Please use this identifier to cite or link to this item:
doi:10.22028/D291-25093
Title: | Automatic classification of prosodically marked phrase boundaries in German |
Author(s): | Kompe, Ralf Batliner, A. Kießling, A. Kilian, U. Niemann, H. Nöth, E. Regel-Brietzmann, P. |
Language: | English |
Year of Publication: | 1993 |
OPUS Source: | Saarbrücken, 1993 |
SWD key words: | Künstliche Intelligenz |
DDC notations: | 004 Computer science, internet |
Publikation type: | Report |
Abstract: | A large corpus has been created automatically and read by speakers. Phrase boundaries were labeled in the sentences automatically during sentence generation. Perception experiments on a subset of 500 utterances showed a high agreement between the automatically generated boundary markers and the ones perceived by listeners. Gaussian distribution and polynomial classifiers were trained on a set of prosodic features computed from the speech signal using the automatically generated boundary markers. Comparing the classification results with the judgments of the listeners yielded in a recognition rate of 87%. A combination with stochastic language models improved the recognition rate to 90%. We found that the pause and the durational features are most important for the classification, but that the influence of F0 is not neglectable. |
Link to this record: | urn:nbn:de:bsz:291-scidok-39897 hdl:20.500.11880/25149 http://dx.doi.org/10.22028/D291-25093 |
Series name: | Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz] |
Series volume: | 4 |
Date of registration: | 21-Jul-2011 |
Faculty: | SE - Sonstige Einrichtungen |
Department: | SE - DFKI Deutsches Forschungszentrum für Künstliche Intelligenz |
Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
File | Description | Size | Format | |
---|---|---|---|---|
report_04_94.pdf | 191,61 kB | Adobe PDF | View/Open |
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.