter can be represented by the DeMUA. To train the DeMUA, we applied it to audio denoising and supervised signal separation. Our experimental results show that the proposed architecture can learn the MUA and the divergences in sparse denoising and speech separation tasks and that the MUA based on generalized divergences with multiple parameters shows favorable performances on these tasks.
科研通智能强力驱动
Strongly Powered by AbleSci AI