语音评估PESQ介绍new.ppt

PESQ介绍 MOS介绍 MOS: Mean Opinion Score，早期用于评估语音通讯系统的质量，后广泛用于鉴定语音通讯系统中关键技术/器件，如：Vocoder MOS测试中常用的参考系统（Vocoder）：PCM，ADPCM PCM：Pulse Code Modulation， 64Kbps，广泛用于ATM，E1/T1 光纤传输系统，语音质量非常高，通常称为：有线电话质量（Toll Quality） 。 ADPCM：Adaptive Differential Pulse Code Modulation，32Kbps，普遍用于电信，卫星通信，MP3等系统，语音质量高，通常称为：长途 电话质量 MOS评分值的范围为『1，5』 PCM系统的MOS值的范围为『4.2，4.4』 ADPCM系统的MOS值的范围为『4.1，4.3』 PCM/ADPCM 常被用来做为衡量其他Vocoder/通讯系统的参照物。 MOS以及语音评估算法 MOS: Mean Opinion Score MOS评分值的范围为『1，5』 ITU语音评估算法标准有：PAMS、PSQM、PSQM+、MNB、PESQ PESQ是电信/通讯领域中应用最广的技术 不同语音评估算法性能比较-与MOS的相关性对比(1) 不同语音评估算法性能比较-与MOS的相关性对比(2) 不同语音评估算法性能比较-与MOS的相关性对比(3) 不同语音评估算法性能比较-误差统计(4) 结论 PESQ是目前最为先进和准确的语音评估算法； 原来的语音评估算法不适合于测试网络，特别是VoIP网络； 原来的语音评估算法在如下条件方面不能有很好的效果： Speech clipping Background noise Packet loss in VoIP network Filtering in analogue elements (such as handset or 2-wire access loop) Variable delay (common in VoIP) PESQ介绍 PESQ: Perceptual Evaluation of Speech Quality; 国际电联（ITU）P.862推荐的语音评估最新算法，同时也是UMTS评估语音的最新标准； PESQ处理过程1 PESQ处理过程2 Level alignment In order to compare the signals, the reference speech signal and the degraded signal should be at the same, constant power level. Input filtering PESQ models the receive path of the telephone handset using an input filter. This takes account of the effect of the electrical and acoustic components of the handset. Time alignment The system under test may include a delay, which may be variable. In order to compare the reference and degraded signals, they need to be lined up with each other. PESQ处理过程3 Auditory transform In order to compare the reference and degraded signals, taking account of how a listener would have heard them, each is passed through an auditory transform that mimics certain key properties of human hearing. This gives a representation in time and frequency of the perceived loudness of the signal, known as the sensation surface. Disturbance processing The difference between the sensation surfaces for the reference and degraded files is known as the error surface; th