A Preliminary Statistical Evaluation of Manual and Automatic Segmentation Discrepancies

The accuracy of automatic alignment systems will always be checked using references manually segmented by phonetic or speech communication experts. Consequently, the statistical characterisation of manual segmentation discrepancies becomes quite an important issue. To achieve the goal of finding a better statistical description of these discrepancies, two different experiments were carried out. The first pilot experiment, which was focused on the segmentation of a small subset of an Italian isolated-word speech data-base, was carried out only to better define the second experiment regarding the segmentation of few continuous Italian sentences.

Publication type: 
Contributo in atti di convegno
Author or Creator: 
Cosi P.
Falavigna D.
Omologo M.
Publisher: 
ISCA, International speech communication association, Baixas, FRA
Source: 
EUROSPEECH-91, 2nd European Conference on Speech Technology, pp. 693–696, Genova, Italia, 24-26 September, 1991
Date: 
1991
Resource Identifier: 
http://www.cnr.it/prodotto/i/241806
http://www.pd.istc.cnr.it/Papers/PieroCosi/cp-ES91.pdf
Language: 
Eng
ISTC Author: 
Piero Cosi's picture
Real name: