Generic placeholder image

Recent Advances in Electrical & Electronic Engineering

Author(s): Rajesh Kumar Dubey* and Arun Kumar

DOI: 10.2174/2352096511666180917100208

DownloadDownload PDF Flyer Cite As
Single-ended Speech Quality Evaluation Using Linear Combination of the Quality Score Estimates of Multi-instances Features

Page: [464 - 474] Pages: 11

  • * (Excluding Mailing and Handling)

Abstract

Background: In a single-ended speech quality evaluation, the measurement of Mean Opinion Score (MOS) is done objectively without the use of clean speech as a reference. In this work, multiple time-instances or multi-instances features using Multi-Resolution Auditory Model (MRAM) along with other relevant features such as Mel-Frequency Cepstral Coefficients (MFCC), and Line Spectral Frequencies (LSF) features are used for single-ended speech quality measurement. The Voice Activity Detection (VAD) algorithm separates the presence of speech-regions from silence in a speech signal.

Methods: The multi-instances features are computed using MRAM, MFCC and LSF for different combinations of speech-regions to capture degradations due to multiple time-localized effects or the attacks of short-time transient distortions such as impulsive noise and their distinctions from plosive sounds in speech. These multi-instances features are used for Gaussian Mixture Model (GMM) MAPPING to compute the objective MOS values, corresponding to all multi-instances features.

Results: The overall objective MOS estimation of the speech signal is calculated by averaging all the values of objective MOS corresponding to the different multi-instances features of a speech signal. The results in terms of Pearson’s Correlation Coefficients (PCC) and root mean square error (RMSE) between the subjective MOS and the estimated overall objective MOS of speech signals are computed and compared with International Telecommunication Union-telephony (ITU-T) Recommendation P.563 and recently published works on similar types of databases.

Conclusion: The improved values of PCC and RMSE between the subjective and the estimated overall objective MOS show the efficacy of the approach.

Keywords: Auditory model, degraded speech, multiple time-instances features, multi-resolution, non-intrusive, speech quality.

Graphical Abstract

[1]
M. Werner, T. Junge, and P. Vary, "Quality control for AMR speech channels in GSM networks In:", Proceedings of the IEEE International Conference on Acoustic., Speech and Signal Processing. Montreal, Quebec, Canada, vol. 3, 2004, pp. 1076-1079.
[2]
ITU-T Recommendation P. 800. Methods for subjective determination of transmission quality, Aug. 30, 1996.
[3]
L. Malfait, J. Berger, and M. Kastner, "P.563-The ITU-T standard for single-ended speech quality assessment", IEEE Trans. Audio Speech Lang. Process., vol. 14, no. 6, pp. 1924-1934, 2006.
[4]
ITU-T Recommendation P.563. Single ended method for objective speech quality assessment in narrow-band telephony applications, May, 2004.
[5]
https://www.itu.int/itu-t/workprog/wp_item.aspx?isn=13743 [accessed].
[6]
R.K. Dubey, and A. Kumar, "Non-intrusive speech quality assessment using several combinations of auditory features", Int. J. Speech Technol. Springer, vol. 16, no. 1, pp. 89-101, 2013.
[7]
V. Grancharov, D.Y. Jhao, J. Lindblom, and W.B. Kleijn, "Low-complexity, non-intrusive speech quality assessment", IEEE Trans. Audio Speech Lang. Process., vol. 14, no. 6, pp. 1948-1956, 2006.
[8]
D.S. Kim, "ANIQUE: An auditory model for single ended speech quality estimation", IEEE Trans. Audio Speech Lang. Process., vol. 13, no. 5, pp. 821-831, 2005.
[9]
R.K. Dubey, and A. Kumar, "Multiple time-instances features of degraded speech for single ended quality measurement", J. Adv. Electric. Electron. Eng., vol. 15, no. 3, pp. 400-407, 2017.
[10]
R.F. Lyon, "A computational model of filtering, detection, and compression in the cochlea In:", Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. California, USA, 1982, pp. 1282-1285.
[11]
L.R. Rabiner, and M.R. Sambur, "Voiced-unvoiced-silence detection using the Itakura LPC distance measure In:", Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. New Jersey, USA, vol. 2, 1977, pp. 323-326.
[12]
M. Narwaria, and W. Lin, "I.V. McLoughlin, S. Emmanuel and L.T. Chia, “Nonintrusive quality assessment of noise suppressed speech with mel-filtered energies and support vector regression", IEEE Trans. Audio Speech Lang. Process., vol. 20, no. 4, pp. 1217-12322012, .
[13]
N.H. Soni, and H.A. Patil, "Novel deep auto encoder features for non-intrusive speech quality assessment In:", Proceedings of the 24th European Signal Processing Conference (EUSIPCO). Budapest, Hungary, 2016, pp. 2315-2319.
[14]
Q. Li, Y. Fang, W. Lin, and D. Thalmann, "Non-intrusive quality assessment for enhanced speech signals based on spectro-temporal features In:", Proceedings of the International Conference on Multimedia and Expo Workshops (ICMEW). Chengdu, China, 2014, pp. 1-6.
[15]
M.R. Islam, M.A. Rahman, M.N. Hasan, A.N.M.S. Hossain, A.N. Uddin, and M.A. Haque, "Non-intrusive objective evaluation of speech quality in noisy condition, In:", Proceedings of the 9th International Conference on Electrical and Computer Engineering (ICECE),. Dhaka, Bangladesh, 2016, pp. 586-589.
[16]
Q. Li, W. Lin, Y. Fang, and D. Thalmann, "Bag-of-words representation for non-intrusive speech quality assessment In:", Proceedings of the International Conference on Signal and Information Processing. Chengdu, China, 2015, pp. 616-619.
[17]
A.K. Karmakar, and R.K. Patney, "Design of optimal wavelet packet trees based on auditory perception criterion", IEEE Signal Process. Lett., vol. 14, no. 4, pp. 240-243, 2007.
[18]
R.K. Dubey, and A. Kumar, "Non-intrusive speech quality assessment using multi-resolution auditory model features for degraded narrowband speech", IET Sig. Prosess., vol. 9, no. 9, pp. 638-646, 2015.
[19]
A.K. Karmakar, and R.K. Patney, "A multiresolution model of auditory excitation pattern and its application to objective evaluation of perceived speech quality", IEEE Trans. Audio Speech Lang. Process., vol. 14, no. 6, pp. 912-1923, 2006.
[20]
R.K. Dubey, and A. Kumar, "Non-intrusive objective speech quality evaluation using multiple time-scale estimates of multi-resolution auditory model (MRAM) features In:", Proceedings of the International conference CIPECH-16. Ghaziabad, India, 2016, pp. 249- 253.
[21]
M.R. Schroeder, "Optimizing digital speech coders by exploiting masking properties of the human ear", J. Acoust. Soc. Am., vol. 66, no. 6, pp. 1647-1652, 1979.
[22]
B.C.J. Moore, An introduction to the psychology of hearing”, 4th ed. London: Elsevier, Academic Press, 1997.
[23]
W. Han, C.F. Chan, C.S. Choy, and K.P. Pun, "An efficient MFCC extraction method in speech recognition In:", Proceedings of the IEEE International Symposium on Circuits and Systems. Island of Kos, Greece, 2006, pp. 145-148.
[24]
M.R. Hasan, M. Jamil, G. Rabbani, and M.S. Rahman, "Speaker identification using mel-frequency cepstral coefficient In:", Proceedings of the 3rd International Conference on Electrical & Computer Engineering. Dhaka, Bangladesh, 2004, pp. 565-568.
[25]
B.J. Lee, S. Kim, and H.G. Kang, "Speaker recognition based on transformed line spectral frequencies In:", Proceedings of the Intelligent Signal Processing and Communication Systems. Seoul, South Korea, South Korea, pp. 177-180.
[26]
ITU-T Recommendation P. Supplement-23, ITU-T Coded-Speech Database, Feb. 1998.
[27]
Y. Hu, and P.C. Loizou, "Subjective comparison and evaluation of speech enhancement algorithms", J. Speech Communications, Elsevier, vol. 49, pp. 588-601, 2007.
[28]
http://www.utdallas.edu/~loizou/speech/noizeus [Accessed Feb. 2009].
[29]
R.K. Dubey, and A. Kumar, "Comparison of subjective and objective speech quality assessment for different degradations/noise conditions In:", Proceedings of the International Conference on Signal Processing and Communication (ICSC),. Noida, India, 2015, pp. 261-266.
[30]
A.P. Dempster, N.M. Laird, and D.B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm", J. Royal Statistical Society, Series B (Methodological),, vol. 39, no. 1, pp. 1-38, 1977.
[31]
J.H. Steiger, "Tests for comparing elements of a correlation matrix", Psychol. Bull., vol. 87, pp. 245-251, 1980.
[32]
M. Hoerger, "ZH: An updated version of Steiger's Z and web-based calculator for testing the statistical significance of the difference between dependent correlations", 2013 URL:, http://www. psychmike.com/dependent_correlations.php