Objective Evaluation System of Speech Quality Based HMM


Article Preview

It is of great significance that objective evaluation of speech quality in language self-learning. Aimed at the objective evaluation process of speech quality the thesis presented to build HMM model based speech feature MFCC of human auditory model, and to use different indicators to achieve the evaluation of phoneme, word and sentence. Effective solution was proposed for such issues as the initial model to select more sequence of observations to train HMM as well as data underflow encountered during practical application of HMM algorithm. According to some speech experts, the evaluation results achieved by speech quality evaluation system were objective.



Advanced Materials Research (Volumes 403-408)

Edited by:

Li Yuan




J. Zhang, "Objective Evaluation System of Speech Quality Based HMM", Advanced Materials Research, Vols. 403-408, pp. 1989-1992, 2012

Online since:

November 2011





[1] Rix A.W. Perceptual speech quality assessment a review,IEEE International Conference on Acoustics,Speeeh and Signal Processing,3(1): 1056-1059, (2004).

DOI: https://doi.org/10.1109/icassp.2004.1326730

[2] Doh-Suk Kim, Tarraf A. Perceptual model for non-intrusive speech quality assessment, IEEE International Conference on Acoustic, Speech and Signal Processing), 3(5): 17-21, (2004).

DOI: https://doi.org/10.1109/icassp.2004.1326731

[3] Doh-Suk Kim, Tarraf A. Enhanced Perceptual Model for Non-Intrusive Speech Quality Assessment. IEEE International Conference on Acoustics, Speech and Signal Processing, 1(5): 829-832, (2006).

DOI: https://doi.org/10.1109/icassp.2006.1660149

[4] Falk T. H, Wai-Yip Chan. Non-intrusive speech quality estimation using Gaussian mixture models, Signal Processing Letters, IEEE, 13(2): 108-111, (2006).

DOI: https://doi.org/10.1109/lsp.2005.861598

[5] Chen G, Parsa V. Output-based speech quality evaluation by measuring perceptual spectral density distribution, Electronics Letters, 40(12): 783-785, (2004).

DOI: https://doi.org/10.1049/el:20040533

[6] Guo Chen, Parsa V Bayesian Model Based Non-Intrusive Speech Quality Evaluation. IEEE International Conference on Acoustics Speech, and Signal Processing (ICASSP'OS), 1(3): 358-388, (2005).

DOI: https://doi.org/10.1109/icassp.2005.1415131

[7] Liu Qingsheng, Xu Xiaopeng, Huang Wenhao. A Study of Speech Endpoint Detection Method. Computer Engineering, 29 (3) : 120-123, (2003).