Speech Signal Processing Using Consonant-Vowel Location Detection

Shusuke Nakazato, Nobuhiko Nakano

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Phoneme identification plays a major role in the field of speech processing. Currently, machine learning-based methods are the mainstream, but for devices that cannot incorporate heavy processing, we proposed a non-machine learning method to detect consonant-vowel positions using consonant classification criteria of voicelessness, Place of articulation, and Manner of articulation. The proposed method is composed of Fourier transform and simple operation and considered to be fully applicable to existing digital signal processors. These methods are implemented in MATLAB/Simulink.

Original languageEnglish
Title of host publicationProceedings - 2021 9th International Symposium on Computing and Networking Workshops, CANDARW 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages301-304
Number of pages4
ISBN (Electronic)9781665428354
DOIs
Publication statusPublished - 2021
Event9th International Symposium on Computing and Networking Workshops, CANDARW 2021 - Virtual, Online, Japan
Duration: 2021 Nov 232021 Nov 26

Publication series

NameProceedings - 2021 9th International Symposium on Computing and Networking Workshops, CANDARW 2021

Conference

Conference9th International Symposium on Computing and Networking Workshops, CANDARW 2021
Country/TerritoryJapan
CityVirtual, Online
Period21/11/2321/11/26

Keywords

  • Acoustic features
  • Consonant location detection
  • Speech recognition

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems
  • Software

Fingerprint

Dive into the research topics of 'Speech Signal Processing Using Consonant-Vowel Location Detection'. Together they form a unique fingerprint.

Cite this