Title Language identification using spectral and prosodic features / K. Sreenivasa Rao, V. Ramu Reddy, Sudhamay Maity

Published Cham : Springer, [2015] ©2015

Click on the following:
Springer Engineering eBooks
Springer eBooks

Copies

Description 1 online resource Series Springer briefs in electrical and computer engineering, 2191-8120 Speech technology, 2191-7388 SpringerBriefs in electrical and computer engineering. SpringerBriefs in electrical and computer engineering. Speech technology Contents 880-01 Introduction.- Literature Review -- Language Identification using Spectral Features -- Language Identification using Prosodic Features -- Summary and Conclusions -- Appendix A: LPCC Features -- Appendix B: MFCC Features -- Appendix C: Gaussian Mixture Model (GMM) 880-01/(S Machine generated contents note: 1.1. Introduction -- 1.2. Cues for Language Identification -- 1.3. Types of Language Identification Systems -- 1.3.1. Explicit LID Systems -- 1.3.2. Implicit LID Systems -- 1.4. Challenging Issues in Automatic Language Identification -- 1.5. Objective and Scope of the Book -- 1.6. Issues Addressed in the Book -- 1.7. Organization of the Book -- References -- 2.1. Introduction -- 2.2. Review of Explicit LID Systems -- 2.3. Review of Implicit LID Systems -- 2.4. Reasons for Attraction Towards Implicit LID Systems -- 2.5. Motivation for the Present Work -- 2.6. Summary and Conclusions -- References -- 3.1. Introduction -- 3.2. Speech Databases -- 3.2.1. Indian Institute of Technology Kharagpur Multi-lingual Indian Language Speech Corpus (IITKGP-MLILSC) -- 3.2.2. Oregon Graduate Institute Database Multi-language Telephone-Based Speech (OGI-MLTS) -- 3.3. Features Used for Automatic Language Identification -- 3.4. Development of Language Models -- 3.5. LID Performance on Indian Language Database (IITKGP-MLILSC) -- 3.5.1. Speaker Dependent LID System -- 3.5.2. Speaker Independent LID System -- 3.5.3. Speaker Independent LID System with Speaker Specific Language Models -- 3.6. LID System Using Spectral Features from Pitch Synchronous Analysis (PSA) and Glottal Closure Regions (GCRs) -- 3.6.1. Epoch Extraction Using Zero Frequency Filter Method -- 3.6.2. Extraction of the Spectral Features from PSA and GCRs -- 3.6.3. Performance Evaluation -- 3.7. Performance of Proposed Spectral Features on OGI-MLTS Database -- 3.8. Summary and Conclusions -- References -- 4.1. Introduction -- 4.2. Extraction of CV Units from Continuous Speech -- 4.3. Prosodic Differences Among Languages -- 4.4. Extraction of Intonation, Rhythm and Stress (IRS) Features from Syllable and Word Levels -- 4.4.1. Intonation -- 4.4.2. Rhythm -- 4.4.3. Stress -- 4.5. Performance Evaluation Using Syllable and Word Level Prosodic Features -- 4.6. Extraction of Prosodic Features from Global Level -- 4.6.1. ΔF0 Contour -- 4.6.2. Duration Contour -- 4.6.3. ΔE Contour -- 4.7. Performance Evaluation Using Global Level Prosodic Features -- 4.8. Performance Evaluation Using Prosodic Features on OGI-MLTS Database -- 4.9. LID Using Combination of Features -- 4.9.1. Performance of LID System Using IRS Features from Syllable and Word Levels -- 4.9.2. Performance of LID System Using Prosodic Features from Syllable, Word and Global Level -- 4.9.3. Performance of LID System Using Spectral and Prosodic Features -- 4.10. Summary and Conclusions -- References -- 5.1. Summary of the Book -- 5.2. Major Contributions of the Book -- 5.3. Scope for Future Work -- References Summary This book discusses the impact of spectral features extracted from frame level, glottal closure regions, and pitch-synchronous analysis on the performance of language identification systems. In addition to spectral features, the authors explore prosodic features such as intonation, rhythm, and stress features for discriminating the languages. They present how the proposed spectral and prosodic features capture the language specific information from two complementary aspects, showing how the development of language identification (LID) system using the combination of spectral and prosodic features will enhance the accuracy of identification as well as improve the robustness of the system. This book provides the methods to extract the spectral and prosodic features at various levels, and also suggests the appropriate models for developing robust LID systems according to specific spectral and prosodic features. Finally, the book discuss about various combinations of spectral and prosodic features, and the desired models to enhance the performance of LID systems Analysis taal language computertechnieken computer techniques taalwetenschappen linguistics engineering beeldverwerking image processing spraak speech Engineering (General) Techniek (algemeen) Bibliography Includes bibliographical references Notes Online resource; title from PDF title page (Ebsco, viewed April 8, 2015) Subject Linguistic analysis (Linguistics) Natural language & machine translation. Computational linguistics. Imaging systems & technology. FOREIGN LANGUAGE STUDY -- Indic Languages. Linguistic analysis (Linguistics) SUBJECT India -- Languages -- Prosodic analysis India -- Languages -- Spectral analysis Subject India Form Electronic book Author Reddy, V. Ramu, author Maity, Sudhamay, author ISBN 9783319171630 3319171631 3319171623 9783319171623

  Permalink