This release of Speech Under Simulated and Actual Stress (SUSAS) was created by the Robust Speech Processing Laboratory at Duke University under the direction of Professor John H. L. Hansen and sponsored by the Air Force Research Laboratory. The database is partitioned into five domains, encompassing a wide variety of stresses and emotions. A total of 32 speakers (13 female, 19 male), with ages ranging from 22 to 76 were employed to generate in excess of 16,000 utterances. SUSAS also contains several longer speech files from four Apache helicopter pilots. These helicopter speech files were transcribed by the Linguistic Data Consortium and are available via ftp. The contents of this CD-ROM are: README This file /doc directory containing all documentation /doc/actual.txt Text file with a summary of the data in the actual stress portion of SUSAS /doc/labeling.csh Script to create the label files for SUSAS /doc/nato0995 A sub-directory which contains both .gif image files and .epsf postscript files of SUSAS slides used in the ESCA-NATO Speech Under Stress Workshop (Lisbon, Portugal) Sept. 1995. /doc/nato97.ps Paper investigating the problem of automatic segmentation of speech recorded in noisy channel environments /doc/rev1b4.ps Postscript file of 12-page document which outlines the SUSAS database, and procedures used for collection, digitizing, and organization. /doc/sim.txt Text file with a summary of the data in the simulated stress portion of SUSAS /labels Label files for all digitized tokens /labels/actual directory containing actual stress label files /labels/sim directory containing simulated stress label files /speech directory containing all speech files /speech/actual directory containing actual stress speech files /speech/sim directory containing simulated stress speech files Directory sizes: /speech/actual 113MB /speech/sim 126MB /labels 3MB /doc 3MB Total Size: /susas 245MB In the speech and label directories you will find files with the extension ".map". These files indicate the original name given to each file and the abbreviated ISO-9660 compliant name used for replication purposes. The first column indicates the name that appears within each directory on this CD-ROM. The second column lists the names given to each file by Duke University. In some instances, label files were not created for the corresponding speech files. In these cases, the appropriate directory within /labels is empty. Likewise, there are three occurrences of empty speech directories. October 20, 1998 Linguistic Data Consortium