The first official release of SLAM [1], [2], a semi-automatic segmentation and labeling environment, especially developed for Windows©-based1 Personal Computers, is described. The system was designed with the aim of being extremely user-friendly and supporting speech scientists in assessing the very heavy and time-consuming task of segmenting and labeling a big amount of speech material such as that caused by the tremendous spread of new and always bigger speech data-bases. SLAM is based on the Multi-Level Segmentation theory [3] and the segmentation process works with various spectral representations of speech. (FFT, LPC... ), even if it was especially created for an auditory-based representation [4].
SLAM v1.0 for Windows: a Simple PC-Based Tool for Segmentation and Labeling
Cosi P
1997
Abstract
The first official release of SLAM [1], [2], a semi-automatic segmentation and labeling environment, especially developed for Windows©-based1 Personal Computers, is described. The system was designed with the aim of being extremely user-friendly and supporting speech scientists in assessing the very heavy and time-consuming task of segmenting and labeling a big amount of speech material such as that caused by the tremendous spread of new and always bigger speech data-bases. SLAM is based on the Multi-Level Segmentation theory [3] and the segmentation process works with various spectral representations of speech. (FFT, LPC... ), even if it was especially created for an auditory-based representation [4].I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
