Acoustic Event Classification using spectral band selection and Non-Negative Matrix Factorization-based features
作者：
Highlights：
• We propose a new front-end for Acoustic Event Classification tasks (AEC).
• It consists of two stages: short-time feature extraction and temporal integration.
• The first module relies on mutual information-based frequency band selection.
• The second module is based on Non-Negative Matrix Factorization (NMF).
• Results show that it outperforms the baseline system in clean and noisy conditions.
摘要
•We propose a new front-end for Acoustic Event Classification tasks (AEC).•It consists of two stages: short-time feature extraction and temporal integration.•The first module relies on mutual information-based frequency band selection.•The second module is based on Non-Negative Matrix Factorization (NMF).•Results show that it outperforms the baseline system in clean and noisy conditions.
论文关键词：Acoustic Event Classification,Feature extraction,Temporal feature integration,Feature selection,Mutual information,Non-Negative Matrix Factorization
论文评审过程：Received 18 April 2015, Revised 16 October 2015, Accepted 17 October 2015, Available online 26 October 2015, Version of Record 18 November 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.10.018
