Learning representations of sound using trainable COPE feature extractors

Abstract

Sound analysis research has mainly been focused on speech and music processing. The deployed methodologies are not suitable for analysis of sounds with varying background noise, in many cases with very low signal-to-noise ratio (SNR).In this paper, we present a method for the detection of patterns of interest in audio signals. We propose novel trainable feature extractors, which we call COPE (Combination of Peaks of Energy). The structure of a COPE feature extractor is determined using a single prototype sound pattern in an automatic configuration process, which is a type of representation learning. We construct

Detection of COVID-19 from speech signal using bio-inspired based cepstral features

“…3 ) and the need and operation of each block are explained. The algorithm is divided into two parts: configuration and application [36] . The configuration part deals with the preparation of a clean balanced dataset, and the application part explains the extraction and use of the proposed C-19CC features.…”

Trainable COPE Features for Sound Event Detection

“…This accounts for different resolution at low and high frequency, similarly to the way the auditory system processes the sound. We refer the reader to [21,27] for details.…”

“…In this paper, we present a method for audio event detection that is based on trainable feature extractors, called COPE (Combination of Peaks of Energy), recently proposed in [27]. The COPE algorithm is based on the analysis of local maxima in a time-frequency representation of the input audio signal, which have been demonstrated to be robust to additive noise [31].…”

Brain-Inspired Algorithms for Processing of Visual Data

“…Parts of higher energy intensity correspond to regions of the cochlea membrane that vibrates more according to the energy of the mechanical sound pressure waves that hit the outer part of the auditory system. This model was exploited in [45][46][47] as input to a trainable feature extractor, the design of which was inspired by the activation of the inner hair cells, placed behind the cochlea, which convert the vibration into electrical stimuli on the auditory nerve.…”