NAME OF THIS FILE: sim.txt SUSAS Speech Under Simulated and Actual Stress Duke University Robust Speech Processing Laboratory http://www.ee.duke.edu/Research/Speech/ April 15, 1998 (Release Rev. 1.4) ----------------------------------------------------------------------------- This Directory is: susas/sim Contents: 9 speakers in a quiet environment simulating speech under stress Speakers: --------- general1, general2, general3: Male General USA Accent boston1, boston2, boston3: Male New England/Boston, MA, USA Accent nyc1, nyc2, nyc3: Male New York City, USA Accent Stress Conditions: ------------------ angry 2 tokens of simulated anger clear 2 tokens of clearly enunciated speech cond50 2 tokens of low task stress cond70 2 tokens of high task stress fast 2 tokens of fast speech lombard 2 tokens of speech produced with 85 dBA pink noise in headphones loud 2 tokens of loudly spoken speech neutral 2 tokens of neutral speech question 2 tokens of speech asked as a question slow 2 tokens of slowly uttered speech soft 2 tokens of softly spoken speech train 12 tokens of neutral training speech Special Comments: ----------------- All of these files are in binary short format (same as short in C++). All of these files have had excessive leading and trailing silence removed via endpoint detection. Sampled at 8kHz (The data originally donated by Lincoln Laboratory was sampled at 16kHz. A number of errors regarding labels and missing files were identified by us, and appropriate updates made to address these errors included in the present release. These modifications are summarized below. MISSING FILES: -------------- Given the token count for each stress condition and speaker from above, there should be 1,190 tokens per speaker under susas/sim. Unfortunately, a very small number of errors and missing files were present in the data originally collected by Lincoln laboratory. In order to make sure that 2 tokens exist for each stress condition, we did the following: (1) if one token exists for a given stress condition, this file was duplicated to make up the second token: (e.g., break1.b1n did exist, but break2.b1n was missing: therefore break1.b1n was copied to break2.b1n) (2) if neither token existed for a given stress condition, then tokens from the neutral directory were used to make up both tokens: (e.g., for speaker general2, under slow conditions, both destin1.g2s and destin2.g2s did not exist: therefore destin1.g2n and destin2.g2n were copied to destin1.g2s and destin2.g2s) (3) if a file was originally labeled incorrectly, we used the correct file when possible; otherwise the second stressed speech token is used in it's place: (e.g., the file on1.b1c7 was actually an original token of the word "oh" (most likely, the speaker said the wrong word): therefore on1.b1c7 was renamed on1.b1c7-OH, and on2.b1c7 was copied to on1.b1c7) Below is a summary of the 51 files which were either missing, or had the incorrect label when it was originally digitized. The file used to replace the missing entry is also listed [if you are performing stressed speech analysis of SUSAS files, we recommend that you set these files aside. Speaker ORIGINAL REPLACED BY REASON FOR FileLength MODIFICATION ---------------------------------------- g1 1. degree2.g1n actually the word "nav" degree2.g1n was renamed as: nav2.g1n 2. fifty2.g1n actually the word "degree" fifty2.g1n was renamed as: degree2.g1n 3. nav2.g1n actually the word "wide" nav2.g1n was renamed as: wide2.g1n 4. wide2.g1n actually the word "mark" wide2.g1n was renamed as: mark3.g1n-EXTRA 5. 0 fifty2.g1n <--- 7808 fifty1.g1n ORIG. MISSING (after renames) g2 6. 0 destin1.g2s <--- 13952 destin1.g2n ORIG. MISSING 7. 0 destin2.g2s <--- 13440 destin2.g2n ORIG. MISSING 8. 0 fifty1.g2s <--- 7552 fifty1.g2n ORIG. MISSING 9. 0 fifty2.g2s <--- 8064 fifty2.g2n ORIG. MISSING 10. 0 histog1.g2s <--- 12928 histog1.g2s ORIG. MISSING 11. 0 histog2.g2s <--- 12544 histog2.g2s ORIG. MISSING 12. 0 zero1.g2s <--- 20480 zero2.g2s ORIG. MISSING g3 13. 0 hot1.g2a <--- 4864 hot1.g2a Orig. token was "break2" (removed and used token1) n3 14. 0 thirty2.n3s <--- ORIG. MISSING 15. 0 hello2.n3c5 <--- 11636 hello1.n3c5 ORIG. MISSING 16. 0 steer2.n3c7 <--- 15520 steer1.n3c7 ORIG. MISSING 17. 0 gain2.n3n <--- 12800 gain1.n3n ORIG. MISSING 18. 0 no1.n3n <--- 10842 no2.n3n ORIG. MISSING 19. 0 south1.n3n <--- 8192 south2.n3n ORIG. MISSING 20. 0 eight1.n3q <--- 13312 eight2.n3q ORIG. MISSING 21. 0 thirty2.n3s <--- 14848 thirty2.n3s ORIG. MISSING 22. 0 fix1.n3w <--- 10880 fix2.n3w ORIG. MISSING 23. 0 nav2.n3w <--- 10624 nav1.n3w ORIG. MISSING 24. 0 white2.n3w <--- 12928 white1.n3w ORIG. MISSING 25. 0 destin10.n3t <--- 24080 destin11.n3t ORIG. MISSING 26. 0 east2.n3t <--- 12380 east4.n3t ORIG. MISSING n2 27. 0 change2.n2c <--- 17024 change1.n2c ORIG. MISSING 28. 0 ten2.n2c <--- 10880 ten1.n2c ORIG. MISSING 29. 0 south2.n2q <--- 15232 south1.n2q ORIG. MISSING 30. 0 thirty2.n2q <--- 11264 thirty1.n2q ORIG. MISSING 31. 0 freeze11.n2t <--- 8576 freeze9.n2t ORIG. MISSING 32. 0 hello5.n2t <--- 7936 hello7.n2t ORIG. MISSING n1 33. 0 oh1.n1n <--- 10548 oh2.n1n ORIG. MISSING 34. 0 south2.n1q <--- 7296 south1.n1q ORIG. MISSING 35. 0 three1.n1w <--- 13056 three2.n1w ORIG. MISSING b1 36. 0 steer1.b1c7 <--- 15744 steer2.b1c7 ORIG. MISSING 37. 0 break1.b1n <--- 8604 break2.b1n ORIG. MISSING 38. 0 go2.b1s <--- 14336 go1.b1s ORIG. MISSING 39. 0 point7.b1t <--- 11070 point9.b1t ORIG. MISSING 40. 0 six10.b1t <--- 19840 six12.b1t ORIG. MISSING 11264 on1.b1c7 <--- on1.b1c7-OH renamed;file still exists in dir. 41. 11392 on2.b1c7 <--- 11392 on1.b1c7 MISSING, since ORIG Wrong Label b2 42. 0 wide1.b2a <--- 8064 wide2.b2a ORIG. MISSING 43. 0 hello2.b2n <--- 20992 hello1.b2n ORIG. MISSING 44. 0 degree5.b2t <--- 12544 degree7.b2t ORIG. MISSING 45. 0 eighty6.b2t <--- 11264 eighty4.b2t ORIG. MISSING 46. 19102 fifty6.b2t <--- fifty6.b2t-FIFTY extra word "an" removed b3 47. 0 oh2.b3f <--- 4224 oh1.b3f ORIG. MISSING 48. 0 degree2.b3l <--- 9088 degree1.b3l ORIG. MISSING 49. 0 eight1.b3q <--- 8192 eight2.b3q ORIG. MISSING 50. 0 help4.b3t <--- 7040 help6.b3t ORIG. MISSING 30634 nav1.b3s <--- nav1.b3s-NAVE.NAV.EXTRA.WORD 51. 20558 nav1.b3s <--- nav1.b3s-NAVE extra word "nave" removed