臺灣博碩士論文加值系統

本研究目的為發展語音處理技術，用以輔助教師對兒童朗讀流暢度之評估。閱讀內容辨識是基於隱藏式馬可夫模型技術，輔以國語句法學之架構，以提升朗讀聲音的即時辨識率。流暢度的評量內容包含閱讀速度、字的正確率、及閱讀韻律等。閱讀速度是計算為每分鐘所朗讀的字數，正確度則是藉由語音辨識系統所求得，而閱讀韻律包含了三個部分：字或詞之間隔時間、音高以及重音。本研究實驗部分是藉由記錄不同閱讀能力的朗讀者所朗讀的國小四年級國語課文，比較各自的流暢度數據，以說明本研究所採用的評量方法。未來，根據評量數據所產生的朗讀流暢度指標，將可用來回授給閱讀者以提升其閱讀的成就。

The study investigates a signal processing technique for the assessment of oral reading fluency to assist children’s reading achievement. Reading voices recognition based on a Hidden Markov Model and the Mandarin Chinese syntax is used to improve the real time character recognition rate out of children’s reading voices. Fluency assessments were performed for reading speed, word accuracy, and prosody. Accuracy was estimated by a voice recognition system. Reading speed is defined as the number of characters read per minute. Prosody includes three parts: pause duration, pitch, and stress. Experiments were conducted to demonstrate the oral reading fluency measures derived from reading sounds of children with different fluency levels. Feedback instructions or indexes could be generated out of the oral reading fluency measures to children for improving their reading achievement.

Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Literature review 2
1.3 Thesis organization 5
Chapter 2 Speech signal pre-processing 6
2.1 Frame Blocking 6
2.2 Speech Endpoint Detection 7
2.3 Normalization 10
2.4 Mel-Frequency Cepstrum Coefficients 11
2.4.1 Pre-emphasis 13
2.4.2 Windowing 14
2.4.3 Discrete Fourier Transform (DFT) 16
2.4.4 Mel-filter bank 16
2.4.5 Log Energy 17
2.4.6 Inverse Discrete Fourier Transform (IDFT) 18
Chapter 3 Hidden Markov Model 21
3.1 Basic Hidden Markov Model 21
3.2 The Three Basic Problems for HMM 26
3.2.1 Baum-Welch (forward-backward) algorithm to solve problem 1 27
3.2.2 The Viterbi algorithm to solve problem 2 30
3.2.3 Problem 3 of Parameter Estimation(HMM training) 33
3.2.4 The k-means algorithm 39
3.3 Speech recognition 40
Chapter 4 Mandarin Syntax 42
Chapter 5 Fluency Assessment 51
5.1 Word accuracy 51
5.2 Reading speed 56
5.3 Prosody 59
5.3.1 Pause duration 59
5.3.2 Pitch 64
5.3.3 Stress 72
Chapter 6 Conclusions 74
References 75

References
[1]B. J. Zimmerman, “Self-regulated learning and academic achievement: An overview,” Educational Psychologist, 25(1), pp. 3-17, 1990.
[2]T. V. Rasinski, “ Investigating measures of reading fluency,” Educational Research Quarterly, Vol. 14, pp. 37-44, 1990.
[3]M. R. Kuhn, S. A. Stahl, “ Fluency: a review of developmental Remedial practices,” Journal of Educational Psychology, Vol. 95, No. 1, pp. 3-21, 2003.
[4]D. LeBergeou, S. J. Samuels, “Toward a theory of automatic information processing in reading,” Cognitive Psychology, Vol. 6, pp. 363-369, 1974.
[5]S. L. Dowhower, “Speaking of prosody: Fluency unattended bedfellow,” Theory in Practice, Vol. 30, pp. 158-164, 1991.
[6]National Reading Panel. (2000). Report of the subgroups: National reading panel. Washington, DC: National Institute of Child Health and Development
[7]Rasinski, T. R. (2004). Creating fluent readers. Educational Leadership, 61, 46–51
[8]Schwanenflugel, P. J., Hamilton, A. M., Kuhn, M. R., Wisenbaker, J. M., & Stahl, S. A.. “Becoming a fluent reader: Reading skill and prosodic features in the oral reading of young readers.” Journal of Educational Psychology, 96, pp. 119–129, 2004.
[9]B.S Atal, S.L Hanauer ”Speech analysis and Synthesis by linear prediction of the speech wave”, J. Acoust Soc. Am. 50(2), pp. 637-655 , 1971
[10]F. Itakura, S. Saito “A statistical method for estimation of speech spectra density and formant frequencies”, Electron. Commun. Jpn. 53A, pp. 36-43 , 1970
[11]J.D. Freguson “Hidden Markov analysis: An introduction. In: Hidden Markov Models for Speech”, (Institute for Defense Analysis, Princeton ,1980)
[12]Waleed H. Abdulla and Nikola K. Kasabov “The Concepts of Hidden Markov Model in Speech Recognition”, University of Otago, New Zealand, 1999
[13]J. R. Deller, J. G. Proakis and, John H. L. Hansen, Discrete-time Processing of Speech Signals, Macmillan Publishing Co.,1993
[14]L. R. Rabiner, B. H. Juang, Fundamentals of Speech Recognition, Prentice Hall, Englewood Cliffs, New Jersey, 1993
[15]F. J. Owens , Signal Processing of Speech, Macmillan Press Ltd., London, 1993
[16]Andrew Radford, Transformational Syntax : A Student''s Guide to Chomsky''s Extended Standard Theory, Cambridge ; New York : Cambridge University Press, 1981
[17]Ting-Chi Tang , Studies in Transformational Grammar of Chinese Volume 1 : Movement Transformation, Student Book Co. , 1982
[18]S.B. Davis, P. Mermelstein “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences”, IEEE Trans. Acoust. Speech Signal Process. 28(4), pp. 357-366, 1980
[19]J. Miller, P. J. Schwanenflugel “Prosody of syntactically complex sentences in the oral reading of young children.” Journal of Educational Psychology, Vol. 98, pp. 839-853, 2006.