Phase-sensitive real-time capable speech enhancement under voiced-unvoiced uncertainty

Phase-sensitive real-time capable speech enhancement under voiced-unvoiced uncertainty
复制标题

浊音不确定性下的相敏实时语音增强

DOI:
--
复制
发表时间:
2013
期刊:
European Signal Processing Conference
影响因子:
--
通讯作者:
Timo Gerkmann
Timo Gerkmann
中科院分区:
--
文献类型:
--
作者:
Martin Krawczyk;R. Rehr;Timo Gerkmann

文献摘要

参考文献

被引文献

相似文献

在许多基于短时傅立叶变换(STFT)的单通道语音增强算法中,从噪声观测中估计干净语音的频谱幅度以抑制加性噪声。对于估计,仅利用噪声幅度及其函数,如先验或后验信噪比(SNR)。关于干净的语音频谱相位的信息大多没有被采用。在这项工作中,我们提出了一个全面的语音增强设置相结合的相位敏感和相位不敏感的幅度估计,提高感知语音质量的增强信号的PESQ相比,相位不敏感的幅度估计单独。所提出的算法是实时的,在这个意义上,它是在一个因果块的方式实现的计算复杂度是可行的。
In many short-time Fourier transform (STFT)-based single channel speech enhancement algorithms, the clean speech spectral amplitude is estimated from a noisy observation to suppress additive noise. For the estimation, only the noisy amplitudes and functions thereof, like the a priori or a posteriori signal-to-noise ratio (SNR), are utilized. Information about the clean speech spectral phase is mostly not employed. In this work we present a comprehensive speech enhancement setup that combines phase-sensitive and phase-insensitive amplitude estimation, improving the perceptual speech quality of the enhanced signal in terms of PESQ compared to phase-insensitive amplitude estimation alone. The proposed algorithm is real-time capable in the sense that it is implemented in a causal block-wise manner and the computational complexity is feasible.
DOI: 10.1109/tassp.1984.1164453
发表时间: 1984-01-01
期刊: IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING
影响因子: --
作者:
EPHRAIM, Y;MALAH, D
通讯作者: MALAH, D
一致维纳滤波:一种保证频谱图一致性的广义时频掩模设计方法
DOI: --
发表时间: 2010
期刊:
影响因子: --
作者:
ルルージョナトン;ヴァンサンエマヌエル;水野優;亀岡弘和;小野順貴;嵯峨山茂樹
通讯作者: 嵯峨山茂樹