Skip to main content

Time Domain Representation of Speech Sounds

A Case Study in Bangla

  • Book
  • © 2018

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

This is a preview of subscription content, log in via an institution to check access.

Access this book

eBook USD 16.99 USD 84.99
Discount applied Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

Licence this eBook for your library

Institutional subscriptions

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

  • (emeritus) Indian Statistical Institute, Kolkata, India

    Asoke Kumar Datta

About the author

Prof. Asoke Kumar Datta, an MSc. (Pure Math), worked at the Indian Statistical Institute from 1955-1994. He retired from the HOD Electronics and Communication Sciences Department, and is an ISI Visiting Professor. He is President, BOM-BOM, Kolkata; Senior Guest Researcher, Sir C V Raman Centre for Physics and Music, JU; Executive Member, Society for Natural Language Technology Research, Kolkata; Life Member, Acoustical Society of India. He received the J C Bose Memorial Award, 1969; Sir C V Raman Award, 1982-83 & 1998-99; S K Mitra Memorial Award, 1984; and the Sri C AchyutMenon Prize, 2001. His areas of academic interest include pattern recognition, AI, speech, music and consciousness.

Bibliographic Information

Publish with us