A nonlinear adaptive noise canceller for speech enhancement using Volterra filter
A nonlinear adaptive noise canceller for speech enhancement using Volterra filter
复制标题
使用 Volterra 滤波器进行语音增强的非线性自适应噪声消除器
DOI：
10.1109/icamechs.2014.6911651
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
K. Hasegawa
中科院分区：
文献类型：
--
作者：
Yegui Xiao;Ran Xiao;Boyan Huang;K. Hasegawa
在非常苛刻的噪声存在下的语音增强具有实际重要性，因为用于语音去噪的常规技术和算法可能遭受严重的性能下降。许多实际应用都需要更复杂和强大的噪声处理技术和系统。近年来，骨导和空气导语音信号被同时用于对抗背景噪声以提高增强质量。这些增强系统包括一个自适应噪声抵消器（ANC），它采取骨导语音作为其参考信号，而采用空气传导测量作为其主要噪声。在ANC中实现了线性或非线性滤波器。本文提出了一种使用沃尔泰拉滤波器的非线性ANC。所提出的系统，享受良好的收敛性和计算效率，是能够恢复的语音信号的高频分量，即使在一个非常嘈杂的设置。使用真实的骨和空气传导的语音测量的仿真进行证明所提出的系统的有效性。
Speech enhancement in the presence of very harsh noise is of practical importance, as conventional techniques and algorithms for speech denoising may suffer from serious performance degradation. A lot of real-life applications are calling for more sophisticated and powerful noise processing techniques and systems. Recently, both bone- and air-conducted speech signals have been used simultaneously to fight up against the background noise to improve the enhancement quality. Those enhancement systems consist of an adaptive noise canceller (ANC) that takes the bone-conducted speech as its reference signal while adopts the air-conducted measurement as its primary noise. A linear or nonlinear filter is implemented in the ANC. In this paper, we propose a nonlinear ANC by using of Volterra filter. The proposed system, enjoying nice convergence and computational efficiency, is capable of recovering the high-frequency components of the speech signal even in a very noisy setting. Simulations using real bone- and air-conducted speech measurements are performed to demonstrate the effectiveness of the proposed system.
影响因子：
5.4
作者：
Xin Zou;P. Jančovič;Ju Liu;M. Köküer
通讯作者：
Xin Zou;P. Jančovič;Ju Liu;M. Köküer