内容介绍

内容简介语音韵律在言语交际中不仅传递语法语义等信息，而且传递副语言信息以及说话人的非语言信息。语音韵律不仅是语言学的重要课题，而且有效的韵律信息处理方法对语音技术系统性能的提升十分关键。本书选自作者近年来关于语音韵律研究的论文，系统考察了字调、声调协同发音、时长与节奏、句调、韵律结构、焦点重音、情感表达等各个层面的韵律特征，特别突出了定量建模的研究方法。研究对象以普通话和粤语为主，涉及多种汉语方言，包含跨语言对比及语言接触的研究。

作者介绍

顾文涛，江苏扬州人。

上海交通大学通信与信息系统专业工学博士，日本东京大学博士后。现任南京师范大学文学院语言科技系特聘教授、博士生导师。曾在美国贝尔实验室访学，曾任日本东京大学JSPS外国人特别研究员、香港中文大学副研究员。主要研究方向为实验语音学与语音信息处理，特别是语音韵律的分析和建模。在Phonetica, IEEETransactions on Audio Speechand Language Processing,Speech Communication,IEICE Transactions onInformation and Systems等国际权威期刊以及INTERSPEECH, ICPhS,ICASSP ISCSLP SpeechProsody等重要国际会议上发表论文40余篇。现主持国家社科基金项目、国家社科基金重大招标项目子课题、江苏省社会科学基金项目、江苏高校哲学社会科学重点研究基地重大项目各l项。

编辑推荐

《语音韵律的实验分析与建模》由世界图书出版公司出版。

目录

PART Ⅰ SPEAKER ADAPTATION FOR DURTION MODEL IN MANDARIN TEXT-TO-SPEECH SYNTHESIS Introduction 1.1 Introduction to Duration Modeling in TTS Systems 1. 1. 1 Text-to-Speech Synthesis and Segmental Duration 1.1.2 Duration Model 1.2 Speaker Adaptation for Duration Model-Goal and Basic Assumption 1.3 The Source Model for Mandarin Duration 1.3. 1 Phone Categorization 1.3.2 Multiplicative Model 1.3.3 Duration Factors Model-Based Optimal Text Selection 2. 1 Introduction 2.2 Coverage and Statistical Model 2.3 Model-Based Greedy Text Selection 2.3.1 Analysis-of-Variance Model 2.3.2 Design Matrix and Parameter Estimability 2.3.3 Matroid Cover Problem 2.3.4 Model-Based Greedy Algorithm 2.4 Multi-Model Based Greedy Algorithm 2.4. 1 Modified Algorithm for Multi-Model Cases 2.4.2 Experimental Result 2.4.3 Analysis of Computational Complexity 2.5 Further Generalization of the Algorithm 2.6 Experimental Result and Discussion 2.7 Conclusion 3 Speech Data 3.1 Speech Recording 3.2 Segmentation and Labeling 3.3 Data Analysis 4 Analysis of Multi-Speaker Mandarin Duration Models 4. 1 Statistical Analysis 4.2 Mu]tiplicative Mode] Fitting 4.3 Effects of Factors in Duration Models 4.3. 1 Vowel 4. 3.2 Plosive Burst and Aspiration 4. 3.3 Plosive Closure 4.3.4 Nasal Coda 4.3.5 Fricative 4.3.6 Sonorant Consonant 4.3.7 Common Effects across Phone Categories 4.4 Compensatory Effects 4.4. 1 Burst/Aspiration and Closure of Plosives 4.4.2 Vowel and Nasal Coda 4.4.3 Obstruent and Vowel 4.4.4 Obstruent and Glide 4.4.5 Syllabic Compensatory Effects 4.5 Syllable Duration 5 Speaker Adaptation for Duration Modeling 5.1 An Efficient Speaker Adaptation Model 5.1.1 Target Model Assumption 5.1.2 Validity of Scalable Hypothesis 5.1.3 Theoretic Analysis of Model Estimation 5.1.4 Model Fitting by Linear Regression 5.1.5 Sentence Effect on Model Estimation 5. 1.6 Analysis of Model Robustness 5.2 Comparison of Different Adaptation Models 5.2.1 Candidate Models 5.2.2 Comparison of Models 5.2.3 Conclusion 6 Effect of Speaking Rate on Duration Model 6. 1 Inherent Speaking Rate Variability 6.2 Duration Model at Different Speaking Rates 6.2. 1 Analysis of Duration Data at Different Speaking Rates 6.2.2 Duration Effects across Speaking Rates 6.2.3 Model Adaptation for Different Speaking Rates 7 Summary References PART Ⅱ QUANTITATIVE ANALYSIS AND MODELING OF TONAL AND INTONATIONAL VARIATIONS ON VARIOUS LAYERS 8 Automatic Extraction of Tone Command Parameters for the Model of F, Contour Generation for Standard Chinese 8. 1 Introduction 8.2 The Command-Response Model for Standard Chinese 8.3 Parameter Extraction Method 8.4 First-Order Estimation of Tone Command Parameters 8.4. 1 Problem Analysis 8.4.2 Tone Command Pattern Recognition 8.5 Experiment 8.6 Conclusion 9 A General Approach for Automatic Extraction of Tone Commands in the Command-Response Model for Tone Languages 9. 1 Introduction 9.2 The Command-Response Model for Tone Languages 9.3 Overall Framework for Command Extraction 9.4 First-Order Estimation of Tone Commands 9.4. 1 Why a Difficult Task? 9.4.2 Recognition of Tone Command Patterns 9.4.3 Estimation of Timing/Amplitude of Tone Commands 9.4.4 Back-Tracing Correction 9.5 Experimental Results 10 Analysis of Tones in Cantonese Speech Based on the Command- Response Model for the Process of Fo Contour Generation 10. 1 Introduction 10.2 Cantonese Tone System 10.3 The Approach Based on the Command-Response Model 10.3.1 The Command-Response Model 10. 3.2 The Framework of the Present Approach 10.4 Speech Data 10.5 Modeling Fo Contours of Cantonese Utterances 10.5.1 Tone Command Patterns for Lexical Tones 10.5.2 Tone Command Patterns for Changed Tones 10.5.3 Model-Based Analysis of Continuous F0 Contours 10.6 Quantitative Analysis of Command Parameters 10.6. 1 Tone Command Parameters in Controlled Context 10.6.2 Tone Command Parameters in Arbitrary Context 10.6. 3 Phrase Command Parameters lO. 7 Synthesis and Perceptual Evaluation of F0 Contours of Cantonese Utterances 10.7.1 Test 1-Tone Identification 10.7.2 Test 2-Naturalness Evaluation 10. 8 Discussion and Conclusion 11 Analysis of Tones in Shanghainese Based on the Command-Response Model 11. 1 Introduction 11.2 Shanghainese Tone System ……

作者简介

顾文涛，江苏扬州人。上海交通大学通信与信息系统专业工学博士，日本东京大学博士后。现任南京师范大学文学院语言科技系特聘教授、博士生导师。曾在美国贝尔实验室访学，曾任日本东京大学JSPS外国人特别研究员、香港中文大学副研究员。主要研究方向为实验语音学与语音信息处理，特别是语音韵律的分析和建模。在Phonetica,IEEETransactions on Audio Speechand Language Processing,Speech Communication,IEICE Transactions on Information and Systems等国际权威期刊以及INTERSPEECH， ICPhS,ICASSP ISCSLP SpeechProsody等重要国际会议上发表论文40余篇。现主持国家社科基金项目、国家社科基金重大招标项目子课题、江苏省社会科学基金项目、江苏高校哲学社会科学重点研究基地重大项目各1项。