Based on fuzzy Gaussian mixture model （FGMM） and support vector regression （SVR）,an improved version of non-intrusive objective measurement for assessing quality of output speech without inputting clean speech is ...Based on fuzzy Gaussian mixture model （FGMM） and support vector regression （SVR）,an improved version of non-intrusive objective measurement for assessing quality of output speech without inputting clean speech is proposed for narrowband speech.Its perceptual linear predictive （PLP） features extracted from clean speech and clustered by FGMM are used as an artificial reference model.Input speech is separated into three classes,for each a consistency parameter between each feature pair from test speech signals and its counterpart in the pre-trained FGMM reference model is calculated and mapped to an objective speech quality score using SVR method.The correlation degree between subjective mean opinion score （MOS） and objective MOS is analyzed.Experimental results show that the proposed method offers an effective technique and can give better performances than the ITU-T P.563 method under most of the test conditions for narrowband speech.展开更多
为了解决传统高斯混合模型GMM(Gaussian m ixture model)的训练方法对模型初值十分敏感、在实际训练中极易得到局部最优模型参数的问题,提出了一种GMM模型参数训练的新方法。将遗传算法与基于模糊聚类分析的GMM参数估计相结合,形成一种...为了解决传统高斯混合模型GMM(Gaussian m ixture model)的训练方法对模型初值十分敏感、在实际训练中极易得到局部最优模型参数的问题,提出了一种GMM模型参数训练的新方法。将遗传算法与基于模糊聚类分析的GMM参数估计相结合,形成一种新的混合算法,对模型参数进行全局优化,提高了参数估计的准确性。采用自适应交叉和变异算子,同时利用模糊最小目标函数FMOF(FuzzyM inimum Objection Function)准则对模型参数进行重估,提高了算法的搜索效率,加快了算法的收敛速度。使用PKU-SRSC语音数据库进行了与文本无关的说话人辨认实验。实验表明,与传统的GMM训练方法和最大似然估计方法相比,本文方法可以得到更优的模型参数,同时识别率也有所提高。展开更多
文摘Based on fuzzy Gaussian mixture model （FGMM） and support vector regression （SVR）,an improved version of non-intrusive objective measurement for assessing quality of output speech without inputting clean speech is proposed for narrowband speech.Its perceptual linear predictive （PLP） features extracted from clean speech and clustered by FGMM are used as an artificial reference model.Input speech is separated into three classes,for each a consistency parameter between each feature pair from test speech signals and its counterpart in the pre-trained FGMM reference model is calculated and mapped to an objective speech quality score using SVR method.The correlation degree between subjective mean opinion score （MOS） and objective MOS is analyzed.Experimental results show that the proposed method offers an effective technique and can give better performances than the ITU-T P.563 method under most of the test conditions for narrowband speech.
