Information on the glottal waveform is an important part of many speech applications. However, glottal waveform estimation remains one of the more inexact sciences of speech processing. The work presented here describes an enhancement to a recently presented algorithm by a new technique involving Rank-Based Glottal Quality Assessment (RB-GQA). The basic premise is to investigate potential measures of glottal quality and use these measures to mark the general trends for determining which glottal waveform estimations are better than others. The work presented here is the beginning of a new research initiative to identify robust methods of glottal waveform estimation across genders for use in speaker analysis applications of normal voices (i.e., no voice pathology).
Cite as: Moore II, E., Torres, J. (2006) Improving glottal waveform estimation through rank-based glottal quality assessment. Proc. Interspeech 2006, paper 1296-Wed2A1O.1, doi: 10.21437/Interspeech.2006-471
@inproceedings{mooreii06_interspeech,
author={Elliot {Moore II} and Juan Torres},
title={{Improving glottal waveform estimation through rank-based glottal quality assessment}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 1296-Wed2A1O.1},
doi={10.21437/Interspeech.2006-471}
}