Abstract
We describe the pronunciation model of the automatic segmentation technique MAUS based on a data-driven Markov process and a new evaluation measure for phonemic transcripts relative symmetric accuracy; results are given for the MAUS segmentation and labelling on German dialog speech. MAUS is currently distributed as a freeware package by the Bavarian Archive for Speech Signals and will also be implemented as a web-service in the near future.
Dokumententyp: | Konferenzbeitrag (Vortrag) |
---|---|
Fakultät: | Sprach- und Literaturwissenschaften > Department 2 > Phonetik und Sprachverarbeitung |
Themengebiete: | 400 Sprache > 400 Sprache |
URN: | urn:nbn:de:bvb:19-epub-13684-8 |
Sprache: | Englisch |
Dokumenten ID: | 13684 |
Datum der Veröffentlichung auf Open Access LMU: | 19. Jul. 2012, 12:02 |
Letzte Änderungen: | 04. Nov. 2020, 12:54 |