METHOD FOR SELECTING FUNDAMENTAL TONE FROM SPEECH SIGNAL

METHOD FOR SELECTING FUNDAMENTAL TONE FROM SPEECH SIGNAL

acoustic engineering. SUBSTANCE: method involves expanding speech signal in a sequence of Fourier spectra, finding absolute maximum, calculating mean value the obtained maximum sequence argument, evaluating mean frequency of the fundamental tone of the speech signal under study, amplitude signal sel...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SULIMA P.M, REPALOV S.A, LEDNOV D.A, AGRANOVSKIJ A.V, POTAPENKO A.M
Format: Patent
Sprache:eng ; rus
Schlagworte:
ACOUSTICS
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:acoustic engineering. SUBSTANCE: method involves expanding speech signal in a sequence of Fourier spectra, finding absolute maximum, calculating mean value the obtained maximum sequence argument, evaluating mean frequency of the fundamental tone of the speech signal under study, amplitude signal selection, calculating autocorrelation matrix determinant values and filtering the values. EFFECT: high accuracy of the method. 2 cl, 1 dwg