Title :
Speech quality objective assessment using neural network
Author :
Fu, Qiung ; Yi, Kechu ; Sun, Mingui
Author_Institution :
Nat. Key Lab. of ISN, Xidian Univ., Xi´´an, China
Abstract :
This paper presents a novel method for objective assessment of speech quality based on one-step strategy using a feedfoward neutral network. Currently, almost all the existing methods for this assessment can be regarded as a two-step strategy, requiring a distortion computation and a mapping from the average distortion value to the mean opinion score (MOS). Our new method combines these two steps by means of a neural network which can incorporate the perception properties of the human auditory system and provide an MOS estimate directly. Our theoretical analysis and experimental results suggest that this method of MOS estimate significantly overperforms the traditional methods. The correlation coefficient between the subjective test score and objective MOS estimate can reach up to about 0.95
Keywords :
multilayer perceptrons; radial basis function networks; speech processing; MOS; average distortion value; feedfoward neutral network; human auditory system; mean opinion score; one-step strategy; perception; speech quality objective assessment; Auditory system; Distortion measurement; Humans; Laboratories; Neural networks; Nonlinear distortion; Quality assessment; Regression analysis; Speech analysis; Testing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
Conference_Location :
Istanbul
Print_ISBN :
0-7803-6293-4
DOI :
10.1109/ICASSP.2000.861932
