Models and Analysis of Vocal Emissions for Biomedical Applications

A special issue of Bioengineering (ISSN 2306-5354). This special issue belongs to the section "Biosignal Processing".

Deadline for manuscript submissions: 29 February 2024 | Viewed by 1323

Special Issue Editors

Department of Information Engineering, Università degli Studi di Firenze, 50139 Firenze, Italy
Interests: acoustical analysis; ecg
Department of Information Engineering, Università degli Studi di Firenze, 50139 Firenze, Italy
Interests: biomedical signal processing; voice analysis; modeling of biomedical signals; parametric spectral estimation; autoregressive models

Special Issue Information

Dear Colleagues,

Following the success of the 13th MAVEBA International Workshop (held in Florence, Italy, 12–13th September, 2023), we propose a Special Issue of Bioengineering that collects an extended version of the contributions presented at the Workshop.

The MAVEBA Workshop concerns the study of the human voice from the methodological point of view and its biomedical applications. The series of MAVEBA international workshops started in 1999, and a multidisciplinary meeting stimulating contacts between specialists active in bioengineering, clinical applications, and industrial development is held every two years.

This SI welcomes contributions ranging from fundamental research to advanced technologies about models and the analysis of signals and images of the human vocal apparatus and any fields related to all kinds of biomedical applications, with emphasis on translational research, the link with the “real” complex world of the human being.

This Special Issue is open to the submission of papers focused on multidisciplinary approaches involving bioengineering, otolaryngology, phoniatrics, neurology, surgery, psychology, psychiatry, logopaedic, linguistics, singing, and related fields, with applications ranging from the newborn to the elderly.

Topics of interest for this Special Issue include, but are not limited to, the following:

  • Tools and methods for voice recording;
  • Wearable devices, mobile apps, and human-computer interaction;
  • Software tools for voice and image analysis;
  • Modeling and Analysis of voice and speech;
  • Modeling of vocal folds and vocal tract;
  • Signal processing methods for singing and drama, classical and modern singing, and acted voice;
  • AI and deep learning in voice recognition, synthesis, and classification;
  • Computational neuroscience;
  • Acoustical and image analysis of the vocal folds;
  • Modeling and simulation of vocal physiology;
  • Biomechanics of the vocal folds;
  • Intonation, mood, stress, and related neurological disorders;
  • Newborn cry, prematurity, and neurological disorders;
  • Voice analysis and native language.

Dr. Lorenzo Frassineti
Dr. Antonio Lanata
Dr. Claudia Manfredi
Guest Editors

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 submissions that pass pre-check are 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. Bioengineering is an international peer-reviewed open access monthly 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 2700 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.

Published Papers (1 paper)

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

Research

19 pages, 3452 KiB  
Article
Towards a Corpus (and Language)-Independent Screening of Parkinson’s Disease from Voice and Speech through Domain Adaptation
Bioengineering 2023, 10(11), 1316; https://doi.org/10.3390/bioengineering10111316 - 15 Nov 2023
Viewed by 1043
Abstract
End-to-end deep learning models have shown promising results for the automatic screening of Parkinson’s disease by voice and speech. However, these models often suffer degradation in their performance when applied to scenarios involving multiple corpora. In addition, they also show corpus-dependent clusterings. These [...] Read more.
End-to-end deep learning models have shown promising results for the automatic screening of Parkinson’s disease by voice and speech. However, these models often suffer degradation in their performance when applied to scenarios involving multiple corpora. In addition, they also show corpus-dependent clusterings. These facts indicate a lack of generalisation or the presence of certain shortcuts in the decision, and also suggest the need for developing new corpus-independent models. In this respect, this work explores the use of domain adversarial training as a viable strategy to develop models that retain their discriminative capacity to detect Parkinson’s disease across diverse datasets. The paper presents three deep learning architectures and their domain adversarial counterparts. The models were evaluated with sustained vowels and diadochokinetic recordings extracted from four corpora with different demographics, dialects or languages, and recording conditions. The results showed that the space distribution of the embedding features extracted by the domain adversarial networks exhibits a higher intra-class cohesion. This behaviour is supported by a decrease in the variability and inter-domain divergence computed within each class. The findings suggest that domain adversarial networks are able to learn the common characteristics present in Parkinsonian voice and speech, which are supposed to be corpus, and consequently, language independent. Overall, this effort provides evidence that domain adaptation techniques refine the existing end-to-end deep learning approaches for Parkinson’s disease detection from voice and speech, achieving more generalizable models. Full article
(This article belongs to the Special Issue Models and Analysis of Vocal Emissions for Biomedical Applications)
Show Figures

Figure 1

Back to TopTop