java - Parsing LIUM Speaker Diarization Output -
how can know speaker spoke how time using lium speaker diarization toolkit?
for example, .seg file.
;; cluster s0 [ score:fs = -33.93166562542459 ] [ score:ft = -34.24966646974656 ] [ score:ms = -34.05223781565528 ] [ score:mt = -34.32834794609819 ] seq06 1 0 237 f s u s0 seq06 1 2960 278 f s u s0 ;; cluster s1 [ score:fs = -33.33289449700619 ] [ score:ft = -33.64489165914674 ] [ score:ms = -32.71833169822944 ] [ score:mt = -33.380835069917275 ] seq06 1 238 594 m s u s1 seq06 1 1327 415 m s u s1 seq06 1 2311 649 m s u s1 ;; cluster s2 [ score:fs = -33.354874450638064 ] [ score:ft = -33.46618707052516 ] [ score:ms = -32.70702429201772 ] [ score:mt = -33.042146088874844 ] seq06 1 832 495 m s u s2 seq06 1 1742 569 m s u s2
how can extract times file?
in line
seq06 1 2960 278 f s u s0
you have
field 1: 19981217_0700_0800_inter_fm_dga = show name field 2: 1 channel number field 3: 1 start of segment (in features) field 4: 317 length of segment (in features) field 5: f speaker gender (u=unknown, f=female, m=male) field 6: s type of band (t=telephone, s=studio) field 7: u type of environment (music, speech only, …) field 8: spk0 speaker label
times in features, 2960 29.60 seconds (divide 100 convert features seconds). length in features, segment length 2.78 seconds.
documented in lium wiki
Comments
Post a Comment