Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
  • 搜尋 TDR
  • 授權 Q&A
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 電機資訊學院
  3. 電機工程學系
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/20601
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor鄭士康(Shyh-Kang Jeng)
dc.contributor.authorPing-Chang(Andy) Chungen
dc.contributor.author鍾秉璋zh_TW
dc.date.accessioned2021-06-08T02:54:54Z-
dc.date.copyright2017-08-20
dc.date.issued2017
dc.date.submitted2017-08-07
dc.identifier.citation[1] D. Wang, “Primitive auditory segregation based on oscillatory correlation,” Cognitive Science, vol. 20, no. 3, pp. 409–456, 1996.
[2] A. S. Bregman, Auditory scene analysis. The Perceptual Organization of Sound. Cambridge, MA: MIT Press, 1990.
[3] C. Von Der Malsburg, “The correlation theory of brain function.,” Models of neural networks II, no. July 1981, pp. 1–26, 1994.
[4] C. von der Malsburg and W. Schneider, “A neural cocktail-party processor,” Biological Cybernetics, vol. 54, no. 1, pp. 29–40, 1986.
[5] C. Eliasmith, How to Build a Brain : A Neural Architecture for Biological Cognition. Oxford University Press, 2013.
[6] T. W. Parsons, “Separation of speech from interfering speech by means of harmonic selection,” The Journal of the Acoustical Society of America, vol. 60, p. 911, 1976.
[7] M. Weintraub, “A computational model for separating two simultaneous talkers,” Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP ’86. (Volume:11 ), pp. 81–84, 1986.
[8] D. Mellinger, “Event formation and separation in musical sound,” Department of Music, Center for Computer Research in Music and Acoustics, vol. Ph.D., p. 244, 1991.
[9] G. J. Brown and M. Cooke, “Computational Auditory Scene Analysis,” Computer Speech & Language, vol. 8, no. 4, pp. 297–336, 1994.
[10] D. P. W. Ellis, “Prediction-driven computational auditory scene analysis,” hons) Engineering Cambridge University S.M. Electrical Engineering Massachusetts Institute of Technology, 1987.
[11] H. T. Kunio Kashino, Kazuhiro Nakadai, Tomoyoshi Kinoshita, “Application of Bayesian Probability Network to Music Scene Analysis,” Computational auditory scene analysis, no. November 1995, pp. 115–137, 1998.
[12] D. Terman and D. Wang, “Global competition and cooperation in a network of neural oscillator,” Physica D, vol. 81, pp. 148–176, 1995.
[13] D. Wang, “Auditory stream segregation based on oscillatory correlation,” Proceedings of IEEE Conference on Neural Networks for Signal Processing, pp. 624–632, 1994.
[14] D. Wang and D. Terman, “Locally Excitatory Globally Inhibitory Oscillator Networks,” IEEE Transactions on Neural Networks, vol. 6, no. 1, pp. 283–286, 1995.
[15] D. L. Wang and G. J. Brown, “Separation of speech from interfering sounds based on oscillatory correlation,” IEEE Transactions on Neural Networks, vol. 10, no. 3, pp. 684–697, 1999.
[16] S. R. Campbell, D. L. Wang, and C. Jayaprakash, “Synchrony and desynchrony in integrate-and-fire oscillators.,” Neural Comput, vol. 11, no. 7, pp. 1595–1619, 1999.
[17] A. J. W. Van Der Kouwe, D. L. Wang, and G. J. Brown, “A comparison of auditory and blind separation techniques for speech segregation,” IEEE Transactions on Speech and Audio Processing, vol. 9, no. 3, pp. 189–195, 2001.
[18] J. J. Fox, C. Jayaprakash, D. Wang, and S. R. Campbell, “Synchronization in relaxation oscillator networks with conduction delays.,” Neural computation, vol. 13, pp. 1003–1021, 2001.
[19] G. J. Brown and J. Barker, “A neural oscillator sound separator for missing data speech recognition,” IJCNN’01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222), pp. 2907–2912, 2001.
[20] C. Eliasmith and C. H. Anderson, Neural engineering: Computation, resentation and dynamics in neurobiological systems. Cambridge,MA: The MIT Press, 2002.
[21] L. P. A. S. van Noorden, “Temporal coherence in the perception of tone sequences,” Uma ética para quantos?, vol. XXXIII, no. 2, pp. 81–87, 2014.
[22] S. McAdams and A. S. Bregman, “Hearing Musical Streams,” Computer Music Journal, vol. 3, no. 4, pp. 26–43, 1979.
[23] B. van der Pol, “LXXXVIII. On ‘relaxation-oscillations,’” The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science, vol. 2, no. 11, pp. 978–992, 1926.
[24] D. Somers and N. Kopell, “Rapid synchronization through fast threshold modulation,” Biological Cybernetics, vol. 68, no. 5, pp. 393–407, 1993.
[25] C. Morris and H. Lecar, “Voltage oscillations in the barnacle giant muscle fiber,” Biophysical Journal, vol. 35, no. 1, pp. 193–213, 1981.
[26] H. R. Wilson and J. D. Cowan, “Excitatory and Inhibitory Interactions in Localized Populations of Model Neurons,” Biophysical Journal, vol. 12, no. 1, pp. 1–24, 1972.
[27] D. L. Wang and D. Terman, “Image segmentation based on oscillatory correlation,” Neural Computation, vol. 9, no. 4, pp. 805–836, 1997.
[28] G. J. Brown and D. W. D. Wang, “Modelling the Perceptual Separation of Concurrent Vowels with a Network of Neural Oscillators,” Proceedings of International Conference on Neural Networks (ICNN’97), vol. 1, no. 9, pp. 1547–1558, 1997.
[29] K. Chen and D. Wang, “A dynamically coupled neural oscillator network for image segmentation,” Neural Networks, vol. 15, no. 3, pp. 423–439, 2002.
[30] G. J. Brown and D. Wang, “Modelling the perceptual segregation of double vowels with a network of neural oscillators,” Neural Networks, vol. 10, no. 9, pp. 1547–1558, 1997.
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/20601-
dc.description.abstractIn this thesis, we proposed a novel unsupervised oscillatory neural network model for the segregation of auditory signals. The proposed model is inspired by the Locally Excitatory Globally Inhibitory Oscillator Networks (LEGION) model presented in [1]. It consists of relaxation oscillators and a global inhibitor to mimic the neural oscillation. In order to maximize the model’s biological plausibility, we built the proposed model within Nengo (Neural Engineering Object), which is a Python neural simulator based upon the Neural Engineering Framework (NEF). At the end, our model is able to recognize the number of sound sources by analyzing a given correlogram. To ensure the correctness of the simulation results and to observe the proposed model’s cognitive process in the biological substrate, we also compare the simulation results of the proposed model with the ones of Wang’s LEGION model, which we built in MATLAB (Matrix Laboratory).en
dc.description.provenanceMade available in DSpace on 2021-06-08T02:54:54Z (GMT). No. of bitstreams: 1
ntu-106-R04921001-1.pdf: 4400764 bytes, checksum: 81b05ffa0aa18025a5a8c5ef8ec7b817 (MD5)
Previous issue date: 2017
en
dc.description.tableofcontents口試委員會審定書 #
ACKNOWLEDGMENTS i
中文摘要 iii
ABSTRACT iv
CONTENTS v
LIST OF FIGURES vii
Chapter 1 Introduction 1
1.1 Motivation and Objectives 1
1.2 Literature Survey 2
Chapter 2 Background Knowledge 5
2.1 “Auditory Streaming” Phenomenon 5
2.2 Principles of Grouping 6
2.2.1 Proximity 6
2.2.2 Common Fate 8
2.3 Schematic Diagram of Wang’s Model 8
2.4 Relaxation Oscillators 9
2.5 LEGION Model Architecture 11
2.6 Runge-Kutta Method 16
Chapter 3 System Architecture in Nengo 18
3.1 Local Oscillator 18
3.2 Globally Inhibitor 19
3.3 The Proposed LEGION Model 21
3.4 Wang’s LEGION Model in Nengo 22
Chapter 4 Simulation Results and Expected Results 25
4.1 Single Relaxation Oscillator 25
4.2 One-dimensional LEGION model 30
4.3 Two-dimensional LEGION model 32
4.3.1 Demonstration of Proximity 33
4.3.2 Demonstration of Common Fate 35
4.3.3 Simulation Result of Wang’s LEGION model in Nengo 37
4.4 Mixture of Sounds 39
Chapter 5 Conclusion 43
REFERENCE 44
Appendix 48
System Architecture in MATLAB 48
dc.language.isoen
dc.titleNengo Implementation of an Unsupervised Oscillatory Neural Network for the Segregation of Auditory Signalszh_TW
dc.typeThesis
dc.date.schoolyear105-2
dc.description.degree碩士
dc.contributor.oralexamcommittee張智星(Jyh-Shing Roger Jang),劉奕汶(Yi-Wen Liu)
dc.subject.keyword類神經網路,zh_TW
dc.subject.keywordLEGION,oscillatory correlation,en
dc.relation.page50
dc.identifier.doi10.6342/NTU201702562
dc.rights.note未授權
dc.date.accepted2017-08-08
dc.contributor.author-college電機資訊學院zh_TW
dc.contributor.author-dept電機工程學研究所zh_TW
顯示於系所單位:電機工程學系

文件中的檔案:
檔案 大小格式 
ntu-106-1.pdf
  目前未授權公開取用
4.3 MBAdobe PDF
顯示文件簡單紀錄


系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved