Speech Signal Processing Using Consonant-Vowel Location Detection

Shusuke Nakazato, Nobuhiko Nakano

研究成果: Conference contribution

抄録

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.

本文言語English
ホスト出版物のタイトルProceedings - 2021 9th International Symposium on Computing and Networking Workshops, CANDARW 2021
出版社Institute of Electrical and Electronics Engineers Inc.
ページ301-304
ページ数4
ISBN(電子版)9781665428354
DOI
出版ステータスPublished - 2021
イベント9th International Symposium on Computing and Networking Workshops, CANDARW 2021 - Virtual, Online, Japan
継続期間: 2021 11月 232021 11月 26

出版物シリーズ

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

Conference

Conference9th International Symposium on Computing and Networking Workshops, CANDARW 2021
国/地域Japan
CityVirtual, Online
Period21/11/2321/11/26

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ネットワークおよび通信
  • 情報システム
  • ソフトウェア

フィンガープリント

「Speech Signal Processing Using Consonant-Vowel Location Detection」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル