arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.04469eess.AScs.CLcs.SD
收藏

一种用于语音增强的非因果FFTNet结构

A non-causal FFTNet architecture for speech enhancement

University of Crete(克里特大学)

Muhammed PV Shifas, Nagaraj Adiga, Vassilis Tsiaras, Yannis Stylianou

摘要:

本文提出了一种基于FFTNet神经网络的并行、非因果、浅波形域语音增强算法。与其他基于波形的方法(如WaveNet)相比,FFTNet使用初始宽膨胀模式。这样的架构更好地表示时域中的语音的长期相关结构,其中噪声通常是高度不相关的,并且因此它适合于基于波形域的语音增强。为了进一步加强FFTNet的这一特性,我们提出了一种非因果FFTNet架构,其中每一层中的当前样本是从前一层的过去和未来样本中估计出来的。通过建议浅层网络并在一定限度内应用非因果关系,与用于语音增强的其他基于神经网络的方法(如WaveNet和SEGAN)相比,所建议的用于语音增强的FFTNet(SE-FFTNet)使用少得多的参数。具体来说,建议的网络大大减少了模型参数:与WaveNet相比减少了32%,与SEGAN相比减少了87%。最后,基于主观和客观指标,SE-FFTNet在增强的信号质量方面优于WaveNet,同时提供与SEGAN同样好的性能。在1中提供了该架构的Tensorflow实现。

英文摘要:

In this paper, we suggest a new parallel, non-causal and shallow waveform domain architecture for speech enhancement based on FFTNet, a neural network for generating high quality audio waveform. In contrast to other waveform based approaches like WaveNet, FFTNet uses an initial wide dilation pattern. Such an architecture better represents the long term correlated structure of speech in the time domain, where noise is usually highly non-correlated, and therefore it is suitable for waveform domain based speech enhancement. To further strengthen this feature of FFTNet, we suggest a non-causal FFTNet architecture, where the present sample in each layer is estimated from the past and future samples of the previous layer. By suggesting a shallow network and applying non-causality within certain limits, the suggested FFTNet for speech enhancement (SE-FFTNet) uses much fewer parameters compared to other neural network based approaches for speech enhancement like WaveNet and SEGAN. Specifically, the suggested network has considerably reduced model parameters: 32% fewer compared to WaveNet and 87% fewer compared to SEGAN. Finally, based on subjective and objective metrics, SE-FFTNet outperforms WaveNet in terms of enhanced signal quality, while it provides equally good performance as SEGAN. A Tensorflow implementation of the architecture is provided at 1 .

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。

↑