考虑包内容特性的网络语音质量评价模型

doi:10.3969/j.issn.1001-2400.2011.02.005

J4 ›› 2011, Vol. 38 ›› Issue (2): 23-28+98.doi: 10.3969/j.issn.1001-2400.2011.02.005

考虑包内容特性的网络语音质量评价模型

李维;杨付正

(西安电子科技大学综合业务网理论及关键技术国家重点实验室，陕西西安 710071)

收稿日期:2010-06-30 出版日期:2011-04-20 发布日期:2011-05-26
通讯作者: 李维
作者简介:李维(1985-)，女，西安电子科技大学博士研究生，E-mail: wli1@mail.xidian.edu.cn．
基金资助:
国家自然科学基金资助项目(60902081,61072102);中央高校基本科研业务费资助项目(K50510010021);国际科技合作计划资助项目(2010DFB10570)

No-reference quality assessment model for networked speech based on the content feature of packets

LI Wei;YANG Fuzheng

(State Key Lab. of Integrated Service Networks, Xidian Univ., Xi'an 710071， China)

Received:2010-06-30 Online:2011-04-20 Published:2011-05-26
Contact: LI Wei

摘要/Abstract

摘要：

丢包是引起网络语音质量下降的主要因素，其影响程度不仅与丢失包的个数有关，而且与丢失包的内容特性有关．考虑丢失包的内容特性，提出了一种无参考的网络语音质量评价模型．首先，利用话音激活检测技术和未丢帧的电平来判断丢失包的内容特性，然后统计语音包的丢失率，进而提出一种无参考的网络语音质量评价模型来预测网络失真语音质量．实验结果表明，相比于国际标准G.1070中的语音质量评价模型，无参考的网络语音质量评价模型与主观质量评价的相关性平均提高了8.4%．

关键词: 语音质量, 语音质量评价, 包丢失, 包内容特性

Abstract:

Packet loss is a primary element to impair the quality of network speech, and the impairment extent is related not only to the number of lost packets, but also to their content feature. This paper proposes a no-reference quality assessment model for networked speech based on analysis of the content feature of packets. This model first estimates the content feature of lost packets by resorting to the voice active detection technology and the level of non-lost frame. Based on the content feature analysis, the proposed model calculates the speech packet loss rate and then predicts the quality of networked speech. Experimental results show that high prediction accuracy can be obtained by the proposed model. Compared with the speech quality evaluation model in G.1070, the average performance gain of the proposed model is raised 8.4% in terms of relativity to subjective results.

Key words: speech quality, speech quality assessment, packet loss, content feature of packets

中图分类号:

TN912

李维;杨付正. 考虑包内容特性的网络语音质量评价模型[J]. J4, 2011, 38(2): 23-28+98.

LI Wei;YANG Fuzheng. No-reference quality assessment model for networked speech based on the content feature of packets[J]. J4, 2011, 38(2): 23-28+98.

参考文献

［1］杨付正, 万帅, 常义林. 基于图像内容失真的全参考视频质量评估方法［J］. 西安电子科技大学学报, 2005, 32(6): 869-872.
Yang Fuzheng, Wan Shuai, Chang Yilin. Full-reference Video Quality Assessment Method Based on the Distortion of Image Content ［J］. Journal of Xidian University, 2005, 32(6): 869-872.
［2］陈国, 胡修林, 张蕴玉. 语音质量客观评价方法研究进展［J］. 电子学报, 2001, 29(4): 548-549.
Chen Guo, Hu Xiulin, Zhang Yunyu. Research Advance on Objective Measures of Speech Quality ［J］. Acta Electronica Sinica, 2001, 29(4): 548-549.
［3］ Cole R G, Rosenbluth J H. Voice Over IP Performance Monitoring ［J］. ACM SIGCOMM Computer Communication Review, 2001, 31(2): 9-24.
［4］ ITU-T Rec. P.800. Methods for Subjective Determination of Transmission Quality ［DB/OL］. ［2010-05-10］. http://www.itu.int/int-t/recommendations/index.aspx?ser=P.
［5］ Moller S, Raake A. Telephone Speech Quality Prediction: towards Network Planning and Monitoring Models for Modern Network Scenarios ［J］. Speech Communication, 2002, 38 (1-2): 47-75.
［6］ ITU-T Rec. P.862. Perceptual Evaluation of Speech Quality (PESQ): an Objective Method for End-to-end Speech Quality Assessment of Narrowband Telephone Networks and Speech Codecs ［DB/OL］. ［2010-05-10］. http://www.itu.int/int-t/recommendations/index.aspx?ser=P.
［7］ ITU-T Rec. G.107. The E-Model, a Computational Model for Use in Transmission Planning ［DB/OL］. ［2010-05-10］. http://www.itu.int/int-t/recommendations/index.aspx?ser=G.
［8］ Lingfen S, Ifeachor E C. Perceived Speech Quality Prediction for Voice over IP-based Network ［C］//IEEE International Communications Conferences. New York: IEEE, 2002: 2573-2577.
［9］ Sun L F, Wade G, Lines B M, et al. Impact of Packet Loss Location on Perceived Speech Quality ［C］//Proceedings of 2nd IP-Telephony Workshop (IPTEL'01). New York: Columbia University, 2001: 114-122.
［10］ Ding L, Lin Z, Radwan A, et al. Non-intrusive Single-ended Speech Quality Assessment in VoIP ［J］. Elsevier Speech Communication Journal, 2007(49): 477-489.
［11］ Jelassi S, Youssef H, Hoene C, et al. Voicing-Aware Parametric Speech Quality Models over VoIP Networks ［C］//Proceedings of 2nd IEEE Global Information Infrastructure Symposium (GIIS 2009). Hammamet: IEEE, 2009: 23-26.
［12］ ITU-T Recommendation G.1070. Opinion Model for Video-telephony Applications ［DB/OL］. ［2010-05-10］. http://www.itu.int/int-t/recommendations/index.aspx?ser=G.
［13］ 3GPP TS 26.094. AMR Speech Codec; Voice Activity Detector ［DB/OL］. ［2010-05-10］. http://www.3gpp.org/ftp/Specs/archieve/26series/26.094/.
［14］ ITU-T Recommendation P.833. Methodology for Derivation of Equipment Impairment Factors from Subjective Listening-only Tests ［DB/OL］. ［2010-05-10］. http://www.itu.int/int-t/recommendations/index.aspx?ser=P.
［15］ 3GPP TS 26.090. AMR Speech Codec; Speech transcoding ［DB/OL］. ［2010-05-10］. http://www.3gpp.org/ftp/Specs/archieve/26series/26.900/.
［16］ Gilbert E N. Capacity of a Burst-noise Channel ［J］. Bell System Technical Journal, 1960, 39(9): 1253-1265.

考虑包内容特性的网络语音质量评价模型

No-reference quality assessment model for networked speech based on the content feature of packets

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

Metrics

本文评价

推荐阅读 0