南京大学学报(自然科学版) ›› 2021, Vol. 57 ›› Issue (5): 875880.doi: 10.13232/j.cnki.jnju.2021.05.019
• • 上一篇
Lifu Wu1,2(), Guangshen Ji1, Qiucen Hu1
摘要:
强混响环境下的话者数量是语音处理应用中的关键信息.以不同话者语音之间的频域幅度平方相干(Magnitude Squared Coherence,MSC)为特征进行话者计数,首先提取语音中的短时频域MSC特征,再采用K?medoids算法对其进行聚类得到话者个数.该方法无需麦克风间距和话者到麦克风之间相对距离的先验信息.不同混响条件、不同信噪比和不同麦克风间距的实验结果表明,频域MSC特征与话者是相干的,与基于广义互相关相位变换(Generalized Cross?Correlation Phase Transform,GCC?PHAT)的到达时间差方法(Time Difference of Arrival,TDOA)相比,本方法的话者计数准确率更高,对麦克风间距的敏感度更低,鲁棒性更优.
中图分类号:
1 | 张雷岳,张兴敢,刘超.麦克风阵列声源定位中时延估计的改进.南京大学学报(自然科学),2015, |
51(1):25-30. (Zhang L Y,Zhang X G,Liu C. The improvement of time delay estimation in the microphone array sound localization system. Journal of Nanjing University(Natural Science),2015,51(1):25-30. ) | |
2 | 滕鹏晓,章林柯,陈日林等.基于双传声器对的多声源二维定位跟踪算法.声学学报,2010,35(2):230-234. |
Teng P X,Zhang L K,Cheng L K,et al.Two?dimensional location and tracking algorithm for multiple sound sources based on dual microphone pairs.Acta Acoustica,2010,35(2):230-234. | |
3 | Blandin C,Ozerov A,Vincent E. Multi?source TDOA estimation in reverberant audio using angular spectra and clustering. Signal Processing,2012,92(8):1950-1960. |
4 | Bertrand A,Moonen M. Energy?based multi?speaker voice activity detection with an ad hoc microphone array∥Acoustics Speech and Signal Processing. Dallas,TX,USA:IEEE Press,2010:85-88. |
5 | 张普芬.基于差分传声器阵列的声源个数估计方法研究.硕士学位论文.南京:南京航空航天大学. 2019. |
Zhang P F. Research on the method of sound source number estimation based on differential microphone array. Master Dissertation. Nanjing:Nanjing University of Aeronautics and Astronautics.2019. | |
6 | Jia M ,Sun J,Bao C. Real?time multiple sound source localization and counting using a soundfield microphone. Journal of Ambient Intelligence & Humanized Computing,2017,8(6):829-844. |
7 | Owa Da N,Tsuji D,Suyama K. Stable sound source tracking based on two updating algorithms. Leej Transactions on Electrical & Electronic Engineering,2011,6(1):30-36. |
8 | Pasha S,Donley J, Ritz C, et al. Towards real?time source counting by estimation of coherent?to?diffuse ratios from ad?hoc microphone array recordings∥The 5th Joint Workshop on Hands?free Speech Communication and Microphone Arrays. San Francisco,CA,USA:IEEE Press,2017:161-165. |
9 | Park H S ,Jun C H. A simple and fast algorithm for K?medoids clustering. Expert Systems with Applications,2009,36(2p2):3336-3341. |
10 | 曾晓迪.一种基于K?medoids改进BIRCH的大数据聚类方法——以证券客户大数据为例.硕士学位论文.云南:云南财经大学,2016.Zeng X D. A Big data clustering method based on K?medoids to improve BIRCH:Taking securities customer big data as an example. Master Dissertation. Yunnan:Yunnan University of Finance and Economics,2016. |
11 | Schwarz A ,Kellermann W. Coherent?to?Diffuse Power Ratio Estimation for Dereverberation. IEEE/ACM Transactions on Audio Speech & Language Processing,2015,23(6):1006-1018. |
12 | Preeti,Arora,Deepali,et al. Analysis of K?means and K?medoids algorithm for big data?sciencedirect. Procedia Computer Science,2016:507-512. |
13 | Velmurugan. Computational complexity between K?means and K?medoids clustering algorithms for normal and uniform distributions of data points. Journal of Computer Science,2010,6(3):363-368. |
14 | 程明畅,刘友波,张程嘉等.基于分位数半径的动态K?means算法. 南京大学学报(自然科学),2018, |
54(1):48-55. (Cheng M C,Liu Y B,Zhang C J,et al. Dynamic K?means algorithm based on quantile | |
radius. Journal of Nanjing University(Natural | |
Science),2018,54(1:48-55. | |
15 | Maulik U ,Bandyopadhyay S. Performance evaluation of some clustering algorithms and validity indices. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002. |
16 | Knapp C ,Carter G. The generalized correlation method for estimation of time delay. IEEE Transactions on Acoustics Speech & Signal Processing,2003,24(4):320-327. |
17 | Brandstein M S ,Silverman H F. A robust method for speech signal time?delay estimation in reverberant rooms∥IEEE International Conference on Acoustics,Speech and Signal Processing. Munich Germany,Germany:IEEE Press,1997:375-378. |
[1] | 蔡宗义*,许学忠,梁旭斌,赵天青,成龙,孙迪峰. 一种水上落点定位方法研究[J]. 南京大学学报(自然科学版), 2015, 51(7): 27-. |
|