Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Glottal Stops in Upper Sorbian: A Data-Driven Approach

: Kraljevski, Ivan; Bissiri, Maria Paola; Duckhorn, Frank; Tschöpe, Constanze; Wolff, Matthias

Volltext urn:nbn:de:0011-n-6403928 (207 KByte PDF)
MD5 Fingerprint: 7792dc496f1d513dd6b6ab492140155c
Erstellt am: 15.9.2021

Heřmanský, H. ; International Speech Communication Association -ISCA-:
Interspeech 2021. Proceedings. Online resource : Brno, Czechia, 30 August - 3 September 2021
Online im WWW, 2021
International Speech Communication Association (INTERSPEECH Annual Conference) <22, 2021, Brno>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IKTS ()
glottal stops; acoustic modeling; under-resourced languages

We present a data-driven approach for the quantitative analysis of glottal stops before word-initial vowels in Upper Sorbian, a West Slavic minority language spoken in Germany. Glottal stops are word-boundary markers and their detection can improve the performance of automatic speech recognition and speech synthesis systems.We employed cross-language transfer using an acoustic model in German to develop a forced-alignment method for the phonetic segmentation of a read-speech corpus in Upper Sorbian. The missing phonemic units were created by combining the existing phoneme models. In the forced-alignment procedure, the glottal stops were considered optional in front of word-initial vowels.To investigate the influence of speaker type (males, females, and children) and vowel on the occurren ce of glottal stops, binomial regression analysis with a generalized linear mixed model was performed. Results show that children glottalize word-initial vowels more frequently than adults, and that glottal stop occurrences are influenced by vowel quality.