Bitte benutzen Sie diese Referenz, um auf diese Ressource zu verweisen: doi:10.22028/D291-25119
Titel: Pitch determination considering laryngealization effects in spoken dialogs
Verfasser: Niemann, Heinrich
Denzler, J.
Kahles, B.
Kompe, R.
Kiessling, A.
Nöth, E.
Strom, V.
Sprache: Englisch
Erscheinungsjahr: 1994
Quelle: Saarbrücken, 1994
SWD-Schlagwörter: Künstliche Intelligenz
DDC-Sachgruppe: 004 Informatik
Dokumentart : Report (Bericht)
Kurzfassung: A frequent phenomenon in spoken dialogs of the information seeking type are short elliptic utterances whose mood (declarative or interrogative) can only be distinguished by intonation. The main acoustic evidence is conveyed by the fundamental frequency or Fo-contour. Many algorithms for Fo determination have been reported in the literature. A common problem are irregularities of speech known as "laryngealizations". This article describes an approach based on neural network techniques for the improved determination of fundamental frequency. First, an improved version of our neural network algorithm for reconstruction of the voice source signal (glottis signal) is presented. Second, the reconstructed voice source signal is used as input to another neural network distinguishing the three classes "voiceless", "voiced non-laryngealized", and "voiced laryngealized". Third, the results are used to improve an existing Fo algorithm. Results of this approach are presented and discussed in the context of the application in a spoken dialog system.
Link zu diesem Datensatz: urn:nbn:de:bsz:291-scidok-40699
hdl:20.500.11880/25175
http://dx.doi.org/10.22028/D291-25119
Schriftenreihe: Vm-Report / Verbmobil, Verbundvorhaben, [Deutsches Forschungszentrum für Künstliche Intelligenz]
Band: 33
SciDok-Publikation: 2-Aug-2011
Fakultät: Sonstige Einrichtungen
Fachrichtung: SE - DFKI Deutsches Forschungszentrum für Künstliche Intelligenz
Fakultät / Institution:SE - Sonstige Einrichtungen

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
report_33_94.pdf287,15 kBAdobe PDFÖffnen/Anzeigen


Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt.