Bitte benutzen Sie diese Referenz, um auf diese Ressource zu verweisen:
doi:10.22028/D291-25313
Titel: | An integrated model of acoustics and language using semantic classification trees |
VerfasserIn: | Nöth, Elmar De Mori, Renato Fischer, J. Gebhard, A. Harbeck, Stefan Kompe, Ralf Kuhn, R. Niemann, Heinrich Mast, Marion |
Sprache: | Englisch |
Erscheinungsjahr: | 1996 |
Kontrollierte Schlagwörter: | Künstliche Intelligenz |
Freie Schlagwörter: | artificial intelligence |
DDC-Sachgruppe: | 004 Informatik |
Dokumenttyp: | Forschungsbericht (Report zu Forschungsprojekten) |
Abstract: | We propose Multi-level Semantic Classication Trees to combine different information sources for predicting speech events (e.g. word chains, phrases, etc.) Traditionally in speech recognition systems these information sources (acoustic evidence, language model) are calculated independently and combined via Bayes rule. The proposed approach allows one to combine sources of different types - is no longer necessary for each source to yield a probability. Moreover the tree can look at several information sources simultaneously. The approach is demonstrated for the prediction of prosodically marked phrase boundaries, combining information about the spoken word chain, word category information, prosodic parameters, and the result of a neural network predicting the boundary on the basis of acoustic-prosodic features. The recognition rates of up to 90% for the two class problem boundary vs. no boundary are already comparable to results achieved with the above mentioned Bayes rule approach that combines the acoustic classifier with a 5-gram categorical language model. This is remarkable, since so far only a small set of questions combining information from different sources have been implemented. |
Link zu diesem Datensatz: | urn:nbn:de:bsz:291-scidok-53210 hdl:20.500.11880/25369 http://dx.doi.org/10.22028/D291-25313 |
Schriftenreihe: | Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz] |
Band: | 128 |
Datum des Eintrags: | 13-Jun-2013 |
Fakultät: | SE - Sonstige Einrichtungen |
Fachrichtung: | SE - DFKI Deutsches Forschungszentrum für Künstliche Intelligenz |
Sammlung: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Dateien zu diesem Datensatz:
Datei | Beschreibung | Größe | Format | |
---|---|---|---|---|
report_128_96.pdf | 169,98 kB | Adobe PDF | Öffnen/Anzeigen |
Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt.