G.729 코덱의 패킷 손실 영향 모델을 이용한 비 침입적 음질 예측 기법 = Non-Intrusive Speech Quality Estimation of G.729 Codec using a Packet Loss Effect Model

국문 초록 (Abstract)

본 논문은 패킷 손실의 영향을 이용한 비 침입적 음질 평가 방법을 제안한다. 패킷 손실은 패킷 기반의 통신 시스템에서 음질을 저하시키는 주된 요소이며 그 영향은 코덱에 내장된 패킷 손실 은닉 알고리듬에 의해 결정된다. 패킷 손실 영향을 반영한 음질평가 시스템을 위해 VoIP 에서 협대역 코덱으로 사용되는 코덱 중 하나인 G.729를 선택하였으며, 음성 특징에 따른 패킷 손실 영향을 구분하기 위해서 G.729 코덱의 음성 파라미터를 이용한 한 음성 특성 분류기를 설계하였다. 이후, 각각의 패킷 특성에 따른 음질 저하의 정도를 수치화하기 위해 원 PESQ-LQ점수와 상관계수를 최대화하는 음질 저하 가중치를 반복적으로 구하였으며, 최종 음질 저하는 가중합으로 구하였다. 그 결과 제안한 모델과 PESQ-LQ의 상관계수는 칩입 모델 에서는 0.8950를, 비 침입 모델 에서는 0.8911의 결과를 나타내었다.

다국어 초록 (Multilingual Abstract)

This paper proposes a non-intrusive speech quality estimation method considering the effects of packet loss to perceptual quality. Packet loss is a major reason of quality degradation in a packet based speech communications network, whose effects are different according to the input speech characteristics or the performance of the embedded packet loss concealment (PLC) algorithm. For the quality estimation system that involves packet loss effects, we first observe the packet loss of G.729 codec which is one of narrowband codec in VoIP system. In order to quantify the lost packet affects, we design a classification algorithm only using speech parameters of G.729 decoder. Then, the degradation values of each class are iteratively selected that maximizes the correlation with the degradation PESQ-LQ scores, and total quality degradation is modeled by the weighted sum. From analyzing the correlation measures, we obtained correlation values of 0.8950 for the intrusive model and 0.8911 for the non-intrusive method.

참고문헌 (Reference)

1 S. R. Broom, "VoIP quality assessment : taking account of the edge-device" 14 : 1977-1983, 2006

2 ITU-T Recommendation G.107, "The E-model : A Computational Model for Use in Transmission Planning"

3 M. K. Lee., "Speech quality estimation using packet loss effects in CELP-type speech coders" 1697-1700, 2007

4 ITU-T Recommendation P. 563, "Single-Ended Method for Objective Speech Quality in Narrowband Telephony Applications"

5 3GPP2 C.S0030-0 Ver 3.0, "Selectable Mode Vocoder (SMV) Service Option for Wideband Spread Spectrum Communication Systems"

6 ITU-T Recommendation P.863, "Perceptual Objective Listening Quality Assessment"

7 ITU-T Recommendation P.862, "Perceptual Evaluation of Speech Quality (PESQ) : An Objective Method for End-To- End Speech Quality Assessment of Narrow-Band Telephone Networks and Speech Codecs"

8 L. Sun., "Perceived speech quality prediction for voice over IP-based networks" 2573-2577, 2002

9 A. W. Rix., "Objective Assessment of Speech and Audio Quality Technology and Applications" 14 : 1890-1901, 2006

10 L. Ding., "Non-intrusive single-ended speech quality assessment in VoIP" 49 : 477-489, 2007

11 "Multi-Lingual Speech Database for Telephonometry"

12 ITU-T Recommendation P. 862.1, "Mapping Function for Transforming P. 862 Raw Result Score to MOS-LQO"

13 ITU-T Recommendation P.Sup23, "ITU-T Coded Speech Database"

14 A. M. Kondoz, "Digital Speech; Coding for Low Bit Rate Communication Systems" John Wiley & Sons 1994

15 ITU-T Recommendation G.729, "Coding of Speech at 8kbit/s using Conjugate-Structure Algebraic Code-Excited Linear Prediction (CS-ACELP)"