期刊文献+

非平稳噪声环境下的噪声功率谱估计方法 被引量:7

New Noise Estimation Method for HighlyNon-Stationary Noise Environments
下载PDF
导出
摘要 提出了一种新的非平稳噪声环境下的噪声功率谱估计方法。该方法通过采用非固定长度的时间窗跟踪含噪语音功率谱的最小值,解决了传统跟踪时延较大的问题。不同频带采用不同的阈值计算语音存在概率,从而利用语音存在概率值的大小调节噪声和语音的混合程度。实验证明,本文提出的方法较基于语音活性判决(Voiceactivity detectors,VAD)的一系列方法和传统的最小统计(Minimal statistic,MS)算法有更好的效果,从而有效地改善了增强后语音的质量。 A new noise power spectrum estimation method is introduced for noise estimation in non-stationary noise environment. The noise estimation is realized by averaging past spectral power values and using a smoothing factor adjusted by the signal presence probability in every bins. Presence of speech is determined by the ratio between the energy of the smoothened noisy speech and its minimum. Experiments prove that the proposed method is superior to a series of exsiting methods based on voice activity detectors and the traditional minimal statistic algorithm.
作者 余耀 赵鹤鸣
出处 《数据采集与处理》 CSCD 北大核心 2012年第4期486-489,共4页 Journal of Data Acquisition and Processing
基金 国家自然科学基金(61071215)资助项目 苏州市科技发展计划(SYG201033)资助项目
关键词 噪声估计 语音存在概率 非平稳噪声 noise estimation signal presence probability non-stationary noise
  • 相关文献

参考文献13

  • 1Farsi H. Improvement of minimum tracking in mini- mum statistics noise estimation method [J]. Signal Processing.. An International Journal (SPIJ), 2010, 4(1) ..17-22. 被引量:1
  • 2Rainer M. Noise power spectral density estimation based on optimal smoothing and minimum statistics [J]. IEEE Transactions on Speech and Audio Pro- cessing, 2001,9(5):504-512. 被引量:1
  • 3Li Ye, Wang Tong, Cui Huijuan,et al. Voice activity detection in non-stationary noise[J]. IMACS Multi- conference on Computational Engineering in Systems Application (CESA), 2006 : 1573-1575. 被引量:1
  • 4Cohen I,Berdugo B. Noise estimation by minima con- trolled recursive averaging for robust speech en- hancement [ J]IEEE Signal Processing Letters,2002,9(1): 12-15. 被引量:1
  • 5Erkelens Jan S, Heusdens R. Tracking of non-sta- tionary noise based on data driven recursive noise power estimation[J]. IEEE Transactions on Speech and Audio Processing, 2008,16(6) .. 1112-1123. 被引量:1
  • 6Alan D, Sven N, Roberto T. Statistical voice activity detection using low variance spectrum estimation and an adaptive threshold [J]. IEEE Transactions on Speech and Audio Processing, 2006,14 (2) : 412-424. 被引量:1
  • 7牛铜,张连海,屈丹.基于加权最小统计的噪声谱估计改进算法[J].电子与信息学报,2009,31(5):1166-1169. 被引量:7
  • 8Fukane A R, Sahare S L. Noise estimation algo- rithms for speech enhancement in highly non-station- ary environments [J]. International Journal of Com- puter Science Issues, 2011,8(2) .. 39-44. 被引量:1
  • 9Rangachari S, Loizou P C. A noise-estimation algo- rithm for highly non-stationary environments [J]. Speech Communication, 2006(48) .. 220-231. 被引量:1
  • 10Varga A,Steeneken H J M. Assessment for automat- ic speech recognition :II. NOISEX-92 :a database and an experiment to study the efficet of additive noise on speech recognition systems[J]. Speech Communi- cation, 1993,12(3) ..247-251. 被引量:1

二级参考文献7

  • 1Martin R, Malah D, and Richard V, et al.. A noise reduction preprocessor for mobile voice communication [J]. EURASIP Journal on Applied Signal Processing, 2004, 2004(1): 1046-1058. 被引量:1
  • 2Loizou P C. Speech Enhancement: Theory and Practice [M]. Boca Raton, FL: CRC Press, 2007, Chapter 9. 被引量:1
  • 3Martin R. Noise power spectral density estimation based on optimal smoothing and minimum statistics [J]. IEEE. Trans. on Speech, and Audio Processing, 2001, 9(5): 504-512. 被引量:1
  • 4Hu Y and Loizou P C. Subjective comparison of speech enhancement algorithms [C]. Proceedings of ICASSP-2006, Toulouse, France, May 2006, vol.I: 153-156. 被引量:1
  • 5Hendriks R C, Jensen J, and Heusdens R. DFT Domain subspace based noise tracking for speech enhancement [C]. INTER,SPEECH 2007, Antwerp, Belgium, August 2007: 830-834. 被引量:1
  • 6ITU. Perceptual evaluation of speech quality (PESQ), and objective method for end-to-end speech quality assessment of narrowband telephone networks and speech codes[S]. ITU-T Recommendation P. 862. 2000. 被引量:1
  • 7Hu Y and Loizou P C. Evaluation of objective quality measures for speech enhancement [J]. IEEE Trans. on Audio, Speech, Language Process., 2008, 16(1): 229-238. 被引量:1

共引文献6

同被引文献64

  • 1温书信,潘威炎,张红旗.长波超长波传播色散对通信解码的影响[J].电波科学学报,2004,19(z1):167-169. 被引量:1
  • 2张峰 徐光华 谢俊 等.稳态视觉诱发电位的研究与展望.仪器仪表学报,2010,31(8):156-165. 被引量:4
  • 3高上凯.浅谈脑—机接口的发展现状与挑战[J].中国生物医学工程学报,2007,26(6):801-803. 被引量:70
  • 4赵胜跃,戴蓓蒨.基于最小统计噪声估计的信号子空间语音增强[J].数据采集与处理,2007,22(4):453-457. 被引量:6
  • 5Yuan Wenhao, Lin Jiajun, An Wei, et al. Noise estimation based on time-frequency correlation for speech enhancement[J]. Applied Acoustics, 2013, 74(5): 770-781. 被引量:1
  • 6Zhong L, Rafik A G, Richard M D. Noise estimation using speech/non-speech frame decision and subband spectral tracking[J]. Speech Communication, 2007, 49: 542-557. 被引量:1
  • 7Martin R. Bias compensation methods for minimum statistics noise power spectral density estimation[J]. Signal Processing, 2006, 86: 1215-1229. 被引量:1
  • 8Cohen I. Noise estimation by minima controlled reeursive averaging for robust speech enhancement[J]. IEEE Signal Process Letters, 2002, 9(1):12-15. 被引量:1
  • 9Cohen I. Noise spectrum estimation in adverse environments: Improved minima controlled recursive averaging[J]. IEEE Transaction on Audio, Speech, and Language Processing, 2003, 11(5): 466-475. 被引量:1
  • 10Quoc V Le. Building high-level features using large scale unsupervised learning [C]//Proc ICASSP13. Vancouver, Canada: IEEE Signal Processing Society, 2013: 8595-8598. 被引量:1

引证文献7

二级引证文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部