公开(公告)号：US09786300B2

公开(公告)日：2017-10-10

申请号：US13195338

申请日：2011-08-01

申请人： Wai-Yip Chan ,  Tiago H Falk ,  Qingfeng Xu

发明人： Wai-Yip Chan ,  Tiago H Falk ,  Qingfeng Xu

IPC分类号： G10L25/00 ,  G10L25/69 ,  H04M1/24 ,  H04M3/22

CPC分类号： G10L25/69

摘要： A non-intrusive speech quality estimation technique is based on statistical or probability models such as Gaussian Mixture Models (“GMMs”). Perceptual features are extracted from the received speech signal and assessed by an artificial reference model formed using statistical models. The models characterize the statistical behavior of speech features. Consistency measures between the input speech features and the models are calculated to form indicators of speech quality. The consistency values are mapped to a speech quality score using a mapping optimized using machine learning algorithms, such as Multivariate Adaptive Regression Splines (“MARS”). The technique provides competitive or better quality estimates relative to known techniques while having lower computational complexity.