Word and syllable Boundary Determination in Continuous Bodo Speech

Word and syllable Boundary Determination in Continuous Bodo Speech

Uzzal Sharma;
adbu journal of engineering technology 2019 Vol. 8
201
sharma2019wordadbu

Abstract

The idea of word boundary is very fundamental and one of the important factors as far as the study of any human language is concerned. In actual practice it seems, describing boundaries of word are somewhat easier to define, although it is a subject with limited spread. In this paper, we try to study the spoken Bodo language, we considered four common criteria for detection of boundaries of syllable or word namely quick initial speech, sluggish terminating speech, reset in pitch and pauses) and examined their existence in a fragment taken from a recorded database that contains approximately 23 similar units. The recorded speech was parsed by two linguistic experts and the result so obtained were examined acoustically to establish which were present at each separation of words. Later on the obtained result is compared with the result obtained from SVM classifier. It has been noticed that both approaches gives similar and comparative result. Further, it is found that only a few of the determined separation of words conformed to all cues. It is found that the sluggish terminating speech was most prevailing, followed by reset in pitch, then pauses, and finally quick initial speech. An intense study, involving large set of units and more speakers is still under process.

Citation

ID: 13769
Ref Key: sharma2019wordadbu
Use this key to autocite in SciMatic or Thesis Manager

References

Blockchain Verification

Account:
NFT Contract Address:
0x95644003c57E6F55A65596E3D9Eac6813e3566dA
Article ID:
13769
Unique Identifier:
9eb7a320518cb61d0c069e68f95de17c
Network:
Scimatic Chain (ID: 481)
Loading...
Blockchain Readiness Checklist
Authors
Abstract
Journal Name
Year
Title
5/5
Creates 1,000,000 NFT tokens for this article
Token Features:
  • ERC-1155 Standard NFT
  • 1 Million Supply per Article
  • Transferable via MetaMask
  • Permanent Blockchain Record
Blockchain QR Code
Scan with Saymatik Web3.0 Wallet

Saymatik Web3.0 Wallet