Special Issue "Applications of Machine Learning in Audio Classification and Acoustic Scene Characterization"

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Acoustics and Vibrations".

Deadline for manuscript submissions: 30 June 2021.

Special Issue Editor

Dr. Sławomir K. Zieliński
E-Mail
Guest Editor
Faculty of Computer Science, Białystok University of Technology, Poland
Interests: machine learning; audio engineering; psychoacoustics; spatial audio

Special Issue Information

Dear Colleagues,

The goal of “audio classification” (AC) is to automatically identify the origin and attributes of individual sounds, while the aim of “acoustic scene characterization” (ASC) is to computationally describe more complex acoustic scenarios, consisting of many simultaneously sound-emitting sources. The additional difference between the tasks of AC and ASC is that the latter one also encompasses the identification and description of acoustical environments where the audio recordings took place. Hence, ASC portrays sonic events at a higher and more generic level compared to AC. Nevertheless, due to a considerable application and methodological overlap between ASC and AC, we decided to cover both areas of research within the scope of this Special Issue.

An important but still under-researched aspect of the ASC is the “spatial” characterization of sound scenes. Most of the AC and ASC systems developed so far are limited to the identification of monaurally recorded audio sources or events, overlooking the importance of their spatial characteristics. Therefore, we are interested in research papers that include but are not limited to the following topics:

  • Spatial audio scene characterization;
  • Localization of sound sources within complex audio scenes;
  • Automatic indexing, search or retrieval of spatial audio recordings;
  • Acoustic scene characterization in music information retrieval;
  • Data-efficient augmentation for deep learning-based audio classification algorithms;
  • Intelligent audio surveillance systems;
  • Detection of anomalous or emergency-related sounds;
  • Acoustically-based systems for early detection and fault prevention in industrial settings.

Dr. Sławomir K. Zieliński
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • audio classification
  • acoustic scene characterization
  • spatial audio
  • machine learning
  • deep learning

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Open AccessArticle
A Biologically Inspired Sound Localisation System Using a Silicon Cochlea Pair
Appl. Sci. 2021, 11(4), 1519; https://doi.org/10.3390/app11041519 - 08 Feb 2021
Viewed by 341
Abstract
We present a biologically inspired sound localisation system for reverberant environments using the Cascade of Asymmetric Resonators with Fast-Acting Compression (CAR-FAC) cochlear model. The system exploits a CAR-FAC pair to pre-process binaural signals that travel through the inherent delay line of the cascade [...] Read more.
We present a biologically inspired sound localisation system for reverberant environments using the Cascade of Asymmetric Resonators with Fast-Acting Compression (CAR-FAC) cochlear model. The system exploits a CAR-FAC pair to pre-process binaural signals that travel through the inherent delay line of the cascade structures, as each filter acts as a delay unit. Following the filtering, each cochlear channel is cross-correlated with all the channels of the other cochlea using a quantised instantaneous correlation function to form a 2-D instantaneous correlation matrix (correlogram). The correlogram contains both interaural time difference and spectral information. The generated correlograms are analysed using a regression neural network for localisation. We investigate the effect of the CAR-FAC nonlinearity on the system performance by comparing it with a CAR only version. To verify that the CAR/CAR-FAC and the quantised instantaneous correlation provide a suitable basis with which to perform sound localisation tasks, a linear regression, an extreme learning machine, and a convolutional neural network are trained to learn the azimuthal angle of the sound source from the correlogram. The system is evaluated using speech data recorded in a reverberant environment. We compare the performance of the linear CAR and nonlinear CAR-FAC models with current sound localisation systems as well as with human performance. Full article
Show Figures

Figure 1

Back to TopTop