The zeros of the spectrogram have proven to be a relevant feature to describe the time-frequency structure of a signal, originated by the destructive interference between components in the time-frequency plane. In this work, a classification of these zeros in three types is introduced, based on the nature of the components that interfere to produce them. Echoing noise-assisted methods, a classification algorithm is proposed based on the addition of independent noise realizations to build a 2D histogram describing the stability of zeros. Features extracted from this histogram are later used to classify the zeros using a non-supervised clusterization algorithm. A denoising approach based on the classification of the spectrogram zeros is also introduced. Examples of the classification of zeros are given for synthetic and real signals, as well as a performance comparison of the proposed denoising algorithm with another zero-based approach.
Motor imagery classification using EEG spectrograms
University of Engineering and Technology, Taxila(塔克西拉工程技术大学);Children’s National Hospital(国家儿童医院);Sheikh Zayed Institute for Pediatric Surgical Innovation(谢赫·扎耶德儿科外科创新研究所);George Washington University(乔治华盛顿大学)
Enhancing time-frequency resolution with optimal transport and barycentric fusion of multiple spectrogram
IRIT, University of Toulouse, CNRS, France(IRIT,图卢兹大学,法国国家科学研究中心,法国);AI Interdisciplinary Institute ANITI(人工智能跨学科研究所ANITI);France 2030 program PEPR(法国2030计划PEPR)
Recover from Horcrux: A Spectrogram Augmentation Method for Cardiac Feature Monitoring from Radar Signal Components
School of Advanced Technology, Xi’an Jiaotong-Liverpool University(西交利物浦大学先进技术学院);Faculty of Information Science and Electrical Engineering, Kyushu University(九州大学信息科学与电气工程学院);Thrust of Artificial Intelligence and Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)人工智能学科、智能交通学科);Institute of Deep Perception Technology, JITRI(江苏产业技术研究院深度感知技术研究所)
Personality Trait Recognition using ECG Spectrograms and Deep Learning
University of Engineering and Technology, Taxila(塔克西拉工程技术大学);Sheikh Zayed Institute for Pediatric Surgical Innovation(谢赫·扎耶德儿科外科创新研究所);Children’s National Hospital(儿童国家医院);School of Medicine and Health Sciences, George Washington University(乔治·华盛顿大学医学与健康科学学院)
AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification
Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh(计算机科学与工程系,BRAC大学,达卡,孟加拉国);Department of Computer Science(计算机科学系);Engineering, BRAC University, Dhaka, Bangladesh(工程系,BRAC大学,达卡,孟加拉国)