Nonlinear Acoustic Analysis in the Evaluation of Occupational Voice Disorders

Niebudek-Bogusz, Ewa; Grygiel, Jacek; Strumiłło, Paweł; Śliwińska-Kowalska, Mariola

doi:10.13075/mp.5893/2013/0004

Cited by 3 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Constantly secreted cortisol not only affects the immune system but also increases susceptibility to other diseases which affect the delicate structures and nerve connections, among others,of the laryngeal nerves and the surrounding muscles, which, with a normal short-term cortisol release, have an improved blood supply; however, with prolonged release of this hormone, the homeostasis of the organ is disturbed [33]. This finally provides the answer in the form of the voice disorders observed above.…”

Section: Systemic Lupus Erythematosus (Sle)mentioning

confidence: 99%

Influence of selected autoimmunological diseases on phonation devices, diagnostics and treatment

Markowska¹,

Jurkiewicz²

2023

J Pre Clin Clin Res.

View full text Add to dashboard Cite

Introduction and Objective. Many autoimmune diseases correlate with phonatory disorders which significantly reduce the well-being and quality of life of patients due to difficulties in verbal communication. The aim of the review is to present the current medical knowledge on ENT complications in patients suffering from selected autoimmune diseases. The text is partially supplemented with the possibilities of diagnosis and treatment of these disorders. Review Methods. PubMed, PubMed Central, and printed literature were searched using key words related to phoniatrix, larynx, immunology, voice, thyroid and dysphonia. Articles in Polish, German and English were searched. Bibliographies with outdated data and those that did not have the latest update or did not meet the selected criteria were excluded. Exclusions were most often due to an incomplete topic as well as results reported by an unrepresentative group of patients. The review was supported by an additional case study included as relevant to add significant clinical and imaging value to the work. Brief description of the state of knowledge. Autoimmune diseases are manifested in various body systems, including the phonational system. Both patients and doctors often do not expect that symptoms such as hoarseness, dysphonia, low voice or sore throat may be caused by an underlying disease. The list of ailments, diagnostic options and treatment is intended to present this problem and to increase medical awareness. Summary. Tthe presented diseases have been shown primarily from the side of disorders in phonation which accompany them. Despite the apparent unrelatedness of the disease with the production of sound, the clinical picture often shows ENT symptoms that are significant for the patient.

show abstract

Section: Systemic Lupus Erythematosus (Sle)mentioning

confidence: 99%

Influence of selected autoimmunological diseases on phonation devices, diagnostics and treatment

Markowska¹,

Jurkiewicz²

2023

J Pre Clin Clin Res.

View full text Add to dashboard Cite

show abstract

“…6. Consequently, three 12-dimensional feature vectors denoted further as LFCC, MFCC and GTCC were analyzed which were assumed to reflect the voice signal properties of the patients as suggested in [22,23]. The vectors contain cepstral coefficients (CC ) corresponding to frequency scales the techniques use: linear-frequency (LF), mel-frequency (MF), and gamma-tone (GT).…”

Section: Feature Engineering Approachmentioning

confidence: 99%

Bulletin of the Polish Academy of Sciences: Technical Sciences

Majda-Zdancewicz,

Potulska-Chromik,

Jakubowski

et al. 2021

View full text Add to dashboard Cite

Voice acoustic analysis can be a valuable and objective tool supporting the diagnosis of many neurodegenerative diseases, especially in times of distant medical examination during the pandemic. The article compares the application of selected signal processing methods and machine learning algorithms for the taxonomy of acquired speech signals representing the vowel a with prolonged phonation in patients with Parkinson's disease and healthy subjects. The study was conducted using three different feature engineering techniques for the generation of speech signal features as well as the deep learning approach based on the processing of images involving spectrograms of different time and frequency resolutions. The research utilized real recordings acquired in the Department of Neurology at the Medical University of Warsaw, Poland. The discriminatory ability of feature vectors was evaluated using the SVM technique. The spectrograms were processed by the popular AlexNet convolutional neural network adopted to the binary classification task according to the strategy of transfer learning. The results of numerical experiments have shown different efficiencies of the examined approaches; however, the sensitivity of the best test based on the selected features proposed with respect to biological grounds of voice articulation reached the value of 97% with the specificity no worse than 93%. The results could be further slightly improved thanks to the combination of the selected deep learning and feature engineering algorithms in one stacked ensemble model.

show abstract

“…Such a result is used by a phoniatrist to detect a subtle early changes in the voice. These changes may be the initial stage in the development of vocal chords nodules [6]. Another field in which sound signal analysis is used is bio-acoustics -it studies the impact and role of sound in the lives of animals.…”

Section: Introductionmentioning

confidence: 99%

Evolution-by-Coevolution of Neural Networks for Audio Classification

Funika,

Koperek,

Wiewióra

2023

cai

View full text Add to dashboard Cite

Neural networks are increasingly used in recognition problems, including static and moving images, sounds, etc. Unfortunately, the selection of optimal neural network architecture for a specific recognition problem is a difficult task, which often has an experimental nature. In this paper we present the use of evolutionary algorithms to obtain optimal architectures of neural networks used for audio sample classification. We extend the Pytorch DNN Evolution tool implementing coevolutionary algorithms which create groups of neural networks that solve a given problem with a certain accuracy, with the support for problems in which training data consists of audio samples. In this paper we use the co-evolutionary approach to solve a sample sound classification problem. We describe how the sound data was prepared for processing with the use of the Mel Frequency Cepstral Coefficients (MFCC). Next we present the results of experiments conducted with the AudioMnist dataset. The obtained neural network architectures, whose classification accuracy is comparable to the classification accuracy attained by the AlexNet neural network, and their implications are discussed.

show abstract

Nonlinear Acoustic Analysis in the Evaluation of Occupational Voice Disorders

Cited by 3 publications

References 13 publications

Influence of selected autoimmunological diseases on phonation devices, diagnostics and treatment

Influence of selected autoimmunological diseases on phonation devices, diagnostics and treatment

Bulletin of the Polish Academy of Sciences: Technical Sciences

Evolution-by-Coevolution of Neural Networks for Audio Classification

Contact Info

Product

Resources

About