基于时域滤波多频段MMSE的语音增强研究
摘要
本文提出一种时域滤波中多频带语音增强的方法,通过将时域中的未处理语音过滤成各种等效的基于矩形带宽的子带,然后在每个频带中使用基于离散余弦变换(DCT)MMSE来估计清晰语音。该算法在0~10d B的SNR水平上优于用于汽车、餐厅、列车、白色和工厂噪声的现有技术。
出处
《科技资讯》
2017年第28期30-31,共2页
Science & Technology Information
二级参考文献25
-
1Boll S F.Suppression of acoustic noise in speech usingspectral subtraction[J].IEEE Trans on ASSP,1979,27(2):l13-120.
-
2Berouti M,Schwartz R,Makhoul J.Enhancement of speechcorrupted by acoustic noise[C]//Proceedings of 1979 IEEE,ICASSP,1979:208-211.
-
3Epharim Y,Malah D.Speech enhancement using a minimummean-square error short-time spectral amplitude estimator[J].IEEE Trans on Acoustic,Speech Signal Processing,1984,32(6):1109-1121.
-
4Lochwood P,Boundy J.Experiments with a NonlinearSpectral Subtractor(NSS),hidden Markov models andprojection,for robust recognition in cars[J].Speech Commun,1992,11(6):215-228.
-
5Ephraim Y.A minimum mean square error approach forspeech enhancement[J].Acoustics,Speech,and Signal Processing,1990,2:829-832.
-
6Liu Zhibin,Xu Naiping.Speech enhancement based onminimum mean-square error short-time spectral estimationand its realization[C]//IEEE International Conferenceon Intelligent Processing System,1997:1794-1797.
-
7Martin R.Speech enhancement using MMSE short timespectral estimation with Gamma distributed speech priors[C]//Proc IEEE Int Conf Acoustics,Speech,SignalProcessing,2002,1:253-256.
-
8Kamath S,Loizou P.A multi-band spectral subtractionmethod for enhancing speech corrupted by colorednoise[C]//Proceedings of ICASSP,Orlando,USA,2002.
-
9Lim J S,Oppenheim A V.Enhancement and bandwidthcompression of noisy speech[J].Proc of the IEEE,1979,67(12):1586-1604.
-
10Gibson J D,Koo B,Gray S D.Filtering of colorednoise for speech enhancement and coding[J].IEEE Transon Signal Processing,1991,39:1732-1742.
-
1张小宇,刘云清,赵馨.基于时域滤波多频段谱减法的语音增强[J].长春理工大学学报（自然科学版）,2017,40(4):78-82.
-
2刘中侠,刘思峰,蒋诗泉.基于离散余弦变换的GM(1,1,d)预测模型[J].嘉兴学院学报,2017,29(6):84-88. 被引量：1
-
3何军,赵雯弘,王思杰.某大型化工厂噪声从业人员听力损失情况调查[J].职业卫生与应急救援,2017,35(1):44-45. 被引量：13
-
4马满振,郭理彬,苏奎峰.基于多类运动想象任务的EEG信号分类研究[J].计算机测量与控制,2017,25(10):232-235. 被引量：5
-
5董红松,刘振宇,马辉栋,闫静.语音增强在去除猪咳嗽噪声中的应用研究[J].山西农业大学学报（自然科学版）,2017,37(11):831-836. 被引量：3
-
6程小伟,王健,曾庆宁,谢先明,龙超.噪声环境下稳健的说话人识别特征研究[J].声学技术,2017,36(5):479-483. 被引量：7
