基于联合语音出现概率的先验信噪比估计算法
doi: 10.3724/SP.J.1146.2006.01927
A Modified a Priori SNR Estimator Based on the United Speech Presence Probabilities
-
摘要: 先验信噪比是语音增强的关键参数。该文分析了几种典型的先验信噪比估计算法,并得到这几种算法的统一形式,最后提出了基于联合语音出现概率的先验信噪比估计算法。测试结果表明,该算法在不引入音乐噪声的同时,平均段信噪比提高和平均对数谱距离等客观评价指标,都优于其它算法。
-
关键词:
- 语音增强; 先验信噪比; 后验信噪比
Abstract: The a priori Signal-to-Noise Ratio (SNR) is the dominant parameter in noise reduction techniques. This paper analyses several typical estimate approaches of the a priori SNR firstly, and then expresses them in the same form, finally presents an improved estimate of the a priori SNR, which is based on the united speech presence probabilities. Simulation results verify that the performance of the proposed estimator is better than those conventional estimators in terms of the segmental SNR and the log-spectral distance. -
Ephraim Y and Malah D. Speech enhancement using aminimum mean-square error short-time spectral amplitudeestimator[J].IEEE Trans. on Acoustics, Speech and SignalProcessing.1984, 32(6):1109-1121[2]Capp O. Elimination of the musical noise phenomenon withthe Ephraim and Malah noise suppressor. IEEE Trans. onSpeech and Audio Processing, 1997, 2(3): 345-349.[3]Cohen I. Relaxed statistical model for speech enhancementand a priori SNR estimation[J].IEEE Trans. on Speech andAudio Processing.2005, 13(5):870-881[4]Plapous C, Marro C, and Scalart P. Improved Signal-to-Noiseratio estimation for speech enhancement[J].IEEE Trans. onSpeech and Audio Processing.2006, 14(6):2098-2108[5]Sohn J, Kim N S, and Sung W. A statistical model-basedvoice activity detector. IEEE Signal Processing Letter, 1999,6(1): 1-3.[6]Cohen I. Noise estimation in adverse environments: improvedminima controlled recursive averaging[J].IEEE Trans. onSpeech and Audio Processing.2003, 11(5):466-475[7]《现代数学应用手册》编委会. 概率统计与随机过程卷(第1版). 北京: 清华大学出版社, 2000, 第15章.[8]Martin R. Noise power spectral density estimation based onoptimal smoothing and minimum statistics[J].IEEE Trans.on Speech Audio Processing.2001, 9(5):504-512[9]Deller J R, Proakis J G, and Hansen J H L. Discrete-TimeProcessing of Speech Signals [M]. New York: MacmillanPublishing Company, 1993: 568-597. -
计量
- 文章访问数: 3559
- HTML全文浏览量: 92
- PDF下载量: 1412
- 被引次数: 0
下载:
