Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/19475
標題: 擴充式離散隱藏式馬可夫模型及其在中文音節辨識上的應用
Extended Discrete Hidden Markov Model and Its Application to Chinese Syllable Recognition
作者: 林耕宇
Lin, Keng-Yu
關鍵字: speech recognition
語音辨識
Chinese syllable recognition
hidden Markov model
vector quantization
中文音節辨識
隱藏式馬可夫模型
向量量化
出版社: 資訊科學系所
引用: [Baker75] James K. Baker, “The Dragon System – An overview,” IEEE Transactions of Acoustics, Speech, and Signal Processing (ASSP), Vol. 23, pp. 24-29, 1975. [Bellegarda89] Jerome R. Bellegarda, David Nahamoo, “Tied Mixture Continuous Parameter Models for Large Vocabulary Isolated Speech Recognition,” Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vol. 2, pp. 13-16, 1989. [Clark95] John Clark, Colin Yallop, “An Introduction to Phonetics and Phonology, 2nd Edition,” Blackwell Publishers, 1995, ISBN 978-0631161813 [Davis80] Steven B. Davis, Paul Mermelstein, “Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences,” IEEE Transactions of Acoustics, Speech, and Signal Processing (ASSP), Vol. 28, No. 4, pp. 357-366. [Huang89] Xuedong Huang, Mervyn A. Jack, “Unified Technique for Vector Quantisation and Hidden Markov Modeling Using Semi-Continuous Models,” Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vol. 1, pp. 639-642, 1989. [Huang90] Xuedong Huang, Kai-Fu Lee, Hsiao-Wuen Hon, “On Semi-Continuous Hidden Markov Modeling,” Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vol. 2, pp. 689-692, 1990. [Huang01] Xuedong Huang, Alex Acero, Hsiao-Wuen Hon, “Spoken Language Processing: A Guide to Theory, Algorithm and System Development, 1st Edition, “Prentice Hall, April 25, 2001, ISBN 978-0130226167. [Jelinek75] Frederick Jelinek, Lalit R. Bahl, Robert L. Mercer, “Design of a Linguistic Statistical Decoder for the Recognition of Continuous Speech,” IEEE Transactions on Information Theory, Vol. 21, Issue 3, pp. 250-256, 1975. [Jelinek97] Frederick Jelinek, “Statistical Methods for Speech Recognition,” MIT Press, 1997, ISBN 0-262-10066-5 [Juang90] Biing-Hwang Juang, Lawrence R. Rabiner, “The Segmental K-Means Algorithm for Estimating Parameters of Hidden Markov Models, “ IEEE Transactions on Acoustics, Speech, and Signal Processing (ASSP), Vol. 38, No. 9, pp. 1639-1641, 1990. [Jurafsky06] Daniel Jurafsky, James H. Martin, “Speech and Language Processing, 2nd Edition(Draft),” Prentice Hall, December 1, 2006, ISBN 978-0131873216. [Levinson05] Stephen E. Levinson, “Mathematical Models for Speech Technology,” John Wiley & Sons, Ltd, 2005, ISBN 0-470-84407-8 [Lévy03] Christophe Lévy, Georges Linarés, Pascal Nocera, “Comparison of Several Acoustic Modeling Techniques and Decoding Algorithms for Embedded Speech Recognition Systems,” Workshop on DSP in Mobile and Vehicular Systems, Nagoya, 2003. [Linde80] Yoseph Linde, Andrés Buzo, Robert M. Gray, “An Algorithm for Vector Quantizer Design,” IEEE Transactions on Communications, Vol. 28, pp. 84-95, 1980. [Ma96] Bin Ma, Taiya Huang, Bo Xu, Xijun Zhang, Fei Qu, “Context-dependent acoustic model for Chinese Recognition,” Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vol. 1, pp. 455-458, 1996. [Marhoul85] John Makhoul, Salim Roucos, Herbert Gish, “Vector Quantization in Speech Coding,” Proceedings of the IEEE, Vol. 73, No. 11, pp. 1551-1588, 1985 [Rabiner85] Lawrence R. Rabiner, Biing-Hwang Juang, Stephen E. Levinson, Mohan M. Sondhi, “Recognition of isolated digits using hidden Markov models with continuous mixture densities,” AT&T Technical Journal, Vol. 64, pp. 1211-1234, 1985. [Redner84] Richard A. Redner, Homer F. Walker, “Mixture Densities, Maximum Likelihood and the EM Algorithm,” SIAM Review, Vol. 26, No. 2, pp. 195-239, 1984. [Son97] R. van Son, JPH van Santen, “Strong Interaction between factors influencing consonant duration,” Proceedings of Eucospeech, 1997 [Takahashi97] Satoshi Takahashi, Kiyoaki Aikawa, Shigeki Sagayama, “Discrete Mixture HMM,” Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vol. 2, pp. 971-974, 1997. [Young05] Steve Young, Gunnar Evermann, Mark Gales, Thomas Hain, Dan Dershaw, Gareth Moor, Julian Odell, Dave Ollason, Dan Povey, Valtcho Valtchev, Phil Woodland, “The HTK Book,” Revised for HTK Version 3.3, April, 2005, Cambridge University Engineering Department [Zhu94] Xiaoyuan Zhu, Bruce Millar, Jain Macleod, Michael Wagner, Fangxin Chen, Shuping Ran, “A Comparative Study of Mixture-Gaussian VQ, Ergodic HMMs, and Left-to-Right HMMs for Speaker Recognition,” Proceedings of IEEE International Symposium on Speech, Image Processing and Neural Network, pp. 618-621, 1994. [謝03] 謝永哲,「應用小波封包轉於PDA之語音辨認研究」,私立中原大學資訊工程所碩士論文,指導教授:杜筑奎,2003。
摘要: 在本論文中,我們提出了一種利用語音特徵點與碼書(codebook)中心的歐式距離(Euclidean distance)配合單變量高斯機率密度函數(univariate Gaussian probabilistic density function)來取代多變量高斯混合模型(multivariate Gaussian Mixture Model)做為輸出機率(output probability)的新型隱藏型馬可夫模型(Hidden Markov Model, HMM),我們稱之為擴充型離散隱藏式馬可夫模型(Extended Discrete Hidden Markov Model, EDHMM)。
It is proposed in the thesis a new type of HMM, which replaces the multivariate Gaussian Mixture Model with a univariate Gaussian probabilistic density function parameterized by the Euclidean distance from the codebook cluster as the output probability. We called it the Extended Discrete Hidden Markov Model.
URI: http://hdl.handle.net/11455/19475
其他識別: U0005-2708200708275900
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-2708200708275900
Appears in Collections:資訊科學與工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.