An evolutionary feature synthesis approach for content-based audio retrieval

Abstract

A vast amount of audio features have been proposed in the literature to characterize the content of audio signals. In order to overcome specific problems related to the existing features (such as lack of discriminative power), as well as to reduce the need for manual feature selection, in this article, we propose an evolutionary feature synthesis technique with a built-in feature selection scheme. The proposed synthesis process searches for optimal linear/ nonlinear operators and feature weights from a pre-defined multi-dimensional search space to generate a highly discriminative set of new (artificial) features. The evolutionary search process is based on a stochastic optimization approach in which a multi-dimensional particle swarm optimization algorithm, along with fractional global best formation and heterogeneous particle behavior techniques, is applied. Unlike many existing feature generation approaches, the dimensionality of the synthesized feature vector is also searched and optimized within a set range in order to better meet the varying requirements set by many practical applications and classifiers. The new features generated by the proposed synthesis approach are compared with typical low-level audio features in several classification and retrieval tasks. The results demonstrate a clear improvement of up to 15-20% in average retrieval performance. Moreover, the proposed synthesis technique surpasses the synthesis performance of evolutionary artificial neural networks, exhibiting a considerable capability to accurately distinguish among different audio classes.

Context-based environmental audio event recognition for scene understanding

“…Their process includes finding the decomposition of a signal from a dictionary of atoms, which would yield the best set of functions to form an approximate representation. More recently, Mäkinen et al [33] propose an evolutionary feature synthesis technique to enhance common audio descriptors by using multidimensional particle swarm optimization to search for the optimal feature synthesis parameters. These works forward the auditory scene research; however, not all the unpredictable structures of auditory environments can be directly discriminated by a low-level feature subset.…”

Evolutionary Multi-objective Training Set Selection of Data Instances and Augmentations for Vocal Detection

“…A multi-objective EA with the target to minimise the number of selected features and the classification error was presented in [29]. EAs have proven their ability to generate new features for music classification by exploring nearly unlimited search spaces of combinations of different transforms and mathematical operations [22,19,15]. EAs have also been successfully applied for training set augmentation in bioinformatics, where the generation of new training data may be very expensive [11,32], and for training set selection (TSS) [6].…”

Evolutionary feature synthesis by multi-dimensional particle swarm optimization

“…The proposed EFS system has been previously successfully applied on audio features [1]. An initial version of the proposed EFS has been also applied on image features in [2], but the fitness functions were not generic nor applicable in real life as they required classification or retrieval over the whole EFS dataset for every fitness evaluation.…”