电子学报Issue(10)：1991-1997,7.DOI:10.3969/j.issn.0372-2112.2014.10.019
基于AR-HMM在线能量调整的语音增强方法
Online Energy Adjustment Using AR-HMM for Speech Enhancement
摘要
Abstract
Because the existing single channel speech enhancement technologies perform not well in the tracking and sup-pression of non-stationary noise ,the speech enhancement method based on online energy adjustment is proposed .The normalized critical band energy parameters are employed as the feature in Gaussian mixture model (GMM ) to distinguish the background nois-es .Based on the AR-HMM of clean speech and the noise of corresponding type ,the power spectrums of speech and noise are esti-mated under minimum mean square error (MMSE ) criteria .When the differences between the training data and test data are consid-ered in the non-stationary noise environment ,the online adjustment method for the speech and noise models is necessary .The scaling factor of speech energy is estimated with the iterative expectation maximization (EM) algorithm and the one of noise energy is esti-mated with the re-estimation approach similar to the training stage .And the initial scaling factor of noise energy is obtained by mini-ma-controlled recursive averaging (MCRA ) algorithm .The evaluation of the proposed method is performed under the standard of ITU-T G .160 .The test results reveal that ,comparing with the two reference methods ,the proposed method performs well in non-stationary noise environments ,including larger noise reduction and shorter convergence time .关键词
语音增强/非平稳噪声/隐马尔可夫模型/高斯混合模型Key words
speech enhancement/non-stationary noise/hidden Markov model/Gaussian mixture model分类
信息技术与安全科学引用本文复制引用
何玉文,鲍长春,夏丙寅..基于AR-HMM在线能量调整的语音增强方法[J].电子学报,2014,(10):1991-1997,7.基金项目
国家自然科学基金（No ．61072089）；北京市教育委员会科技发展计划重点项目 （）
