published_or_final_version / Linguistics / Master / Master of Philosophy

published_or_final_version / Humanities / Master / Master of Philosophy

岑寶蘭. / 手稿影印本. / Thesis (M.A.)--香港中文大學硏究院敎育學院. / Shou gao yin yin ben. / Title also in English: The phonology of homonyms : a contrastive study of Guang Zhou hua and pu ... / Cen Baolan. / Thesis (M.A.)--Xianggang Zhong wen da xue yan jiu yuan jiao yu xue yuan. / 前言 / Chapter 第一章 --- 引言 / Chapter 一 --- 背景 --- p.1 / Chapter 二 --- 文獻參考 --- p.3 / Chapter 三 --- 理論根據 --- p.6 / Chapter 四 --- 解釋名詞 --- p.9 / Chapter 五 --- 研究目標 --- p.12 / Chapter 六 --- 研究範圍 --- p.14 / Chapter 第二章 --- 研究方法 / Chapter 一 --- 樣本選取 --- p.15 / Chapter 二 --- 方法限制 --- p.25 / Chapter 三 --- 製訂字卡 --- p.26 / Chapter 四 --- 對照表的編排 --- p.27 / Chapter 五 --- 對應關係表的編排及應用方法 --- p.28 / Chapter 六 --- 二表的錯漏 --- p.33 / Chapter 第三章 --- 廣州話音節結構 / Chapter 一 --- 概說 --- p.36 / Chapter 二 --- 聲母 --- p.37 / Chapter 三 --- 韻母 --- p.39 / Chapter 四 --- 聲調 --- p.42 / Chapter 五 --- 聲母與韻母的結構和限制 --- p.44 / Chapter 六 --- 元音與聲調的配合 --- p.49 / Chapter 七 --- 聲母與聲調的關係 --- p.50 / Chapter 第四章 --- 普通話音節結構 / Chapter 一 --- 聲母 --- p.63 / Chapter 二 --- 韻母 --- p.65 / Chapter 三 --- 聲調 --- p.70 / Chapter 四 --- 普通話音節的結構和限制 --- p.72 / Chapter 第五章 --- 音素對應概況 / Chapter 一 --- 聲母對應 --- p.88 / Chapter 二 --- 韻母對應 --- p.92 / Chapter 三 --- 聲調對應 --- p.101 / Chapter 第六章 --- I－I 對應 / Chapter 一 --- 定義 --- p.104 / Chapter 二 --- 字彙最豐富的對應 --- p.104 / Chapter 三 --- 六字組 --- p.105 / Chapter 四 --- 舌尖前音 --- p.107 / Chapter 五 --- “I－I對´應ح的特點 --- p.109 / Chapter 第七章 --- I－多對應 / Chapter 一 --- “I─多對´應ح的意義及概況 --- p.113 / Chapter 二 --- ／uk／韻母 --- p.114 / Chapter 三 --- p.118 / Chapter 四 --- p.122 / Chapter 五 --- “I─多對´應ح的特徵 --- p.128 / Chapter 第八章 --- 多－I對應 / Chapter 一 --- “多─I對´應ح的定義及概況 --- p.132 / Chapter 二 --- 音節最多的對應 --- p.133 / Chapter 三 --- p.135 / Chapter 四 --- p.138 / Chapter 五 --- 其他顯著的對應情況 --- p.139 / Chapter 六 --- “多─I對´應ح的特徵 --- p.146 / Chapter 第九章 --- 結論 / Chapter 一 --- 同音字字音的一致性 --- p.151 / Chapter 二 --- 同音字字音的差異 --- p.153 / Chapter 三 --- 歸納同音字字音的一致性和差異 --- p.156 / Chapter 四 --- 檢討 --- p.159 / Chapter 五 --- 建議 --- p.161 / 參考書目 --- p.162

Thesis (M.A.)--香港中文大學硏究院語文學部. / Includes bibliographical references (leaves 150-151). / Thesis (M.A.)--Xianggang Zhong wen da xue yan jiu yuan yu wen xue bu. / 導言 --- p.2 / 閩語歷史背景 --- p.3 / 音系 / 與中古音的比較 --- p.6 / 表 --- p.9 / 今音，聲韻調的詳細描寫 --- p.64 / 表 --- p.68 / 連續變調 --- p.90 / 韵聲同化 --- p.92 / 表 --- p.94 / 詞滙 / 常用詞滙表分類 --- p.117 / 古漢語 --- p.136 / 語法特點 --- p.140 / 附錄 / 標音例文 --- p.143 / 再者，引用與參考書目 --- p.150

by Wai-Hoo Au Yeung. / Thesis submitted in 1997. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1998. / Includes bibliographical references (leaves i-v (3rd gp.)). / Abstract also in Chinese. / Acknowledgments / Abstract / Contents / Abbreviations & Tables / Chapter 1. --- INTRODUCTION --- p.1 / Chapter 1.1. --- What is a parameter? / Chapter 1.2. --- Parameter resetting in SLA / Chapter 1.3. --- Parameter as feature checking / Chapter 1.4. --- Research goals and outline of the thesis / Chapter 2. --- PARAMETERIZATION IN CHINESE NOMINALS --- p.18 / Chapter 2.1. --- DP-analysis and its parameterization / Chapter 2.2. --- Evaluation of the four models of Chinese nominal structures / Chapter 2.3. --- Parameterization in Cantonese and Mandarin nominals / Chapter 2.4. --- The Lexical CL Parameter / Chapter 3. --- METHODOLOGY --- p.86 / Chapter 3.1. --- The subject / Chapter 3.2. --- Timing of recording / Chapter 3.3. --- What is recorded / Chapter 3.4. --- The corpus / Chapter 3.5. --- Criteria of counting utterances and point of acquisition / Chapter 4. --- THE ACQUISITION OF CANTONESE NOMINALS --- p.92 / Chapter 4.1. --- Overall development of Cantonese nominal structure / Chapter 4.2. --- Acquisition of Cantonese-specific CLP properties / Chapter 4.3. --- Comparison with native Cantonese children's data / Chapter 4.4. --- Acquisition by resetting the Lexical CL Parameter / Chapter 5. --- AN INFORMAL EXPERIMENT ON GENERIC di AND di-N PHRASES --- p.118 / Chapter 5.1. --- Design of the experiment / Chapter 5.2. --- Materials / Chapter 5.3. --- Procedures and results / Chapter 5.4. --- Comparison between Ching's and native children's results / Chapter 6. --- CONCLUSION --- p.134 / Chapter 6.1. --- Theoretical and acquisition findings / Chapter 6.2. --- Further evidence for parameter resetting / Chapter 6.3. --- Implications for future research / Chapter 6.4. --- Concluding remarks / References / Appendix A: 3 sample files of the corpus

前人發現非母語者对言語的感知主要受其母語和聲學因素的影響。但是多數研究集中在音段(segment)方面，鮮有研究關注這些因素如何影響超音段(supra-segment)的感知。母語中的聲調可能使有聲調的語言使用者比無聲調的語言使用者在聲調感知中有更好的發揮，兩組無聲調的語言使用者在各自母語的影響下，對聲調感知的表現也未必一致。本文旨在探索母語和聲學因素如何影響非母語者對廣東話聲調的感知。三組非母語者參加了我們的實驗。普通話組是有聲調的語言使用者, 英語組和法語組是無聲調的語言使用者。實驗一採用AX辨別範式 (AX discrimination) ，實驗材料包括廣東話言語聲調(speech tones)和非言語聲調 (non-speech tones)。實驗結果顯示，被試在聽辨言語聲調和非言語聲調時有不同的表現。在聽辨言語聲調時，一方面三組被試受聲調間的聲學距離影響在某些聲調組有相似表現，但另一方面普通話組在母語聲調的影響下，在總體上和某些聲調組中都比英語和法語組有更好的表現。相反，在聽辨非言語聲調時，三組被試的表現並無明顯的差異。實驗二採用相似度評判範式 (dissimilarity rating)，實驗材料為廣東話言語聲調。實驗結果顯示，被試在母語的影響下，側重不同的感知特徵 (perceptual cues)。普通話組對聲調的調形 (pitch direction) 比較敏感。英語和法語組都只對聲調音高的高低變化 (pitch height)敏感，但此兩組非母語者的感知特徵並不完全相同。綜觀以上所得，我們發現普通話組在母語聲調的幫助下有最好的表現，而英語和法語組因為母語中並無聲調，所以在辨別聲調時表現類似，但評判聲調相似度時則受母語的影響而關注不同的感知特徵。另外，本文在現行的理論模型的框架下討論了我們的實驗結果，並基於此對相關模型作出評價。最後，我們提出母語和聲學因素共同影響非母語者的聲調感知，兩項涉及影響聲調感知的要素應當受到現行理論模型的重視。 / The influences of first language (L1) experience and psychoacoustic factors are well-attested in the perception of non-native segments, but such influence on the perception of non-native tones is still unclear. While the presence of lexical tones in L1 could cause differences in the perception of tones between speakers of tone languages and of non-tone languages, language-specific use of pitch may differentiate speakers of non-tone languages as well. This study conducted two experiments to investigate how L1 experience and psychoacoustic factors affect speakers of tone language (Mandarin) and two non-tone languages (English and French) in the perception of Cantonese tones. In Experiment 1, three groups of subjects with no Cantonese knowledge, native speakers of Mandarin, English and French, participated in an AX discrimination task of speech and non-speech tones in Cantonese. Results showed that the subjects performed differently in the speech and non-speech tasks. In the speech task, while the three L1 groups shared some confusable tone pairs due to acoustic similarity of the tonal stimuli, the Mandarin group had a better performance than the English and French groups and differed from them in specific pairs under the influence of L1 experience. In the non-speech task, however, the three L1 groups did not have significant differences. In Experiment 2, the same subjects participated in a dissimilarity rating task of speech tones. Results indicated that the three L1 groups assigned weight to different dimensions of tones because of the language-specific use of pitch in their L1. While the Mandarin speakers were more sensitive to pitch direction than pitch height, the English and French speakers were similar in only attending to pitch height. Nevertheless, they also differed in terms of the perceptual cues they used. The English speakers attended to the beginning and ending pitch height whereas the French speakers were sensitive to the overall pitch height. In summary, L1 experience with native tones facilitated the Mandarin speakers’ perception of non-native Cantonese tones. The English and French speakers had no difference in discriminating non-native tones due to the lack of lexical tones in their L1, although they were sensitive to different perceptual cues. The findings are discussed with respect to current models of non-native perception, the Perceptual Assimilation Model (PAM) and the Attention to Dimension (A2D) model. Our findings suggest that L1 experience and psychoacoustic similarity of stimuli jointly influence the perception of non-native tones and both factors should be incorporated into the models of speech perception. / Detailed summary in vernacular field only. / Qin, Zhen. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2012. / Includes bibliographical references (leaves 85-93). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts in also Chinese; appendix A in Chinese. / Abstract --- p.III / 摘要 --- p.IV / Acknowledgements --- p.V / Table of Content --- p.VI / List of Figures --- p.IX / List of Tables --- p.X / Chapter CHPATER 1 --- GENERAL INTRODUCTION --- p.1 / Chapter 1.1 --- Factors in perception of non-native tones --- p.1 / Chapter 1.2 --- Our aim --- p.2 / Chapter 1.3 --- Our solution --- p.3 / Chapter 1.4 --- Thesis Organization --- p.4 / Chapter CHPATER 2 --- LITERATURE REVIEW --- p.5 / Chapter 2.1 --- Modeling cross-linguistic perception --- p.5 / Chapter 2.1.1 --- Category Assimilation Approach---the PAM --- p.5 / Chapter 2.1.2 --- Cue-Weighting Approach---the A2D model --- p.8 / Chapter 2.1.3 --- Comparison of the two models --- p.11 / Chapter 2.3. --- Perception of lexical tones --- p.12 / Chapter 2.3.1 --- The phonemic status of pitch --- p.12 / Chapter 2.3.2. --- Perceptual cues of tones --- p.14 / Chapter 2.3.3 --- Psychoacoustic factors --- p.15 / Chapter 2.4. --- Pitch in Cantonese, Mandarin and English and French --- p.16 / Chapter 2.4.1 --- Lexical tones in Cantonese --- p.17 / Chapter 2.4.2 --- Lexical tones in Mandarin --- p.18 / Chapter 2.4.3 --- Pitch in English and French --- p.19 / Chapter 2.5 --- Research Questions --- p.22 / Chapter 2.6 --- Predictions --- p.22 / Chapter CHAPTER 3 --- EXPERIMENT ONE --- p.26 / Chapter 3.1 --- Introduction --- p.26 / Chapter 3.2 --- Subjects --- p.27 / Chapter 3.3 --- Materials --- p.31 / Chapter 3.3.1 --- Speech stimuli --- p.31 / Chapter 3.3.2 --- Non-speech stimuli --- p.34 / Chapter 3.4 --- Procedures --- p.35 / Chapter 3.4.1 --- Speech Task --- p.35 / Chapter 3.4.2 --- Non-speech task --- p.36 / Chapter 3.5 --- Results and Analysis --- p.37 / Chapter 3.5.1 --- Overall performance in the speech task versus non-speech task --- p.37 / Chapter 3.5.2 --- Performance for individual tone pairs --- p.40 / Chapter 3.5.3 --- Different types of tone pairs --- p.46 / Chapter 3.5.4 --- Individual differences --- p.48 / Chapter 3.6 --- Discussion --- p.53 / Chapter 3.6.1 --- Overall performance in speech and non-speech tasks --- p.53 / Chapter 3.6.2 --- Performance on individual tone pairs --- p.54 / Chapter 3.6.3 --- Individual differences --- p.57 / Chapter 3.6.4 --- Comparison with previous studies --- p.57 / Chapter 3.7 --- Summary --- p.58 / Chapter CHAPTER 4 --- EXPERIMENT TWO --- p.59 / Chapter 4.1 --- Introduction --- p.59 / Chapter 4.2 --- Subjects and Materials --- p.59 / Chapter 4.3 --- Procedures --- p.60 / Chapter 4.4 --- Analysis --- p.61 / Chapter 4.5 --- Results --- p.62 / Chapter 4.5.1 --- Number of Dimensions --- p.62 / Chapter 4.5.2 --- Tonal distribution --- p.64 / Chapter 4.5.3 --- Interpretation of dimensions --- p.64 / Chapter 4.5.4 --- Weighting of dimensions and individuals --- p.65 / Chapter 4.6 --- Discussion --- p.66 / Chapter 4.6.1 --- Psychoacoustic factors --- p.66 / Chapter 4.6.2 --- L1 experience --- p.67 / Chapter 4.6.3 --- Comparison with the discrimination task --- p.68 / Chapter 4.6.4 --- Comparison with previous studies --- p.69 / Chapter 4.7 --- Summary --- p.70 / Chapter CHAPTER 5 --- GENERAL DISCUSSION --- p.71 / Chapter 5.1 --- Summary of findings --- p.71 / Chapter 5.1.1 --- Psychoacoustic factors --- p.71 / Chapter 5.1.2 --- L1 experience --- p.71 / Chapter 5.2 --- Revisiting the PAM and the A2D model --- p.73 / Chapter 5.2.1 --- The predictions of the two models --- p.73 / Chapter 5.2.2 --- Evaluations of the two models --- p.76 / Chapter 5.3 --- The psycholinguistic representation of lexical tone --- p.79 / Chapter 5.3.1 --- Tone versus Segment --- p.79 / Chapter 5.3.2 --- Tone versus Other prosodic categories --- p.80 / Chapter 5.4 --- Limitations and Future study --- p.82 / Chapter 5.5 --- Conclusion --- p.83 / References --- p.85 / Appendix --- p.94 / Chapter Appendix A- --- The randomized wordlists --- p.94 / Chapter Appendix B- --- Dissimilarity rating answer sheet --- p.95

Automatic recognition of Cantonese tones has long been regarded as a difficult task. Cantonese has one of the most complicated tone systems among all languages in the world. This thesis presents a novel approach of modeling Cantonese tones. We propose the use of supra-tone models. Each supra-tone unit covers a number of syllables in succession. The supra-tone model characterizes not only the tone contours of individual syllables but also the transitions among them. By including multiple tone contours in one modeling unit, the relative heights of the tones are captured explicitly. This is especially important for the discrimination among the level tones of Cantonese. / The decoding in conventional LVCSR systems aims at finding the sentence hypothesis, i.e. the string of words, which has the maximum a posterior (MAP) probability in comparison with other hypotheses. However, in most applications, the recognition performance is measured in terms of word error rate (or word accuracy). In Chinese languages, given that "word" is a rather ambiguous concept, speech recognition performance is usually measured in terms of the character error rate. In this thesis, we develop a decoding algorithm that can minimize the character error rate. The algorithm is applied to a reduced search space, e.g. a word graph or the N-best sentence list, which results from the 1st pass of search, and the generalized character posterior probability (GCPP) is maximized. (Abstract shortened by UMI.) / This thesis addresses two major problems of the existing large vocabulary continuous speech recognition (LVCSR) technology: (1) inadequate exploitation of alternative linguistic and acoustic information; and (2) the mismatch between the decoding (recognition) criterion and the performance evaluation. The study is focused on Cantonese, one of the major Chinese dialects, which is also monosyllabic and tonal. Tone is somewhat indispensable for lexical access and disambiguation of homonyms in Cantonese. However, tone information into Cantonese LVCSR requires effective tone recognition as well as a seamless integration algorithm. / Qian Yao. / "July 2005." / Adviser: Tan Lee. / Source: Dissertation Abstracts International, Volume: 67-07, Section: B, page: 4009. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (p. 100-110). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract in English and Chinese. / School code: 1307.

張可人. / "2002年12月". / 論文(哲學碩士)--香港中文大學, 2002. / 參考文獻 (leaves 95-105). / 附中英文摘要. / "2002 nian 12 yue". / Zhang Keren. / Lun wen (zhe xue shuo shi)--Xianggang Zhong wen da xue, 2002. / Can kao wen xian (leaves 95-105). / Fu Zhong Ying wen zhai yao. / Chapter 第一章： --- 引言 --- p.1 / Chapter 第二章： --- 量詞的定義和特點 --- p.5 / Chapter 1. --- 量詞的定義 --- p.5 / Chapter 2. --- 以往的學者對量詞的看法 --- p.5 / Chapter 2-1. --- 著重量詞的語法功能 --- p.9 / Chapter 2.1.1. --- 著重量詞和名詞、動詞的語法關係 --- p.9 / Chapter 2.1.2. --- 著重量詞和數詞的語法關係 --- p.10 / Chapter 2.2. --- 著重量詞的表義作用 --- p.11 / Chapter 2.2.1. --- 從量詞的表義作用注意到量詞的修辭作用 --- p.12 / Chapter 2.2.2. --- 從量詞的表義作用注意到量詞劃分範疇的功用 --- p.12 / Chapter 3. --- 漢語量詞和印歐語系冠詞的異同 --- p.14 / Chapter 4. --- 漢語量詞的語法特點 --- p.16 / Chapter 5. --- 量詞的語義特點 --- p.17 / Chapter 6. --- 香港粤語量詞的特點 --- p.19 / Chapter 6.1. --- 和普通話的寫法一樣，意思和用法相同的量詞 --- p.19 / Chapter 6.2. --- 和普通話的寫法一樣，但用法並不完全相同的量詞 --- p.19 / Chapter 6.3. --- 普通話沒有，粤語特有的量詞 --- p.21 / Chapter 7. --- 小結 --- p.24 / Chapter 第三章 --- ：理論基礎 --- p.25 / Chapter 1. --- 西方傳統理論對範疇化的誤解 --- p.25 / Chapter 2. --- 何謂理想化的認知模式 --- p.28 / Chapter 3. --- 原形效應的四種認知模式 --- p.32 / Chapter 3.1. --- 命題模式 --- p.32 / Chapter 3.2. --- 形象´ؤ´ؤ圖式模式 --- p.34 / Chapter 3.3. --- 隱喻模式 --- p.36 / Chapter 3.3.1. --- 結構隱喻 --- p.37 / Chapter 3.3.2. --- 方位隱喻 --- p.39 / Chapter 3.3.3. --- 本體隱喻 --- p.40 / Chapter 3.4. --- 轉喻模式 --- p.42 / Chapter 3.4.1. --- 常規內心意象的轉喻 --- p.42 / Chapter 3.4.2. --- 用於經驗領域的轉喻 --- p.42 / Chapter 3.4.2. --- 居於中心的基本層次物體的轉喻 --- p.43 / Chapter 3.5. --- 小結 --- p.44 / Chapter 4. --- 小結 --- p.44 / Chapter 第四章： --- 實例考察 --- p.47 / Chapter 1. --- 命題模式 --- p.47 / Chapter 1.1. --- 和量詞的意義有直接關係的命題 --- p.48 / Chapter 1.2. --- 相近的命題 --- p.52 / Chapter 1.3. --- 和本義沒有直接關係的命題 --- p.59 / Chapter 1.4. --- 小結 --- p.62 / Chapter 2. --- 形象´ؤ´ؤ圖式模式 --- p.62 / Chapter 3. --- 隱喻模式 --- p.64 / Chapter 3.1. --- 結構隱喻 --- p.64 / Chapter 3.2. --- 方位隱喻 --- p.66 / Chapter 3.3. --- 本體隱喻 --- p.69 / Chapter 3.4. --- 小結 --- p.71 / Chapter 4. --- 轉喻模式 --- p.71 / Chapter 4.1. --- 用於常規內心意象的轉喻 --- p.71 / Chapter 4.2. --- 用於經驗領域的轉喻 --- p.75 / Chapter 4.3. --- 居於中心的基本層次物體的轉喻 --- p.76 / Chapter 4.4. --- 小結 --- p.79 / Chapter 5. --- 範疇並不是單靠共同特徵而形成 --- p.80 / Chapter 6. --- 香港粤語中代表「其他」的範疇 --- p.82 / Chapter 7. --- 小結 --- p.92 / Chapter 第五章： --- 結論 --- p.93 / 參考書籍及論文 --- p.95 / 附錄：香港粤語量詞問卷調查 --- p.106 / 香港粤語量詞表示度量衝的量詞舉隅 --- p.131 / 香港粤語量詞四種認知模式舉隅 --- p.131

Kam Patgi. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2003. / Includes bibliographical references (leaf 103). / Abstracts in English and Chinese. / Chapter Chapter 1. --- Introduction --- p.1 / Chapter 1.1 --- Automatic Speech Recognition --- p.1 / Chapter 1.2 --- Pronunciation Modeling in ASR --- p.2 / Chapter 1.3 --- Obj ectives of the Thesis --- p.5 / Chapter 1.4 --- Thesis Outline --- p.5 / Reference --- p.7 / Chapter Chapter 2. --- The Cantonese Dialect --- p.9 / Chapter 2.1 --- Cantonese - A Typical Chinese Dialect --- p.10 / Chapter 2.1.1 --- Cantonese Phonology --- p.11 / Chapter 2.1.2 --- Cantonese Phonetics --- p.12 / Chapter 2.2 --- Pronunciation Variation in Cantonese --- p.13 / Chapter 2.2.1 --- Phone Change and Sound Change --- p.14 / Chapter 2.2.2 --- Notation for Different Sound Units --- p.16 / Chapter 2.3 --- Summary --- p.17 / Reference --- p.18 / Chapter Chapter 3. --- Large-Vocabulary Continuous Speech Recognition for Cantonese --- p.19 / Chapter 3.1 --- Feature Representation of the Speech Signal --- p.20 / Chapter 3.2 --- Probabilistic Framework of ASR --- p.20 / Chapter 3.3 --- Hidden Markov Model for Acoustic Modeling --- p.21 / Chapter 3.4 --- Pronunciation Lexicon --- p.25 / Chapter 3.5 --- Statistical Language Model --- p.25 / Chapter 3.6 --- Decoding --- p.26 / Chapter 3.7 --- The Baseline Cantonese LVCSR System --- p.26 / Chapter 3.7.1 --- System Architecture --- p.26 / Chapter 3.7.2 --- Speech Databases --- p.28 / Chapter 3.8 --- Summary --- p.29 / Reference --- p.30 / Chapter Chapter 4. --- Pronunciation Model --- p.32 / Chapter 4.1 --- Pronunciation Modeling at Different Levels --- p.33 / Chapter 4.2 --- Phone-level pronunciation model and its Application --- p.35 / Chapter 4.2.1 --- IF Confusion Matrix (CM) --- p.35 / Chapter 4.2.2 --- Decision Tree Pronunciation Model (DTPM) --- p.38 / Chapter 4.2.3 --- Refinement of Confusion Matrix --- p.41 / Chapter 4.3 --- Summary --- p.43 / References --- p.44 / Chapter Chapter 5. --- Pronunciation Modeling at Lexical Level --- p.45 / Chapter 5.1 --- Construction of PVD --- p.46 / Chapter 5.2 --- PVD Pruning by Word Unigram --- p.48 / Chapter 5.3 --- Recognition Experiments --- p.49 / Chapter 5.3.1 --- Experiment 1 ´ؤPronunciation Modeling in LVCSR --- p.49 / Chapter 5.3.2 --- Experiment 2 ´ؤ Pronunciation Modeling in Domain Specific task --- p.58 / Chapter 5.3.3 --- Experiment 3 ´ؤ PVD Pruning by Word Unigram --- p.62 / Chapter 5.4 --- Summary --- p.63 / Reference --- p.64 / Chapter Chapter 6. --- Pronunciation Modeling at Acoustic Model Level --- p.66 / Chapter 6.1 --- Hierarchy of HMM --- p.67 / Chapter 6.2 --- Sharing of Mixture Components --- p.68 / Chapter 6.3 --- Adaptation of Mixture Components --- p.70 / Chapter 6.4 --- Combination of Mixture Component Sharing and Adaptation --- p.74 / Chapter 6.5 --- Recognition Experiments --- p.78 / Chapter 6.6 --- Result Analysis --- p.80 / Chapter 6.6.1 --- Performance of Sharing Mixture Components --- p.81 / Chapter 6.6.2 --- Performance of Mixture Component Adaptation --- p.84 / Chapter 6.7 --- Summary --- p.85 / Reference --- p.87 / Chapter Chapter 7. --- Pronunciation Modeling at Decoding Level --- p.88 / Chapter 7.1 --- Search Process in Cantonese LVCSR --- p.88 / Chapter 7.2 --- Model-Level Search Space Expansion --- p.90 / Chapter 7.3 --- State-Level Output Probability Modification --- p.92 / Chapter 7.4 --- Recognition Experiments --- p.93 / Chapter 7.4.1 --- Experiment 1 ´ؤModel-Level Search Space Expansion --- p.93 / Chapter 7.4.2 --- Experiment 2 ´ؤ State-Level Output Probability Modification …… --- p.94 / Chapter 7.5 --- Summary --- p.96 / Reference --- p.97 / Chapter Chapter 8. --- Conclusions and Suggestions for Future Work --- p.98 / Chapter 8.1 --- Conclusions --- p.98 / Chapter 8.2 --- Suggestions for Future Work --- p.100 / Reference --- p.103 / Appendix I Base Syllable Table --- p.104 / Appendix II Cantonese Initials and Finals --- p.105 / Appendix III IF confusion matrix --- p.106 / Appendix IV Phonetic Question Set --- p.112 / Appendix V CDDT and PCDT --- p.114

No description available.