Muutke küpsiste eelistusi

Language Identification Using Spectral and Prosodic Features 2015 ed. [Pehme köide]

, ,
  • Formaat: Paperback / softback, 98 pages, kõrgus x laius: 235x155 mm, kaal: 1825 g, 5 Illustrations, color; 16 Illustrations, black and white; XI, 98 p. 21 illus., 5 illus. in color., 1 Paperback / softback
  • Sari: SpringerBriefs in Speech Technology
  • Ilmumisaeg: 09-Apr-2015
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319171623
  • ISBN-13: 9783319171623
Teised raamatud teemal:
  • Pehme köide
  • Hind: 48,70 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 57,29 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Language Identification Using Spectral and Prosodic Features 2015 ed.Suurem pilt
  • Formaat: Paperback / softback, 98 pages, kõrgus x laius: 235x155 mm, kaal: 1825 g, 5 Illustrations, color; 16 Illustrations, black and white; XI, 98 p. 21 illus., 5 illus. in color., 1 Paperback / softback
  • Sari: SpringerBriefs in Speech Technology
  • Ilmumisaeg: 09-Apr-2015
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319171623
  • ISBN-13: 9783319171623
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9783319171623.html
Märksõnad:
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.
1 Introduction 1(12)
1.1 Introduction
1(1)
1.2 Cues for Language Identification
2(4)
1.3 Types of Language Identification Systems
6(1)
1.3.1 Explicit LID Systems
6(1)
1.3.2 Implicit LID Systems
7(1)
1.4 Challenging Issues in Automatic Language Identification
7(1)
1.5 Objective and Scope of the Book
8(1)
1.6 Issues Addressed in the Book
9(1)
1.7 Organization of the Book
10(1)
References
10(3)
2 Literature Review 13(14)
2.1 Introduction
13(1)
2.2 Review of Explicit LID Systems
14(3)
2.3 Review of Implicit LID Systems
17(3)
2.4 Reasons for Attraction Towards Implicit LID Systems
20(1)
2.5 Motivation for the Present Work
21(1)
2.6 Summary and Conclusions
22(1)
References
22(5)
3 Language Identification Using Spectral Features 27(28)
3.1 Introduction
27(1)
3.2 Speech Databases
28(3)
3.2.1 Indian Institute of Technology Kharagpur Multi-lingual Indian Language Speech Corpus (IITKGP-MLILSC)
28(2)
3.2.2 Oregon Graduate Institute Database Multi-language Telephone-Based Speech (OGI-MLTS)
30(1)
3.3 Features Used for Automatic Language Identification
31(1)
3.4 Development of Language Models
32(1)
3.5 LID Performance on Indian Language Database (IITKGP-MLILSC)
33(9)
3.5.1 Speaker Dependent LID System
33(1)
3.5.2 Speaker Independent LID System
34(3)
3.5.3 Speaker Independent LID System with Speaker Specific Language Models
37(5)
3.6 LID System Using Spectral Features from Pitch Synchronous Analysis (PSA) and Glottal Closure Regions (GCRs)
42(9)
3.6.1 Epoch Extraction Using Zero Frequency Filter Method
46(1)
3.6.2 Extraction of the Spectral Features from PSA and GCRs
47(2)
3.6.3 Performance Evaluation
49(2)
3.7 Performance of Proposed Spectral Features on OGI-MLTS Database
51(1)
3.8 Summary and Conclusions
52(1)
References
52(3)
4 Language Identification Using Prosodic Features 55(28)
4.1 Introduction
55(1)
4.2 Extraction of CV Units from Continuous Speech
56(6)
4.3 Prosodic Differences Among Languages
62(1)
4.4 Extraction of Intonation, Rhythm and Stress (IRS) Features from Syllable and Word Levels
62(6)
4.4.1 Intonation
63(3)
4.4.2 Rhythm
66(1)
4.4.3 Stress
67(1)
4.5 Performance Evaluation Using Syllable and Word Level Prosodic Features
68(1)
4.6 Extraction of Prosodic Features from Global Level
69(2)
4.6.1 ΔF0 Contour
70(1)
4.6.2 Duration Contour
70(1)
4.6.3 ΔE Contour
70(1)
4.7 Performance Evaluation Using Global Level Prosodic Features
71(1)
4.8 Performance Evaluation Using Prosodic Features on OGI-MLTS Database
71(2)
4.9 LID Using Combination of Features
73(7)
4.9.1 Performance of LID System Using IRS Features from Syllable and Word Levels
75(1)
4.9.2 Performance of LID System Using Prosodic Features from Syllable, Word and Global Level
75(2)
4.9.3 Performance of LID System Using Spectral and Prosodic Features
77(3)
4.10 Summary and Conclusions
80(1)
References
80(3)
5 Summary and Conclusions 83(4)
5.1 Summary of the Book
83(1)
5.2 Major Contributions of the Book
84(1)
5.3 Scope for Future Work
85(1)
References
86(1)
Appendix A: LPCC Features 87(2)
Appendix B: MFCC Features 89(4)
Appendix C: Gaussian Mixture Model (GMM) 93