SLAM v1.0 for Windows: a Simple PC-Based Tool for Segmentation and Labeling

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].