Human language technologies for under-resourced African languages : design, challenges, and prospects /: design, challenges, and prospects. (2018)
- Record Type:
- Book
- Title:
- Human language technologies for under-resourced African languages : design, challenges, and prospects /: design, challenges, and prospects. (2018)
- Main Title:
- Human language technologies for under-resourced African languages : design, challenges, and prospects
- Further Information:
- Note: Moses Effiong Ekpenyong, editor.
- Editors:
- Ekpenyong, Moses Effiong
- Contents:
- Intro; Foreword; Preface; Contents; About the Author; Chapter 1: Adaptive Template-Based Front End for Tone Language Speech Synthesis; 1.1 Introduction; 1.2 Speech Synthesis: The Problem; 1.3 TTS System Front End; 1.3.1 Rule-Based (RB) Vs. Data-Driven (DD); 1.3.2 The Ibibio Language; 1.3.2.1 Phonological Structure; 1.3.3 Utterance Database; 1.3.3.1 Ibibio TTS Utterance Processing; 1.3.4 Context Features Modeling; 1.3.5 HTS Label Generation; 1.3.6 HTS Question File; 1.4 NLP Modules; 1.4.1 Important Folders and Data Files; 1.4.2 Required Scripts; 1.4.3 Running the Front End; Appendix. 2.3.4 Phonology: Implications for Language/Speech Technology2.4 Methodology; 2.4.1 System Architecture; 2.4.2 Utterance Dataset; 2.4.3 Participants/Speakers Selection for Speech Recording â#x80;#x93; Speech Signal Dataset; 2.4.3.1 Participants/Speakers Selection; 2.4.3.2 Speech Recording: Environment, Instrument, Sessions; 2.4.3.3 Speech Signal Dataset; 2.4.4 Speech Feature Extraction; 2.4.4.1 Prosodic Feature Extraction; 2.4.4.2 Spectro-Temporal Feature Extraction; 2.4.4.3 Speech Feature Dataset; 2.5 Results; 2.5.1 Frame-by-Frame Analysis; 2.5.2 Principal Component Analysis. 2.5.2.1 Results of Duration Components Analysis2.5.3 SOM Clustering and Visualization; 2.5.3.1 Results of SOM Clustering; 2.5.3.2 Results of Component Plane Visualization; 2.6 Conclusion and Future Research Direction; References; Chapter 3: Towards Ontology-Driven Application for Multilingual Speech LanguageIntro; Foreword; Preface; Contents; About the Author; Chapter 1: Adaptive Template-Based Front End for Tone Language Speech Synthesis; 1.1 Introduction; 1.2 Speech Synthesis: The Problem; 1.3 TTS System Front End; 1.3.1 Rule-Based (RB) Vs. Data-Driven (DD); 1.3.2 The Ibibio Language; 1.3.2.1 Phonological Structure; 1.3.3 Utterance Database; 1.3.3.1 Ibibio TTS Utterance Processing; 1.3.4 Context Features Modeling; 1.3.5 HTS Label Generation; 1.3.6 HTS Question File; 1.4 NLP Modules; 1.4.1 Important Folders and Data Files; 1.4.2 Required Scripts; 1.4.3 Running the Front End; Appendix. 2.3.4 Phonology: Implications for Language/Speech Technology2.4 Methodology; 2.4.1 System Architecture; 2.4.2 Utterance Dataset; 2.4.3 Participants/Speakers Selection for Speech Recording â#x80;#x93; Speech Signal Dataset; 2.4.3.1 Participants/Speakers Selection; 2.4.3.2 Speech Recording: Environment, Instrument, Sessions; 2.4.3.3 Speech Signal Dataset; 2.4.4 Speech Feature Extraction; 2.4.4.1 Prosodic Feature Extraction; 2.4.4.2 Spectro-Temporal Feature Extraction; 2.4.4.3 Speech Feature Dataset; 2.5 Results; 2.5.1 Frame-by-Frame Analysis; 2.5.2 Principal Component Analysis. 2.5.2.1 Results of Duration Components Analysis2.5.3 SOM Clustering and Visualization; 2.5.3.1 Results of SOM Clustering; 2.5.3.2 Results of Component Plane Visualization; 2.6 Conclusion and Future Research Direction; References; Chapter 3: Towards Ontology-Driven Application for Multilingual Speech Language Therapy; 3.1 Introduction; 3.2 Ontology-Driven Applications; 3.3 Ontology Evaluation; 3.3.1 Evaluation Metric; 3.4 Speech Language Therapy: Challenges and Prospects; 3.5 Proposed MNCH Information System; 3.5.1 Domain Data Collection and Classification; 3.5.2 The SLT Framework. 3.6 Implications of the SLT Framework3.7 Model Implementation; 3.7.1 The MNCH OntoGraph; 3.8 Conclusion and Future Research Direction; References; Chapter 4: Ibibio Spoken-CALL System; 4.1 Introduction; 4.1.1 CALL Overview; 4.1.2 Design Challenges; 4.1.3 Design Approach; 4.2 CALL Systems: Genesis and Development; 4.2.1 From CALL to Spoken-CALL; 4.2.2 CALL and Speech Technology; 4.3 System Design; 4.3.1 Model Framework; 4.3.2 Interface Architecture; 4.4 System Evaluation; 4.4.1 Subjects/Participants; 4.4.2 Evaluation Method; 4.5 Results; 4.5.1 Naturalness Test; 4.5.2 Intelligibility Test. … (more)
- Publisher Details:
- Cham, Switzerland : Springer
- Publication Date:
- 2018
- Extent:
- 1 online resource
- Subjects:
- 006.4/54
Engineering
Automatic speech recognition
Natural language processing (Computer science)
COMPUTERS -- General
Engineering
Signal, Image and Speech Processing
Language Translation and Linguistics
Computational Linguistics
Automatic speech recognition
Natural language processing (Computer science)
Computers -- Speech & Audio Processing
Language Arts & Disciplines -- Linguistics -- General
Natural language & machine translation
Computational linguistics
Natural language processing (Computer science)
Computational linguistics
Technology & Engineering -- Electronics -- General
Imaging systems & technology
Electronic books
Electronic book - Languages:
- English
- ISBNs:
- 9783319699608
3319699601 - Related ISBNs:
- 9783319699585
331969958X - Notes:
- Note: Includes bibliographical references at the end of each chapters and index.
Note: Online resource; title from PDF title page (EBSCO, viewed February 1, 2018). - Access Rights:
- Legal Deposit; Only available on premises controlled by the deposit library and to one user at any one time; The Legal Deposit Libraries (Non-Print Works) Regulations (UK).
- Access Usage:
- Restricted: Printing from this resource is governed by The Legal Deposit Libraries (Non-Print Works) Regulations (UK) and UK copyright law currently in force.
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library HMNTS - ELD.DS.358238
- Ingest File:
- 01_318.xml