Consonant-to-Vowel/Vowel-to-Consonant Transitions to Analyze the Speech of Cochlear Implant Users.

Arias Vergara T, Gollwitzer S, Orozco Arroyave JR, Schuster M, Nöth E (2019)


Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 2019

Publisher: Springer

Pages Range: 299-306

Conference Proceedings Title: Lecture Notes in Computer Science

Event location: Ljubljana SI

ISBN: 978-3-030-27946-2

DOI: 10.1007/978-3-030-27947-9_25

Abstract

People with postlingual onset of deafness often present speech production problems even after hearing rehabilitation by cochlear implantation. In this paper, the speech of 20 postlingual (aged between 33 and 78 years old) and 20 healthy control (aged between 31 and 62 years old) German native speakers is analyzed considering acoustic features extracted from Consonant-to-Vowel (CV) and Vowel-to-Consonant (VC) transitions. The transitions are analyzed with reference to the manner of articulation of consonants according to 5 groups: nasals, sibilants, fricatives, voiced stops, and voiceless stops. Automatic classification between cochlear implant (CI) users and healthy speakers shows accuracies of up to 93%. Considering CV transitions, it is possible to detect specific features of altered speech of CI users. More features are to be evaluated in the future. A comprehensive evaluation of speech changes of CI users will help in the rehabilitation after deafening.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Arias Vergara, T., Gollwitzer, S., Orozco Arroyave, J.R., Schuster, M., & Nöth, E. (2019). Consonant-to-Vowel/Vowel-to-Consonant Transitions to Analyze the Speech of Cochlear Implant Users. In Kamil Ekštein (Eds.), Lecture Notes in Computer Science (pp. 299-306). Ljubljana, SI: Springer.

MLA:

Arias Vergara, Tomás, et al. "Consonant-to-Vowel/Vowel-to-Consonant Transitions to Analyze the Speech of Cochlear Implant Users." Proceedings of the Text, Speech, and Dialogue 2019, Ljubljana Ed. Kamil Ekštein, Springer, 2019. 299-306.

BibTeX: Download