Parameterisation of human speech after total laryngectomy surgery. (March 2022)

• Record Type: Journal Article
• Authors: Tyburek, Krzysztof
• Is Part Of: Computer speech & language. Volume 72(2022)
• Publication Date: 2022-03
• Subjects: Vocal rehabilitation -- Laryngectomy -- Voice quality -- Voice pathology -- Acoustic analysis -- Speech signal; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2021.101313
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract: The aim of the rehabilitation in laryngectomised patients is to produce phonatory communication. It is important to choose the optimal method of speech rehabilitation. Most of the patients use esophageal or pharyngeal speech as an effect of natural rehabilitation with the vocalistic method. The aim of the study was to compare the quality of esophageal speech in laryngectomised people during speech rehabilitation with the speech of healthy people — without speech disorders. The purpose was to compare the values of the physical features of the speech signal (feature vector) read from the time and spectral domains. Voice samples were taken from 12 people aged 30–70 after total laryngectomy. They were recorded at the Bydgoszcz Laryngectomy Association (Bydgoszcz, Poland). In line with the rehabilitation process, words (spoken in Polish) such as "barrel", "roll", "egg", "package", and "snow" were analysed (each as a separate pattern). In addition, the slow counting from 1 to 10 was analysed, each word separately. In order to compare the values of the obtained descriptors of the speech signals of the laryngectomised people, voice samples (the same words) were also recorded by healthy people (3 men and 3 women aged 25–60). The obtained research results may help to improve the quality of the rehabilitation process of larygectomised patients by increasing the quality of esophageal speech. Highlights: There are features of time-domain efficiently parametrizing replacement speech. The frequency domain features improves recognition of the physical esophageal speech. The need to increase the effectiveness of rehabilitation of esophageal speech. The indexing of the speech signal according to the main classification approach.