No description available.

This report explores the subject of speech synthesis. Information given includes a brief explanation of speech production in man, an historical view of speech synthesis, and four types of electronic synthesizers in use today. Also included is a brief presentation on phonetics, the study of speech sounds. An understanding of this subject is necessary to see how a synthesizer must produce certain sounds, and how these sounds are put together to create words. Finally a description of a limited text speech synthesizer is presented. This system allows the user to enter English text via a keyboard and have it output in spoken form. The future of speech synthesis appears to be very bright. This report also gives some possible applications of verbal computer communication.

No description available.

Thesis--PlanB (M.S.)--University of Wisconsin--Stout, 1998. / Includes bibliographical references.

胡承慈. / 大字複印本. / Thesis (M.A.)--香港中文大學研究院電子計算學部. / Da zi fu yin ben. / Includes bibliographical references (leaves 26-27 (2nd group)). / Hu Chengci. / Thesis (M.A.)--Xianggang Zhong wen da xue yan jiu yuan dian zi ji suan xue bu. / 嗚謝 --- p.I / ABSTRACT --- p.II / 提要 --- p.III / Chapter 第一章 --- 緒論 / Chapter 1.1 --- 用聲音作爲輸出媒介 --- p.1 / Chapter 1.2 --- 各種聲音輸出方法 --- p.1 / Chapter 1.3 --- 音素合成法及VOTRAX SC01語音合成片 --- p.3 / Chapter 1.4 --- 國語輸出 --- p.3 / Chapter 第二章 --- 中文分折 / Chapter 2.1 --- 國語分析 --- p.4 / Chapter 2.1.1 --- 國語音素 --- p.4 / Chapter 2.1.1.1 --- 單元音 --- p.4 / Chapter 2.1.1.2 --- 輔音 --- p.5 / Chapter 2.1.2 --- 國語音素的互相結合 / Chapter 2.1.2.1 --- 複元音 --- p.6 / Chapter 2.1.2.2 --- 鼻元音 --- p.6 / Chapter 2.1.3 --- 國語音節 --- p.7 / Chapter 2.2 --- 漢詞 --- p.9 / Chapter 2.3 --- 漢字 --- p.9 / Chapter 第三章 --- 硬件和軟件的設計 / Chapter 3.1 --- 硬件設計 --- p.10 / Chapter 3.2 --- 軟件設計 --- p.11 / Chapter 3.2.1 --- 漢字編碼和音素地址表 --- p.12 / Chapter 3.2.2 --- 音素串表 --- p.13 / Chapter 3.2.3 --- 語音合成器操作程序 --- p.14 / Chapter 3.2.4 --- 語音合成器管理程序和音素編輯程序 --- p.15 / Chapter 第四章 --- 建立和發現 / Chapter 4.1 --- 硬件的建立 --- p.15 / Chapter 4.2 --- 軟件的建立 --- p.18 / Chapter 4.2.1 --- 表的建立 --- p.18 / Chapter 4.2.2 --- 程序的建立 --- p.23 / Chapter 第五章 --- 結論 --- p.24 / Chapter 附錄A --- 參考資料 --- p.26 / Chapter 附錄B --- 漢語輔音音素表 --- p.28 / Chapter 附錄C --- 漢語元音音素表 --- p.29 / Chapter 附錄D --- SC01音素表 --- p.31 / Chapter 附錄E --- 軟件應用 / Chapter E.1 --- 語音合成器操作程序應用 --- p.34 / Chapter E.2 --- 語音合成器管理程序應用 --- p.41 / Chapter E.3 --- 音素編輯程序應用 --- p.45 / Chapter 附錄F --- 中英名詞對照表 / Chapter F.1 --- 聲音及發聲方法 --- p.53 / Chapter "F,2" --- 硬件 --- p.53 / Chapter F.3 --- 軟件 --- p.53 / Chapter 附錄G --- 語音合成器硬件電路圖 --- p.55

by Andrew Poon Ngai Ho. / Thesis (M.S.)--Chinese University of Hong Kong, 1993. / Includes bibliographical references (leaves [97-98]). / ABSTRACT / ACKNOWLEDGMENTS / Chapter 1. --- INTRODUCTION / Chapter 2. --- REPRESENTATION OP SPEECH DATA --- p.4 / Chapter 2.1 --- SAMPLE DATA REPRESENTATION --- p.4 / Chapter 2.2 --- ANALOG LINEAR SYSTEM MODEL --- p.7 / Chapter 2.3 --- DISCRETE FOURIER TRANSFORM --- p.8 / Chapter 2.4 --- FILTER BAND REPRESENTATION --- p.8 / Chapter 2.5 --- LINEAR PREDICTIVE CODING (LPC) --- p.10 / Chapter 2.2 --- LPC CEPSTRAL COEFFICIENT --- p.13 / Chapter 3. --- MULTI-DIMENSIONAL ANALYSIS --- p.18 / Chapter 3.1 --- PURE GRAPHICAL TOOLS --- p.18 / Chapter 3.1.1 --- MULTI-HISTOGRAM --- p.18 / Chapter 3.1.2 --- STARS --- p.19 / Chapter 3.1.3 --- SPIKED SCATTERPLOT --- p.19 / Chapter 3.1.4 --- GLYPHS --- p.22 / Chapter 3.1.5 --- BOXES --- p.22 / Chapter 3.1.6 --- LIMITATIONS OF THE BASIC METHODS --- p.22 / Chapter 3.1.7 --- CHERNOFF FACES --- p.26 / Chapter 3.1.8 --- ANDREW'S CURVE --- p.27 / Chapter 3.1.9 --- LIMITATIONS OF CHERNOFF FACES AND ANDREW'S CURVE --- p.30 / Chapter 3.1.10 --- SCATTERED PLOT MATRIX --- p.30 / Chapter 3.1.11 --- PARALLEL-AXIS SYSTEM --- p.32 / Chapter 3.1.12 --- COMMON BASIC PITFALL --- p.33 / Chapter 3.2 --- PURE PROJECTION METHODS --- p.36 / Chapter 3.2.1 --- PRINCIPAL COMPONENTS ANALYSIS --- p.36 / Chapter 3.2.2 --- PRINCIPLE CO-ORDINATES ANALYSIS --- p.37 / Chapter 3.2.3 --- REGRESSION ANALYSIS --- p.38 / Chapter 3.3 --- SLICED INVERSE REGRESSION (SIR) --- p.41 / Chapter 4 --- DATA ANALYSIS --- p.50 / Chapter 4.1 --- PROGRAMS AND TEST DATA --- p.50 / Chapter 4.2 --- ACTUAL SPEECH DATA RESULTS --- p.63 / Chapter 4.2.1 --- "SINGLE UTTERANCE OF ""4"" BY SPEAKER A ONLY" --- p.66 / Chapter 4.2.2 --- "TWELVE UTTERANCES OF ""4"" BY SPEAKER A" --- p.72 / Chapter 4.2.3 --- "THREE UTTERANCES PER SPEAKER OF ""4"" BY SPEAKER A, B AND C" --- p.78 / Chapter 4.2.4 --- "TWO UTTERANCES PER DIGIT OF ""1"" TO ""9"" BY SPEAKER A" --- p.83 / Chapter 4.2.5 --- "ONE UTTERANCE PER DIGIT PER SPEAKER OF ""1"" TO ""9"" BY SPEAKER A,B,C" --- p.86 / CONCLUSION AND FURTHER WORKS --- p.93 / Chapter 5.1 --- CONCLUSION --- p.93 / Chapter 5.2 --- FURTHER WORKS --- p.94 / REFERENCES / APPENDIX I MATLAB PROGRAM LISTING FOR SIR / APPENDIX 2 C PROGRAM LISTING FOR ROTATIONAL VIEW / APPENDIX 3 C PROGRAM LISTING FOR LPC AND CEPSTRAL TRANSFORMS / "APPENDIX 4 ALL VIEWS, EIGENVALUES AND EIGENVECTORS FOR SINGLE UTTERANCE OF ""4"" BY SPEAKER A" / "APPENDIX 5 ALL VIEWS, EIGENVALUES AND EIGENVECTORS FOR 12 UTTERANCES OF ""4"" BY SPEAKER A" / "APPENDIX 6 ALL VIEWS, EIGENVALUES AND EIGENVECTORS FOR 5 UTTERANCES PER SPEAKER OF ""4"" BY SPEAKER A,B,C" / "APPENDIX 7 ALL VIEWS, EIGENVALUES AND EIGENVECTORS FOR 2 UTTERANCES PER DIGIT OF DIGIT ""l"" TO ""9"" BY SPEAKER A" / "APPENDIX 8 ALL VIEWS, EIGENVALUES AND EIGENVECTORS FOR 1UTTERANCE PER SPEAKER PER DIGIT OF ""1"" TO ""9"" BY SPEAKER A,B,C"

by Ge Gao. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1999. / Includes bibliographical references (leaves 101-107). / Text in English; abstracts in English and Chinese. / by Ge Gao. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Attributes of speech coders --- p.1 / Chapter 1.1.1 --- Bit rate --- p.2 / Chapter 1.1.2 --- Speech quality --- p.3 / Chapter 1.1.3 --- Complexity --- p.3 / Chapter 1.1.4 --- Delay --- p.4 / Chapter 1.1.5 --- Channel-error sensitivity --- p.4 / Chapter 1.2 --- Development of speech coding techniques --- p.5 / Chapter 1.3 --- Motivations and objectives --- p.7 / Chapter 2 --- Waveform interpolation speech model --- p.9 / Chapter 2.1 --- Overview of speech production model --- p.9 / Chapter 2.2 --- Linear prediction(LP) --- p.11 / Chapter 2.3 --- Linear-prediction based analysis-by-synthesis coding(LPAS) --- p.14 / Chapter 2.4 --- Sinusoidal model --- p.15 / Chapter 2.5 --- Mixed Excitation Linear Prediction(MELP) model --- p.16 / Chapter 2.6 --- Waveform interpolation model --- p.16 / Chapter 2.6.1 --- Principles of waveform interpolation model --- p.18 / Chapter 2.6.2 --- Outline of a WI coding system --- p.25 / Chapter 3 --- Pitch detection --- p.31 / Chapter 3.1 --- Overview of existing pitch detection methods --- p.31 / Chapter 3.2 --- Robust Algorithm for Pitch Tracking(RAPT) --- p.33 / Chapter 3.3 --- Modifications of RAPT --- p.37 / Chapter 4 --- Development of a 1.7kbps speech coder --- p.44 / Chapter 4.1 --- Architecture of the coder --- p.44 / Chapter 4.2 --- Encoding of unvoiced speech --- p.46 / Chapter 4.3 --- Encoding of voiced speech --- p.46 / Chapter 4.3.1 --- Generation of PCW --- p.48 / Chapter 4.3.2 --- Variable Dimensional Vector Quantization(VDVQ) --- p.53 / Chapter 4.3.3 --- Sparse frequency representation(SFR) of speech --- p.56 / Chapter 4.3.4 --- Sample selective linear prediction (SSLP) --- p.58 / Chapter 4.4 --- Practical implementation issues --- p.60 / Chapter 5 --- Development of a 2.0kbps speech coder --- p.67 / Chapter 5.1 --- Features of the coder --- p.67 / Chapter 5.2 --- Postfiltering --- p.75 / Chapter 5.3 --- Voice activity detection(VAD) --- p.76 / Chapter 5.4 --- Performance evaluation --- p.79 / Chapter 6 --- Conclusion --- p.85 / Chapter A --- Subroutine for pitch detection algorithm --- p.88 / Chapter B --- Subroutines for Pitch Cycle Waveform(PCW) generation --- p.96 / Chapter B.1 --- The main subroutine --- p.96 / Chapter B.2 --- Subroutine for peak picking algorithm --- p.98 / Chapter B.3 --- Subroutine for encoding the residue (using VDVQ) --- p.99 / Chapter B.4 --- Subroutine for synthesizing PCW from its residue --- p.100 / Bibliography --- p.101

Law Ka Man = 利用子音節的粤語文語轉換系統 / 羅家文. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2001. / Includes bibliographical references. / Text in English; abstracts in English and Chinese. / Law Ka Man = Li yong zi yin jie de Yue yu wen yu zhuan huan xi tong / Luo Jiawen. / Chapter 1. --- INTRODUCTION --- p.1 / Chapter 1.1 --- Text analysis --- p.2 / Chapter 1.2 --- Prosody prediction --- p.3 / Chapter 1.3 --- Speech generation --- p.3 / Chapter 1.4 --- The trend of TTS technology --- p.5 / Chapter 1.5 --- TTS systems for different languages --- p.6 / Chapter 1.6 --- Objectives of the thesis --- p.8 / Chapter 1.7 --- Thesis outline --- p.8 / References --- p.10 / Chapter 2. --- BACKGROUND --- p.11 / Chapter 2.1 --- Cantonese phonology --- p.11 / Chapter 2.2 --- Cantonese TTS - a baseline system --- p.16 / Chapter 2.3 --- Time-Domain Prrch-Synchronous-OverLap-Add --- p.17 / Chapter 2.3.1 --- "From, speech signal to short-time analysis signals" --- p.18 / Chapter 2.3.2 --- From short-time analysis signals to short-time synthesis signals --- p.19 / Chapter 2.3.3 --- From short-time synthesis signals to synthetic speech --- p.20 / Chapter 2.4 --- Time-scale and Pitch-scale modifications --- p.20 / Chapter 2.4.1 --- Voiced speech --- p.20 / Chapter 2.4.2 --- Unvoiced speech --- p.21 / Chapter 2.5 --- Summary --- p.22 / References --- p.23 / Chapter 3. --- SUB-SYLLABLE BASED TTS SYSTEM --- p.24 / Chapter 3.1 --- Motivations --- p.24 / Chapter 3.2 --- Choices of synthesis units --- p.27 / Chapter 3.2.1 --- Sub-syllable unit --- p.29 / Chapter 3.2.2 --- "Diphones, demi-syllables and sub-syllable units" --- p.31 / Chapter 3.3 --- Proposed TTS system --- p.32 / Chapter 3.3.1 --- Text analysis module --- p.33 / Chapter 3.3.2 --- Synthesis module --- p.36 / Chapter 3.3.3 --- Prosody module --- p.37 / Chapter 3.4 --- Summary --- p.38 / References --- p.39 / Chapter 4. --- ACOUSTIC INVENTORY --- p.40 / Chapter 4.1 --- The full set of Cantonese sub-syllable units --- p.40 / Chapter 4.2 --- A reduced set of sub-syllable units --- p.42 / Chapter 4.3 --- Corpus design --- p.44 / Chapter 4.4 --- Recording --- p.46 / Chapter 4.5 --- Post-processing of speech data --- p.47 / Chapter 4.6 --- Summary --- p.51 / References --- p.51 / Chapter 5. --- CONCATENATION TECHNIQUES --- p.52 / Chapter 5.1 --- Concatenation of sub-syllable units --- p.52 / Chapter 5.1.1 --- Concatenation of plosives and affricates --- p.54 / Chapter 5.1.2 --- Concatenation of fricatives --- p.55 / Chapter 5.1.3 --- "Concatenation of vowels, semi-vowels and nasals" --- p.55 / Chapter 5.1.4 --- Spectral distance measure --- p.57 / Chapter 5.2 --- Waveform concatenation method --- p.58 / Chapter 5.3 --- Selected examples of waveform concatenation --- p.59 / Chapter 5.3.1 --- I-I concatenation --- p.60 / Chapter 5.3.2 --- F-F concatenation --- p.66 / Chapter 5.4 --- Summary --- p.71 / References --- p.72 / Chapter 6. --- PERFORMANCE EVALUATION --- p.73 / Chapter 6.1 --- Listening test --- p.73 / Chapter 6.2 --- Test results： --- p.74 / Chapter 6.3 --- Discussions --- p.75 / References --- p.78 / Chapter 7. --- CONCLUSIONS & FUTURE WORKS --- p.79 / Chapter 7.1 --- Conclusions --- p.79 / Chapter 7.2 --- Suggested future work --- p.81 / APPENDIX 1 SYLLABLE DURATION --- p.82 / APPENDIX 2 PERCEPTUAL TEST PARAGRAPHS --- p.86

Fung Tien Ying. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2001. / Includes bibliographical references (leaves 119-128). / Abstracts in English and Chinese. / Abstract --- p.1 / Acknowledgement --- p.1 / List of Figures --- p.7 / List of Tables --- p.11 / Chapter 1 --- Introduction --- p.14 / Chapter 1.1 --- General Trends on Speech Generation --- p.15 / Chapter 1.2 --- Domain-Optimized Speech Generation in Chinese --- p.16 / Chapter 1.3 --- Thesis Organization --- p.17 / Chapter 2 --- Background --- p.19 / Chapter 2.1 --- Linguistic and Phonological Properties of Chinese --- p.19 / Chapter 2.1.1 --- Articulation --- p.20 / Chapter 2.1.2 --- Tones --- p.21 / Chapter 2.2 --- Previous Development in Speech Generation --- p.22 / Chapter 2.2.1 --- Articulatory Synthesis --- p.23 / Chapter 2.2.2 --- Formant Synthesis --- p.24 / Chapter 2.2.3 --- Concatenative Synthesis --- p.25 / Chapter 2.2.4 --- Existing Systems --- p.31 / Chapter 2.3 --- Our Speech Generation Approach --- p.35 / Chapter 3 --- Corpus-based Syllable Concatenation: A Feasibility Test --- p.37 / Chapter 3.1 --- Capturing Syllable Coarticulation with Distinctive Features --- p.39 / Chapter 3.2 --- Creating a Domain-Optimized Wavebank --- p.41 / Chapter 3.2.1 --- Generate-and-Filter --- p.44 / Chapter 3.2.2 --- Waveform Segmentation --- p.47 / Chapter 3.3 --- The Use of Multi-Syllable Units --- p.49 / Chapter 3.4 --- Unit Selection for Concatenative Speech Output --- p.50 / Chapter 3.5 --- A Listening Test --- p.51 / Chapter 3.6 --- Chapter Summary --- p.52 / Chapter 4 --- Scalability and Portability to the Stocks Domain --- p.55 / Chapter 4.1 --- Complexity of the ISIS Responses --- p.56 / Chapter 4.2 --- XML for input semantic and grammar representation --- p.60 / Chapter 4.3 --- Tree-Based Filtering Algorithm --- p.63 / Chapter 4.4 --- Energy Normalization --- p.67 / Chapter 4.5 --- Chapter Summary --- p.69 / Chapter 5 --- Investigation in Tonal Contexts --- p.71 / Chapter 5.1 --- The Nature of Tones --- p.74 / Chapter 5.1.1 --- Human Perception of Tones --- p.75 / Chapter 5.2 --- Relative Importance of Left and Right Tonal Context --- p.77 / Chapter 5.2.1 --- Tonal Contexts in the Date-Time Subgrammar --- p.77 / Chapter 5.2.2 --- Tonal Contexts in the Numeric Subgrammar --- p.82 / Chapter 5.2.3 --- Conclusion regarding the Relative Importance of Left versus Right Tonal Contexts --- p.86 / Chapter 5.3 --- Selection Scheme for Tonal Variants --- p.86 / Chapter 5.3.1 --- Listening Test for our Tone Backoff Scheme --- p.90 / Chapter 5.3.2 --- Error Analysis --- p.92 / Chapter 5.4 --- Chapter Summary --- p.94 / Chapter 6 --- Summary and Future Work --- p.95 / Chapter 6.1 --- Contributions --- p.97 / Chapter 6.2 --- Future Directions --- p.98 / Chapter A --- Listening Test Questionnaire for FOREX Response Genera- tion --- p.100 / Chapter B --- Major Response Types For ISIS --- p.102 / Chapter C --- Recording Corpus for Tone Investigation in Date-time Sub- grammar --- p.105 / Chapter D --- Statistical Test for Left Tonal Context --- p.109 / Chapter E --- Statistical Test for Right Tonal Context --- p.112 / Chapter F --- Listening Test Questionnaire for Backoff Unit Selection Scheme --- p.115 / Chapter G --- Statistical Test for the Backoff Unit Selection Scheme --- p.117 / Chapter H --- Statistical Test for the Backoff Unit Selection Scheme --- p.118 / Bibliography --- p.119

Kwan Ka Yan. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2002. / Includes bibliographical references. / Abstracts in English and Chinese. / Chapter 1. --- Introduction --- p.1 / Chapter 1.1. --- Automatic Speech Recognition --- p.1 / Chapter 1.2. --- Robustness of ASR Systems --- p.3 / Chapter 1.3. --- Model Adaptation for Robust ASR --- p.4 / Chapter 1.4. --- Thesis outline --- p.6 / References --- p.8 / Chapter 2. --- Fundamentals of Continuous Speech Recognition --- p.10 / Chapter 2.1. --- Acoustic Front-End --- p.10 / Chapter 2.2. --- Recognition Module --- p.11 / Chapter 2.2.1. --- Acoustic Modeling with HMM --- p.12 / Chapter 2.2.2. --- Basic Phonology of Cantonese --- p.14 / Chapter 2.2.3. --- Acoustic Modeling for Cantonese --- p.15 / Chapter 2.2.4. --- Language Modeling --- p.16 / References --- p.17 / Chapter 3. --- Unsupervised Model Adaptation --- p.18 / Chapter 3.1. --- A General Review of Model Adaptation --- p.18 / Chapter 3.1.1. --- Supervised and Unsupervised Adaptation --- p.20 / Chapter 3.1.2. --- N-Best Adaptation --- p.22 / Chapter 3.2. --- MAP --- p.23 / Chapter 3.3. --- MLLR --- p.25 / Chapter 3.3.1. --- Adaptation Approach --- p.26 / Chapter 3.3.2. --- Estimation of MLLR regression matrices --- p.27 / Chapter 3.3.3. --- Least Mean Squares Regression --- p.29 / Chapter 3.3.4. --- Number of Transformations --- p.30 / Chapter 3.4. --- Experiment Results --- p.32 / Chapter 3.4.1. --- Standard MLLR versus LMS MLLR --- p.36 / Chapter 3.4.2. --- Effect of the Number of Transformations --- p.43 / Chapter 3.4.3. --- MAP Vs. MLLR --- p.46 / Chapter 3.5. --- Conclusions --- p.48 / Referencesxlix / Chapter 4. --- Use of Confidence Measure for MLLR based Adaptation --- p.50 / Chapter 4.1. --- Introduction to Confidence Measure --- p.50 / Chapter 4.2. --- Confidence Measure Based on Word Density --- p.51 / Chapter 4.3. --- Model-level confidence measure --- p.53 / Chapter 4.4. --- Integrating Confusion Information into Confidence Measure --- p.55 / Chapter 4.5. --- Adaptation Data Distributions in Different Confidence Measures..… --- p.57 / References --- p.65 / Chapter 5. --- Experimental Results and Analysis --- p.66 / Chapter 5.1. --- Supervised Adaptation --- p.67 / Chapter 5.2. --- Cheated Confidence Measure --- p.69 / Chapter 5.3. --- Confidence Measures of Different Levels --- p.71 / Chapter 5.4. --- Incorporation of Confusion Matrix --- p.81 / Chapter 5.5. --- Conclusions --- p.83 / Chapter 6. --- Conclusions --- p.35 / Chapter 6.1. --- Future Works --- p.88