客观语音质量评估算法的研究
Study on Objective Speech Quality Assessment Algorithm
摘要: 本文的目的是研究最新客观语音质量评估算法的表现。在通信系统中，语音的质量对于评估系统的表现是一个主要的因素。为了达到评估语音质量的目的，开发有效的语音质量评估算法是必须的。感知的语音质量客观评估算法是最有用和最便捷的方法。在这篇论文里，我们将要讨论评估通信系统和网路中的语音质量的最新的ITU标准PESQ (语音质量的感知评估)和POLQA (感知客观语音质量评估)算法。POLQA是一个技术升级，它能够覆盖最新的语音编码和网络传输技术，对于3G，4G/LTE和VoIP网络有了更高的准确度。我们分析了POLQA的表现，并且将POLQA和PESQ作了对比。从实验数据的结论来看，我们得出了如下结论：POLQA相较于PESQ有更好的表现，并且即将替代PESQ。
Abstract: The aim of this paper is to investigate the performance of the latest objective speech quality assessment algorithm. In the communication system, the quality of speech is an important factor to evaluate the performance of the system. In order to achieve speech quality assessment, it is necessary to develop effective speech quality assessment method. The perceptive speech quality objective assessment algorithm is the most useful and convenient method. In this paper we will discuss the PESQ (Perceptual Evaluation of Speech Quality) and POLQA (Perceptual objective listening quality assessment) algorithm, which are the latest ITU standard for evaluating speech quality for communication systems and networks. POLQA is a technology upgrade covering the latest speech coding and network transport technology, with higher accuracy for 3G, 4G/LTE and VoIP networks. We analyze the performance of POLQA, and make a comparison between POLQA and PESQ. From the result of the experiment data, we can conclude that the POLQA performance is better than the PESQ, and the POLQA will replace the PESQ in the future.
文章引用：肖累累, 张伟伟. 客观语音质量评估算法的研究[J]. 无线通信, 2013, 3(6): 149-154. http://dx.doi.org/10.12677/HJWC.2013.36024

参考文献

[1] Shaikh, J., Fiedler, M. and Collange, D. (2010) Quality of Experience from user and network perspectives. Annals of Tele- communications, 65, 47-57.
[2] Jelassi, S., Rubino, G., Melvin, H., Youssef, H. and Pujolle, G. (2012) Assessing the quality of voice communications over internet backbones. IEEE Communications Surveys & Tutorials, 14, 1.
[3] Taal, C.H., Hendriks, R.C., Heusdens, R. and Jensen, J. (2011) An algorithm for intelligibility prediction of time-frequency weighted noisy speech. IEEE Transactions on Audio, Speech, and Language Processing, 19, 2125-2136.
[4] Mowlaee, P., Saeidi, R., Christensen, M.G. and Martin, R. (2012) Subjective and objective quality assessment of single-channel speech separation algorithms. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, 25-30 March 2012, 69-72.
[5] Rix, A.W., Beerends, J.G., Kim, D.-S., Kroon, P. and Ghitza, O. (2006) Objective assessment of speech and audio quality— Technology and applications. IEEE Transactions on Audio, Speech, and Language Processing, 14, 1890-1901.
[6] Ma, J. and Loizou, P.C. (2011) SNR loss: A new objective measure for predicting the intelligibility of noise-suppressed speech. Speech Communication, 53, 340-354.
[7] Brooks, P. and Hestnes, B. (2010) User measures of quality of experience: Why being objective and quantitative is important. IEEE Network, 24, 8-13.
[8] ITU-T Recommendation P.862 (2001) Perceptual evaluation of speech quality (PESQ), an objective method for end-to-end speech quality assessment of narrowband telephone networks and speech codecs. International Telecommunication Union, Ge- neva.
[9] Chen, W.-E. (2011) Real-time VoIP quality measurement for mobile devices. IEEE Systems Journal, 5, 538-544.
[10] ITU-T Study Group 12 (2008) PESQ limitations for EVRC family of narrowband and wideband speech codecs. Qualcomm Inc., San Diego.
[11] ITU-T Recommendation P.863 (2011) Perceptual objective listen- ing quality assessment (POLQA). International Telecommuni- cation Union, Geneva.
[12] ITU-T Recommendation P.800 (1996) Methods for subjective determination of transmission quality. International Telecom- munication Union, Geneva.
[13] Zhang, W., Chang, Y., Liu, Y., et al. (2013) A new method of objective speech quality assessment in communication system. Journal of Multimedia, 8, 291-298.
[14] ITU-T Rec. P.862.1 (2003) Mapping function for transforming P.862 raw result scores to MOS-LQO. International Telecom- munication Union, Geneva.
[15] ITU-T Recommendation P.1401 (2012) Methods, metrics and procedures for statistical evaluation, qualification and compare- son of objective quality prediction models. International Tele- communication Union, Geneva.