Overview
- Development of complete time domain representation of speech signals with full illustration using the Standard Colloquial Bengali (Bangla)
- State phase analysis, a new time domain algorithm for proto-phonetic segmentation of Speech signal
- Spectral domain representation all Bangla phones
- Evidence that spectral representation of phones is neither necessary nor sufficient for cognition of phones
- Use of cohorts driven by manner based labelling in ASR in Bangla (a novel approach in ASR) resulting in an estimated recognition rate of around 95%
- Study of Chaos and Fractal dimensions in Bangla Vowels
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (7 chapters)
Keywords
About this book
The book presents the history of time-domain representation and the extent of its development along with that of spectral domain representation in the cognitive and technology domains. It discusses all the cognitive experiments related to this development, along with details of technological developments related to both automatic speech recognition (ASR) and text to speech synthesis (TTS), and introduces a viable time-domain representation for both objective and subjective analysis, as an alternative to the well-known spectral representation.
The book also includes a new cohort study on the use of lexical knowledge in ASR.
India has numerous official dialects, and spoken-language technology development is a burgeoning area. In fact TTS and ASR taken together constitute the most important technology for empowering people. As such, the book describes time domain representation in such a way that it can be easily and seamlessly incorporated into ASR and TTS research and development. In short, it is a valuable guidebook for the development of ASR and TTS in all the Indian Standard Dialects using signal domain parameters.
Authors and Affiliations
About the author
Bibliographic Information
Book Title: Time Domain Representation of Speech Sounds
Book Subtitle: A Case Study in Bangla
Authors: Asoke Kumar Datta
DOI: https://doi.org/10.1007/978-981-13-2303-4
Publisher: Springer Singapore
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: Springer Nature Singapore Pte Ltd. 2018
Hardcover ISBN: 978-981-13-2302-7Published: 13 November 2018
eBook ISBN: 978-981-13-2303-4Published: 03 November 2018
Edition Number: 1
Number of Pages: XVI, 154
Number of Illustrations: 90 b/w illustrations, 27 illustrations in colour
Topics: User Interfaces and Human Computer Interaction, Signal, Image and Speech Processing, Natural Language Processing (NLP)