Curated Database of Pathological Speech Parameters
Year: 2025
Type: dataset
Abstract: The cured database was built in (Fernandes, et al., 2019) taking into account the sounds available in the Saarbrucken Voice Database (SVD) (Barry, et al.). Included in this cured database were 19 diseases and control subjects. It has a total number of samples of 707 pathological subjects (distributed by the various diseases) and 194 control subjects, and for each subject there is a sentence and three vowels /a/, /i/, and /u/, each vowel with three tones: high, low and normal. In the cured database there is an initial page containing the id of each subject, the age, gender, characterisation group that corresponds to the subject and the abbreviation that is used for this group. For each group there are 3 pages. The first page of each group includes the parameters: absolute jitter, relative jitter, absolute shimmer, relative shimmer, HNR, NHR and autocorrelation. For each subject, the subject's age and gender are also identified, as well as the vowel and tone to which the parameter corresponds. The second page lists the MFCCs of the recorded sentences, in this there are 13 cepstral coefficients throughout the sentence, making a total of 50 sentence segments. Finally, the third page lists the MFCCs for the vowels. This parameter was also extracted with 13 cepstral coefficients for each vowel and tone. However, for the vowels the sound was not segmented as happened for the phrase, extracting a value per coefficient for the whole sound. References Barry, B., Just, M., Pützer, M., Caradonna, R., Dressler, C., Erriquez, A., . . . Woldert-Jokisz, B. (s.d.). Saarbruecken Voice Database. [Accessed in 5 November 2021] http://stimmdb.coli.uni-saarland.de/index.php4#target Fernandes, J., Silva, L., Teixeira, F., Guedes, V., Santos, J., & Teixeira, J. P. (2019). Parameters for Vocal Acoustic Analysis - Cured Database. Procedia Computer Science, 164, 654-661.
Authors: Fernandes, Joana, Teixeira, João Paulo
Institution: Universidade Politécnica de Bragança
Language: English
Topic: Voice and Speech Disorders
Subfield: Speech and Hearing
Field: Health Professions
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W7104686753