OS11-6 Classification and Recognition of Baby Cry Signal Feature Extraction Based on Improved MFCC

Title:	OS11-6 Classification and Recognition of Baby Cry Signal Feature Extraction Based on Improved MFCC
Publication:	ICAROB2020
Volume:	25
Pages:	556-559
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2020.OS11-6
Author(s):	Zhenjiang Chen, Yizhun Peng, Di Li, Zhou Yang, Nana Wang
Publication Date:	January 13, 2020
Keywords:	MFCC, feature extraction, triangle band-pass filter bank, after framing, classification and recognition rate
Abstract:	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.
PDF File:	https://alife-robotics.co.jp/members2020/icarob/data/html/data/OS/OS11/OS11-6.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/