摘要
在低信噪比条件下,传统谱减算法对语音和噪声的独立性假设会产生一定的"音乐噪声",从而降低了语音的可懂度.对此,本文提出了一种结合多窗谱估计和几何谱减的语音增强算法.本算法利用多窗谱估计带噪语音信号的功率谱,采用改进最小值控制递归平均算法实时跟踪估计噪声谱,应用几何谱减算法求解增益函数,从而恢复出精确的语音信号.通过在IEEE数据集上进行实验,并以PESQ和LSD作为评价指标,结果表明本算法在低信噪比条件下,缩短了带噪语音与纯净语音之间的频谱距离,并有效的抑制了增强语音的背景噪声,提高了语音可懂度.
The traditional spectral subtraction methods tend to produce"music noise"under low signal-to-noise ratio(SNR)due to the independence assumption of speech and noise.The intelligibility of speech is reduced greatly.In this paper,we proposed a speech enhancement method via integrating multi-taper spectrum(MTM)estimation and spectral subtraction of geometric(GA).Our method employs the MTM to estimate the power spectrum of the noisy speech,and the improved minima controlled recursive average method to track the estimated noise spectrum in real time.Furthermore,the GA is used to calculate the gain function and speech signal is recovered accurately.Our method can reduce the spectral distance between the noisy speech and the clean speech under the low signal-to-noise ratio prominently,and restrain the background noise of the enhanced speech effectively.Experiments on the IEEE dataset,PESQ and LSD as the evaluation metrics,show that our method improves the speech intelligibility significantly.
作者
李湑
胡俊
刘新
黄石磊
LI Xu;HU Jun;LIU Kin;HUANG Shi-lei(Chongqing Key Laboratory of Optical Communication and Networks,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;IMSL Shenzhen Key Lab,PKU-HKUST Shenzhen Hong Kong Institution,Shenzhen 518057,China;Peking University Shenzhen institute,Shenzhen 518057,China;Key Laboratory of Intelligent Computing & Signal Processing,Ministry of Education,Anhui University,Hefei 230601,China)
出处
《微电子学与计算机》
CSCD
北大核心
2018年第11期62-66,共5页
Microelectronics & Computer
基金
国家自然科学基金(U1613209)
深圳市基础研究项目(JCYJ20160331104524983)
关键词
语音增强
多窗谱
改进的最小控制递归平均
几何谱减
speech enhancement
multi-taper spectrum
improved minima controlled recursive average
spectralsubtraction of geometric