請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/48760
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 郭振華(Jen-Hwa Guo) | |
dc.contributor.author | Shin-Hau Huang | en |
dc.contributor.author | 黃信豪 | zh_TW |
dc.date.accessioned | 2021-06-15T07:12:31Z | - |
dc.date.available | 2013-09-29 | |
dc.date.copyright | 2010-09-29 | |
dc.date.issued | 2010 | |
dc.date.submitted | 2010-09-24 | |
dc.identifier.citation | [1] B. J. Zimmerman, “Self-regulated learning and academic achievement: An overview,” Educational Psychologist, 25(1), pp. 3-17, 1990.
[2] H. Franco, V. Abrash, K. Precoda, H. Bratt, R. Rao, J. Butzberger, “The SRI EduSpeak(TM) System: Recognition and Pronunciation Scoring for Language Learning”, Proceedings of InSTILL 2000, Dundee, Scotland, pp. 123-128. , 2000 [3] W., Menzel, D. Herron, P. Bonaventura, R. Morton, “Automatic detection and correction of non-native English pronunciations”, Proceedings of InSTILL 2000, Dundee, Scotland, [4] B. Mak, M.H. Siu, M. Ng, Y.C. Tam, “PLASER: Pronunciation Learning via Automatic Speech Recognition”, Proceedings of HLT-NAACL, Edmonton, Canada, pp. 23-29, 2003 [5] L. Changchun, C. Karla, S. Nilanjan, S. Wendy, “Online Affect Detection and Adaptation in Robot Assisted Rehabilitation for Children with Autism”, Robot and Human interactive Communication, pp. 588 - 593 , 2007 [6] H. Eun-ja, K. So-yeon, J. Siekyung, P. Sungju, “Comparative study of effects of language instruction program using intelligence robot and multimedia on linguistic ability of young children”, Robot and Human Interactive Communication, pp. 187 - 192 ,2008 [7] L. Rabiner, B. Juang, “An introduction to hidden Markov models”, ASSP Magazine, IEEE , vol. 3 Issue.1 , pp. 4 -16, 1986 [8] L. Rabiner, “A tutorial on hidden Markov models and selected applications in speech recognition” Proceedings of the IEEE, pp. 257—286, 1989 [9] J. R. Deller, J. G. Proakis and, John H. L. Hansen, Discrete-time Processing of Speech Signals, Macmillan Publishing Co.,1993 [10] L. R. Rabiner, B. H. Juang, Fundamentals of Speech Recognition, Prentice Hall, Englewood Cliffs, New Jersey, 1993 [11] M. Johnson, “PCFG Models of Linguistic Tree Representations” JOURNAL of Computational Linguistics, pp. 613-632, 1998 [12] C. Keh-Jian, “Sinica Treebank”,Computational Linguistics and Chinese Language Processing , pp. 87-104, 1999 [13] S. Fine, “The Hierarchical Hidden Markov Model: Analysis and Applications”, Machine Learning, pp. 41 - 62 , 1998 [14] M. Skounakis, M. Craven, “Hierarchical hidden Markov models for information extraction”, Proceedings of the 18th international joint conference on Artificial intelligence, pp. 427-433 , 2003 [15] L. Po-Hsuan, “Oral Reading Fluency Assessment by Voice Processing”, 2009 [16] Leonardo N.. Horacio F., Vassilios D., Mitchel W., “Automatic Scoring of Pronunciation Quality”, JOURNAL of Speech Communication, pp. 83-93, 1999 [17] B. Andrea, W. Dirk, B. Martin, “Information retrieval system for human-robot communication: asking for directions”, Proceedings of the 2009 IEEE international conference on Robotics and Automation, 2009 [18] T. Yong, W. Hongxing, W. Tianmiao ,” A Speech Interaction System based on Finite State Machine for Service Robot”, International Conference on Computer Science and Software Engineering, 2008 [19] Combridge University Engineering Dept. (CUED) Machine Intelligence Laboratory “HTK BOOK”, http://htk.eng.cam.ac.uk [20] F. Helsinki, “Information-based Case Grammar”, Proceedings of the 13th conference on Computational linguistics, pp. 54-59, 1990 [21] C. Keh-Jiann, “Sinica Treebank: design criteria, annotation guidelines, and on-line interface”, Proceedings of the second workshop on Chinese language processing, pp. 29- 37, 2000 [22] L. Rabiner, “On the use of autocorrelation analysis for pitch detection”, Acoustics, Speech and Signal Processing, pp. 24-33, 1977 [23] P. C. Mahalanobis, “On the generalized distance in statistics”, In Proceedings National Institute of Science, pp. 49-55, 1936 [24] Y. Binyong, F. Mary, “Chinese Romanization. Pronunciation and Orthography”, Beijing: Sinolingua. ISBN 7-80052-148-6 , 1990 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/48760 | - |
dc.description.abstract | 本文的目的為發展伴讀型寵物機器人,輔助教師對於兒童之流暢度評估。 評估的結果會用來做為小孩與伴讀型機器人的回授抑或是教師和家長對於小孩學習情況的掌握因素。首先,將在此伴讀型寵物機器人架設自動語音辨識系統,此語音辨識系統包含了:聲學模型、語言模型和中文句法的階層式隱藏馬可夫模型。聲學模型乃根據人的發聲方式而訓練出特定的模式;語言模型是根據教材中的文章,去計算出字與字之間的關係,最後產生出中文字串;而中文句法的階層式隱藏馬可夫將語音的辨識系統結合中文句法結構樹,使其對於每句辨識結果都會產生到語法樹之葉的節點中。再由各個節點去判斷閱讀時的正確與否。除了朗讀時的準確率外,流暢閱讀的評分條件還包括了:字的間隔時間、閱讀速度、音高、重音與發音。根據這些特徵圖樣,將計算學習者與示範者之間的特徵圖樣之距離。總和以上六種特徵,找母語非中文的人和母語是中文的人來做實驗,驗證此評分系統的可行信,將學習者與示範者的資料做一比對,並探討其結果。最後,將此閱讀流暢度中有問題的指標,轉換成有效的回授給閱讀者以提升其閱讀的成就。 | zh_TW |
dc.description.abstract | The study investigates a fluency scoring technique for a reading assistance robot. The scoring technique is utilized for the evaluation of oral reading fluency to assist teachers by quantifying children’s reading achievement from children’ reading voices. The scoring of oral reading fluency could be used as a feedback when children are learning and it also can be regarded as a kind of evaluation tool to let the teachers or parents know the learning status of children. An automatic speech recognition system based on acoustic recognizer, language model and Chinese grammar based hierarchical hidden Markov model (CGBHHMM) is established. Acoustic model is trained by human pronunciation. Language model is trained to find the relationship between word and word from elementary school text book materials. CGBHHMM is a statistical model trained by the Chinese grammar tree structure. In the CGBHHMM, each sentence of acoustic syllabus is clustered into phrase production state, and CGBHHMM is then combined with ASR to detect a learner’s word accuracy. Five indicators, read speed, pause duration, pitch, stress and pronunciation, are considered as the features of oral reading fluency (ORF). The distance of ORF indicators is calculated of learners with respect to fluent teachers. These distances of ORF features were compared between fluent readers and foreigners who have learned Chinese for two years. It is verified that the proposed scoring method is effective to detect the fluency differences of fluent and influent readers. For future applications, oral reading fluency is could be used in real time by the assistance robot as feedback instructions to guide children for improving their reading achievement. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T07:12:31Z (GMT). No. of bitstreams: 1 ntu-99-R97525019-1.pdf: 2347480 bytes, checksum: 48996f375ce51798bdaae6e3c01c3f89 (MD5) Previous issue date: 2010 | en |
dc.description.tableofcontents | 誌謝 I
摘要 III Abstract IV Table of Contents VI List of Figure IX List of Table XII List of Symbol XV Chapter 1. Introduction 1 1.1 Motivation 1 1.2 Literature review 2 1.3 Thesis organization 6 Chapter 2. System Architecture 8 Chapter 3. Acoustic Model of Automatic Speech Recognition System 14 3.1 Feature Generation 15 3.2 Acoustic Model of Mandarin Chinese Pronunciation 22 3.3 Acoustic Model Training 26 3.3.1 The forward procedure 27 3.3.2 The backward procedure 29 3.3.3Initialization of HMM 30 3.3.4 Baum-Welch algorithm 31 3.4 Viterbi Algorithm for Model Recognition 34 3.5 The Scoring Algorithm of Pronunciation 37 Chapter 4. Mandarin Syntax and Language Model 41 4.1 Treebank Based on Chinese Grammar 42 4.2 Series of Phonation 48 4.3 Hierarchical Hidden Markov Model 50 4.4 Chinese Grammar Based Hierarchical Hidden Markov Model 53 4.5 Training Corpora of Teaching Material 58 4.6 ASR by Language Model and Acoustic Model 60 Chapter 5. Scoring of Oral Reading Fluency 63 5.1 Features of Fluency 63 5.1.1 Word Accuracy 64 5.1.2 Pronunciation Score 67 5.1.3 Read Speed 68 5.1.4 Pause Duration 69 5.1.5 Pitch Detection 70 5.1.6 Stress Detection 72 5.2 Scoring 74 5.2.1 Normalization of ORF Feature Extraction 75 5.2.1.1 Interpolation 75 5.2.1.2 Linear Shifting 76 5.2.2 The Scoring Method of Oral Reading Fluency 78 5.3 Experiments and Results 79 Chapter 6. Conclusion 93 References 96 Appendix A 100 | |
dc.language.iso | en | |
dc.title | 中文句法輔助朗讀評分於伴讀型寵物機器人之研究 | zh_TW |
dc.title | Fluency Evaluation Aided by Mandarin Chinese Syntax for A Reading Assistant Robot | en |
dc.type | Thesis | |
dc.date.schoolyear | 99-1 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 江茂雄(Mao-Hsiung Chiang),王傑智(Chieh-Chih Wang),洪儷瑜(Li-Yun Hung) | |
dc.subject.keyword | 語音辨識,隱藏馬可夫模型,朗讀,流暢度評分,中文句法結構樹,階層式隱藏馬可夫模型, | zh_TW |
dc.subject.keyword | speech recognition,hidden Markov model,oral reading,fluency,Mandarin syntax,hierarchical hidden Markov model, | en |
dc.relation.page | 100 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2010-09-24 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 工程科學及海洋工程學研究所 | zh_TW |
顯示於系所單位: | 工程科學及海洋工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-99-1.pdf 目前未授權公開取用 | 2.29 MB | Adobe PDF |
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。