计算机科学 ›› 2016, Vol. 43 ›› Issue (9): 310-314.doi: 10.11896/j.issn.1002-137X.2016.09.062
张爱英,倪崇嘉
ZHANG Ai-ying and NI Chong-jia
摘要： 随着监控系统中音频传感器应用的与日俱增,音频事件检测与分类已成为一个重要的研究课题。音频系统所处的音频环境(不同场所、不同噪声)非常复杂,以致检测与分类音频事件异常困难。因此,进行背景模型自适应从而适应不断变化的音频环境变得十分重要。提出了利用受限的最大似然线性回归方法对背景模型进行自适应。采用实际监控场景中的音频数据和模拟录制数据,研究了背景模型自适应方法以及如何有效地进行背景模型自适应。实验结果表明背景模型自适应可以提高目标声音事件的检测性能,减少系统误报。
| [1] Wang D L,Brown G J.Computational Auditory Scene Analysis:Principles,Algorithms,and Applications [M].Wiley-IEEE Press,2006 [2] Espi M, Fujimoto M, Kinoshita K, et al.Feature ExtractionStrategies in Deep Learning Based Acoustic Event Detection [C]∥INTERSPEECH.2015:2922-2926 [3] Plinge A,Grzeszick R,Fink G A.A Bag-of-Features Approach to Acoustic Event Detection [C]∥2014 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).2014:3704-3708 [4] Phan H,Maab M,Mazur R,et al.Random Regression Forestsfor Acoustic Event Detection and Classification [J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2015,23(1):20-31 [5] Parascandolo G, Huttunen H, Virtanen T.Recurrent NeuralNetworks for Polyphonic Sound Event Detection in Real Life Recordings [C]∥2016 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).2016:6440-6444 [6] Lim H,Kim M J,Kim H.Cross-Acoustic Transfer Learning for Sound Event Classification [M]∥2016 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).2016:2504-2508 [7] Atrey P K,Maddage N C,Kankanhalli M S.Audio based Event Detection for Multimedia Surveillance [C]∥IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).2006:813-816 [8] Zhuang X,Zhou X,Hasegawa-Hohnson M,et al.Real-world Acoustic Event Detection [J].Pattern Recognition Letter,2010,1(12):1543-1551 [9] Zhang A Y.Using Hierarchical Method to Improve Real Time for Audio-based Surveillance System [C]∥International Symposim on Chinese Spoken Language Processing (ISCSLP).2014:570-573 [10] Rabaoui A,Davy M,Rossignol S,et al.Using One-Class SVM and Wavelets for Audio Surveillance [J].IEEE Trans.on Information Forensics and Security,2008,3(4):763-775 [11] Angel D L T,Peinado A M,Segura J C,et al.Histogram Equalization of Speech Representation for Robust Speech Recognition [J].IEEE Trans.on Speech and Audio Processing,2005,13(3):355-366 [12] Lee C H,Lin C H,Juang B H.A Study on Speaker Adaptation of Parameters of Continuous Density Hidden Markov Models [J].IEEE Trans.on Signal Processing,1991,39(4):806-814 [13] Kaltenmeier A,Regel P,Trottler K.Fast Speaker Adaptationfor Speech Recognition Systems [C]∥IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).1990:133-136 [14] Legetter C,Woodland P.Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models [J].Computer Speech and Language,1995,9(2):171-185 [15] Povey D,Yao K.A Basis Method of Robust Estimation of Constrained MLLR [C]∥IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).2011:4460-4463 [16] Ntalampiras S,Potamitis I,Fakotakis N.An Adaptive Frame-work for Acoustic Monitoring of Potential Hazards [J].EURASIP Journal on Audio,Speech,and Music Processing,2009,0:1-15 [17] Kryze D,Rigazio L,Junqua J C.A New Noise-Robust Subband Front-End and Its Comparison To PLP [J].J.Chem.educ,2000,1(15):269 [18] Young S,Evermann G,Gales M,et al.The HTK Book .http://htk.eng.cam.ac.uk/docs/docs.shtml |
| No related articles found! |
|
||
首页