Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/16682Full metadata record
| ???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
|---|---|---|
| dc.contributor.advisor | 陳宏銘 | |
| dc.contributor.author | Yu-An Chen | en |
| dc.contributor.author | 陳昱安 | zh_TW |
| dc.date.accessioned | 2021-06-07T23:43:32Z | - |
| dc.date.copyright | 2014-08-21 | |
| dc.date.issued | 2014 | |
| dc.date.submitted | 2014-07-17 | |
| dc.identifier.citation | [1] C. M. Bishop, Pattern Recognition and Machine Learning, Springer-Verlag, New York, Inc., 2006.
[2] C. Chesta, O. Siohan, and C.-H. Lee. “Maximum a posteriori linear regression for hidden Markov model adaptation,” in Proc. Eurospeech, 1999. [3] M. Gales, “Maximum likelihood linear transformations for hmm-based speech recognition,” Computer Speech and Language, vol. 12, pp. 75–98, 1998. [4] A. Gabrielsson, “Emotion perceived and emotion felt: Same or different?” Musicae Scientiae, pp. 123–147, 2002. [5] J. Gauvain and C.-H. Lee, “Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains,” IEEE Trans. Speech and Audio Processing, vol. 2, pp. 291–298, 1994. [6] B. J. Han, S. Rho, S. Jun, and E. Hwang, “Music emotion classification and context-based music recommendation,” in Multimedia Tools and Applications, vol. 47, issue 3, pp. 433-460, 2010. [7] J. Hershey and P. Olsen, “Approximating the Kullback-Leibler divergence between Gaussian mixture models,” in Proc. Int. Conf. Acoustic, Speech, and Signal Processing, vol. 4, 2007, pp. 317–320. [8] D. Huron, Sweet Anticipation: Music and the Psychology of Expectation, MIT Press, Cambridge, Massachusetts, 2006. [9] X. Hu, J. S. Downie, C. Laurier, M. Bay, and A. F. Ehmann, “The 2007 MIREX audio mood classification task: Lessons learned,” in Proc. Int. Society Music Information Retrieval Conf., 2008. [10] Y. E. Kim, E. M. Schmidt, R. Migneco, B. G. Morton, P. Richardson, J. J. Scott, J. A. Speck, and D. Turnbull, “Mu-sic emotion recognition: A state of the art review,” in Proc. Int. Society Music Information Retrieval Conf., 2010, pp. 255–266. [11] S. Koelstra, C. M‥uhl, M. Soleymani, J.-S. Lee, A. Yazdani, T. Ebrahimi, T. Pun, A. Nijholt, and I. Patras, “DEAP: A database for emotion analysis; using physiological signals,” IEEE Trans. Affective Computing, vol. 3, no. 1, pp. 18–31, 2012. [12] O. Lartillot and P. Toiviainen, “A Matlab toolbox for musical feature extraction from audio,” in Proc. Int. Conf. Digi-tal Audio Effects, 2007. [13] C. J. Leggetter and P. C. Woodland, “Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models,” Computer speech and lan-guage, vol. 9, no. 2, p. 171, 1995. [14] D. A. Reynolds, T. F. Quatieri, and R. B. Dunn, “Speaker verification using adapted Gaussian mixture models,” Digital Signal Processing, vol. 10, no. 1-3, pp. 19–41, 2000. [15] J. A. Russell, “A circumplex model of affect,” J. Personality and Social Science, vol. 39, no. 6, pp. 1161–1178, 1980. [16] E. M. Schmidt and Y. E. Kim, “Prediction of time-varying musical mood distributions from audio,” in Proc. Int. Society Music Information Retrieval Conf., 2010. [17] E. M. Schmidt, and Y. E. Kim, “Prediction of time-varying musical mood distributions using Kalman filtering,” in Proc. Int. Conf. Machine Learning and Applications, 2010, pp. 655-660. [18] M. Riley, E. Heinen, and J. Ghosh, “A text retrieval approach to content-based audio retrieval,” in Int. Symp. on Music Information Retrieval, 2008, pp. 295-300. [19] G. Salton, A. Wong, and C.-S. Yang. 'A vector space model for automatic indexing.' Communications of the ACM, vol. 18, no. 11, pp. 613-620, 1975. [20] D. Su and P. Fung, “Personalized music emotion classification via active learning,” in Proc. ACM Workshop Music Information Retrieval with User-centered and Multimodal Strategies, 2012. [21] [online] http://www.allmusic.com/moods [22] J.-C. Wang, Y.-H. Yang, H.-M. Wang, and S.-K. Jeng, “The acoustic emotion Gaussians model for emotion-based music annotation and retrieval,” in Proc. ACM Multimedia, pp. 89–98, 2012. [23] J.-C. Wang, Y.-H. Yang, H.-M. Wang, and S.-K. Jeng, “Personalized music emotion recognition via model adaptation,” in Proc. Asia-Pacific Signal and Information Processing Association Annu. Summit and Conference, 2012. [24] J.-C. Wang, Y.-H. Yang, K. Chang, H.-M. Wang, and S.-K. Jeng, “Exploring the relationship between categorical and dimensional emotion semantics of music,” in Proc. ACM Workshop Music Information Retrieval with User-centered and Multimodal Strategies, 2012, pp. 63–68. [25] Y.-H. Yang, Y.-F. Su, Y.-C. Lin, and H. H. Chen, “Music emotion recognition: The role of individuality,' in Proc. ACM Int. Workshop Human-centered Multimedia, 2007. [26] Y.-H. Yang, Y.-C. Lin, and H. H. Chen, “Personalized music emotion recognition,” in Proc. ACM Special Interest Group Information Retrieval Conf., 2009, pp. 748–749. [27] Y.-H. Yang and H. H. Chen, “Predicting the distribution of perceived emotions of a music signal for content retrieval,” IEEE Trans. Audio, Speech, and Language Processing, vol. 19, no. 7, pp. 2184–2196, 2011. [28] Y.-H. Yang and H. H. Chen, Music Emotion Recognition, CRC Press, 2011. [29] C.-C. Yeh, S.-S. Tseng, P.-C. Tsai, and J.-F. Weng, “Building a personalized music emotion prediction system.” in Proc. Pacific-Rim Conf. Multimedia, 2006, pp. 730–739. [30] B. Zhu and T. Liu, “Research on emotional vocabulary-driven personalized music retrieval,” in Edutainment, 2008, pp. 252–261. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/16682 | - |
| dc.description.abstract | 情緒在人聆聽音樂的經驗中是不可或缺的要素，因此，自動化的音樂情緒辨識是音樂資訊檢索的一個重要研究分支。由於音樂情緒的感知在本質上是非常主觀的，要能夠有效提升辨識結果的可靠度，針對音樂情緒辨識進行個人化被廣泛認為是不可或缺的一環。然而，音樂情緒辨識的個人化通常需要使用者提供大量的音樂情緒標註才能夠出現成效，實際應用上飽受侷限。因此，本論文提出一個基於線性迴歸的音樂情緒辨識模型個人化方法，該方法採用漸進式學習的方式，只需要少量的使用者標註就可以產生成效。更進一步的，本論文探索了不同模型參數類聚的策略，以同時調整數個高度相關的模型參數，強化從既有標註中學習的能力。實驗結果顯示本論文所提出的個人化方法能夠有效地提升音樂情緒辨識模型的準確度，也映證了所提出的模型參數類聚策略的可靠度。 | zh_TW |
| dc.description.abstract | Personalization techniques can be applied to address the subjectivity issue of music emotion recognition, which is important for music information retrieval. However,
achieving satisfactory accuracy in personalized music emotion recognition for a user is difficult because it requires an impractically huge amount of annotations from the user. In this thesis, a linear regression based method is proposed to personalize a music emotion model in an online learning fashion. In addition, two parameter tying strategies are employed to improve the efficiency of personalization by modifying closely related model parameters together. An empirical justification of the design of parameter tying strategies are given, and comprehensive experiments conducted on several datasets showed the effectiveness of the proposed method. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-07T23:43:32Z (GMT). No. of bitstreams: 1 ntu-103-R01942128-1.pdf: 1174607 bytes, checksum: 0059cf49ccc62da79439693a1200a2a4 (MD5) Previous issue date: 2014 | en |
| dc.description.tableofcontents | 誌謝 i
摘要 ii ABSTRACT iii CONTENTS iv LIST OF FIGURES vi LIST OF TABLES vii Chapter 1 Introduction 1 Chapter 2 Related Work 3 2.1 Personalized music emotion recognition 3 2.2 Speaker adaptation of speech recognition 4 Chapter 3 Music Emotion Model 6 3.1 Audio word 7 3.2 Associate audio word with emotion 8 3.3 Prediction of music emotion 8 Chapter 4 Linear Regression for Model Adaptation 9 4.1 Linear regression and parameter tying 9 4.2 MAPLR 10 4.3 Parameter tying strategies 12 Chapter 5 Experiments 14 5.1 Datasets and acoustic features 14 5.2 Justification of parameter tying 16 5.3 Experimental settings and evaluation metrics 18 5.4 Experimental results 20 Chapter 6 Conclusion 28 References 29 | |
| dc.language.iso | en | |
| dc.subject | 個人化 | zh_TW |
| dc.subject | 音樂 | zh_TW |
| dc.subject | 情緒辨識 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 線性迴歸 | zh_TW |
| dc.subject | 模型參數類聚 | zh_TW |
| dc.subject | MAPLR | en |
| dc.subject | parameter tying | en |
| dc.subject | Personalization | en |
| dc.subject | music | en |
| dc.subject | emotion recognition | en |
| dc.subject | machine learning | en |
| dc.title | 基於線性迴歸之個人化音樂情緒辨識 | zh_TW |
| dc.title | Linear Regression-Based Model Adaptation for Personalized Music Emotion Recognition | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 102-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 鄭士康,王新民,蔡振家,楊奕軒 | |
| dc.subject.keyword | 音樂,情緒辨識,個人化,機器學習,線性迴歸,模型參數類聚, | zh_TW |
| dc.subject.keyword | Personalization,music,emotion recognition,machine learning,MAPLR,parameter tying, | en |
| dc.relation.page | 31 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2014-07-17 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
| Appears in Collections: | 電信工程學研究所 | |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ntu-103-1.pdf Restricted Access | 1.15 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.