Paper data
Title:
Wavelet decomposition of voiced speech and mathematical morphology analysis for glottal closure instants detection. Author(s): Ben Slimane Rahmouni Amel, ENIT TUNISIA Bouzid Aicha, ENIT TUNISIA Ellouze Noureddine, ENIT TUNISIA Page numbers in the proceedings: Volume III pp 81-84 Session: Multimedia Data Protection / Speech Analysis and Recognition
Paper abstract
This paper presents a robust algorithm for glottal closure instants (GCIs) detection of speech signals. The algorithm uses a multi-scale analysis based on a dyadic wavelet filterbank. Significant minima and maxima of the filtered signals are localized at each scale using adaptive mathematical morphology transformation of erosion. With reference to the GCIs detected from the laryngograph signal, a robust strategy for GCI localization was deduced. Each GCI is determined as the position of a minimum suitably chosen on one of the outputs of the different filters. This choice aims to insure the best accuracy and reliability even for weak glottal effort.
Paper
|