Classification and Recognition of Baby Cry Signal Feature Extraction Based on Improved MFCC

DOI
  • Chen Zhenjiang
    College of Electronic Information and Automation, Tianjin University of Science and Technology Advanced Structural Integrity International Joint Research Centre, Tianjin University of Science and Technology
  • Peng Yizhun
    College of Electronic Information and Automation, Tianjin University of Science and Technology Advanced Structural Integrity International Joint Research Centre, Tianjin University of Science and Technology
  • Li Di
    College of Electronic Information and Automation, Tianjin University of Science and Technology Advanced Structural Integrity International Joint Research Centre, Tianjin University of Science and Technology
  • Yang Zhou
    College of Electronic Information and Automation, Tianjin University of Science and Technology Advanced Structural Integrity International Joint Research Centre, Tianjin University of Science and Technology
  • Wang Nana
    College of Electronic Information and Automation, Tianjin University of Science and Technology Advanced Structural Integrity International Joint Research Centre, Tianjin University of Science and Technology

説明

Since MFCC was proposed, it has been widely used in feature extraction of speech signals. However, for some specific sound signals, such as baby crying signal, the direct MFCC feature extraction has a low classification and recognition rate. Through the study of MFCC feature extraction process, it is found that if each filter in the triangle filter bank is shifted upward by an ∂𝑖 (∂𝑖 ≥ 0).In addition, in the calculation of single frame MFCC, a continuous segment of sound information is reconstructed. The improved MFCC feature extraction can greatly improve the recognition rate and speed of baby crying recognition.

収録刊行物

キーワード

詳細情報 詳細情報について

  • CRID
    1390846609806456576
  • DOI
    10.5954/icarob.2020.os11-6
  • ISSN
    21887829
  • 本文言語コード
    en
  • データソース種別
    • JaLC
    • Crossref
  • 抄録ライセンスフラグ
    使用不可

問題の指摘

ページトップへ