| |
| |
| Contributor Biographies | |
| |
| |
| Foreword | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Language Characteristics | |
| |
| |
| |
| |
| Languages and Dialects | |
| |
| |
| |
| Linguistic Description and Classification | |
| |
| |
| |
| Language in Context | |
| |
| |
| |
| Writing Systems | |
| |
| |
| |
| Languages and Speech Technology | |
| |
| |
| |
| Linguistic Data Resources | |
| |
| |
| |
| |
| Demands and Challenges of Multilingual Data-Collection Efforts | |
| |
| |
| |
| International Efforts and Cooperation | |
| |
| |
| |
| Data Collection Efforts in the United States | |
| |
| |
| |
| Data Collection Efforts in Europe | |
| |
| |
| |
| Overview Existing Language Resources in Europe | |
| |
| |
| |
| Multilingual Acoustic Modeling | |
| |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Problems and Challenges | |
| |
| |
| |
| Language Independent Sound Inventories and Representations | |
| |
| |
| |
| Acoustic Model Combination | |
| |
| |
| |
| Insights and Open Problems | |
| |
| |
| |
| Multilingual Dictionaries | |
| |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Multilingual Dictionaries | |
| |
| |
| |
| What Is a Word? | |
| |
| |
| |
| Vocabulary Selection | |
| |
| |
| |
| How to Generate Pronunciations | |
| |
| |
| |
| Discussion | |
| |
| |
| |
| Multilingual Language Modeling | |
| |
| |
| |
| |
| Statistical Language Modeling | |
| |
| |
| |
| Model Estimation for New Domains and Speaking Styles | |
| |
| |
| |
| Crosslingual Comparisons: A Language Modeling Perspective | |
| |
| |
| |
| Crosslinguistic Bootstrapping for Language Modeling | |
| |
| |
| |
| Language Models for Truly Multilingual Speech Recognition | |
| |
| |
| |
| Discussion and Concluding Remarks | |
| |
| |
| |
| Multilingual Speech Synthesis | |
| |
| |
| |
| |
| Background | |
| |
| |
| |
| Building Voices in New Languages | |
| |
| |
| |
| Database Design | |
| |
| |
| |
| Prosodic Modeling | |
| |
| |
| |
| Lexicon Building | |
| |
| |
| |
| Non-native Spoken Output | |
| |
| |
| |
| Summary | |
| |
| |
| |
| Automatic Language Identification | |
| |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Human Language Identification | |
| |
| |
| |
| Databases and Evaluation Methods | |
| |
| |
| |
| The Probabilistic LID Framework | |
| |
| |
| |
| Acoustic Approaches | |
| |
| |
| |
| Phonotactic Modeling | |
| |
| |
| |
| Prosodic LID | |
| |
| |
| |
| LVCSR-Based LID | |
| |
| |
| |
| Trends and Open Problems in LID | |
| |
| |
| |
| Other Challenges: Non-native Speech, Dialects, Accents, and Local Interfaces | |
| |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Characteristics of Non-native Speech | |
| |
| |
| |
| Corpus Analysis | |
| |
| |
| |
| Acoustic Modeling Approaches for Non-native Speech | |
| |
| |
| |
| Adapting to Non-native Accents in ASR | |
| |
| |
| |
| Combining Speaker and Pronunciation Adaptation | |
| |
| |
| |
| Cross-Dialect Recognition of Native Dialects | |
| |
| |
| |
| Applications | |
| |
| |
| |
| Other Factors in Localizing Speech-Based Interfaces | |
| |
| |
| |
| Summary | |
| |
| |
| |
| Speech-to-Speech Translation | |
| |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Statistical and Interlingua-Based Speech Translation Approaches | |
| |
| |
| |
| Coupling Speech Recognition and Translation | |
| |
| |
| |
| Portable Speech-to-Speech Translation: The ATR System | |
| |
| |
| |
| Conclusion | |
| |
| |
| |
| Multilingual Spoken Dialog Systems | |
| |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Previous Work | |
| |
| |
| |
| Overview of the ISIS System | |
| |
| |
| |
| Adaptivity to Knowledge Scope Expansion | |
| |
| |
| |
| Delegation to Software Agents | |
| |
| |
| |
| Interruptions and Multithreaded Dialogs | |
| |
| |
| |
| Empirical Observations on User Interaction with ISIS | |
| |
| |
| |
| Implementation of Multilingual SDS in VXML | |
| |
| |
| |
| Summary and Conclusions | |
| |
| |
| Bibliography | |
| |
| |
| Index | |